0% found this document useful (0 votes)
20 views36 pages

STC Final

Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
0% found this document useful (0 votes)
20 views36 pages

STC Final

Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 36

A

Seminar Report

on

Implementation of Generative Artificial Intelligence in


Predicting Flight Rates for Customers
Submitted in partial fulfillment of the requirement for the Third Year of
Bachelor degree in Computer Engineering

BY

Mr Kaushal Vyas (3327)


TE Computer A
Under the guidance of
Prof Sushama A Shirke

DEPARTMENT OF COMPUTER ENGINEERING

Army Institute of Technology, Pune

Alandi Rd, Dighi Hills, Pune - 411015

Savitribai Phule Pune University

2024-25
Army Institute of Technology, Pune
DEPARTMENT OF COMPUTER ENGINEERING

Certificate
This is to certify that the Seminar entitled

“Implementation of Generative Artificial Intelligence in Predicting Flight


Rates for Customers”

has been completed by

Mr Kaushal Vyas (3327)

of TE COMPUTER A in Semester I of the academic year 2024-2025 in partial


fulfilment of the Third Year of Bachelor's degree in Computer Engineering as
prescribed by the Savitribai Phule Pune University.

Prof Sushama A Shirke Dr Sunil Dhore


Seminar Guide Head of Department

Place: AIT Pune.

Date: 09/10/2024

2
Acknowledgement

I am very grateful for the invaluable support and guidance I have received along
the course of this project. The successful completion of this seminar report
wouldn’t have been possible without the help of many people, whose
contributions supported my ideas from not remaining basic mediocre concepts
and advanced concrete ideas.

Firstly, I sincerely thank my seminar guide, Prof. Sushma A Shirke, for her
continuous direction and support in our work. Her insightful feedback, helped
mold this report into its final form. I am especially thankful for her guidance,
even with her busy schedule, which build the foundation for developing an
innovative and effective approach to AI-based flight price prediction.

I am also deeply thankful to the teaching staff of the Computer Engineering


Department for their continuous encouragement and expert guidance, which
significantly contributed to the completion of this seminar report. My heartfelt
appreciation also goes out to my seniors, whose knowledgeable support
provided clarity and confidence as I navigated the challenges of this research.

A special thanks to Dr. Sunil Dhore, Head of the Computer Engineering


Department, for his valuable counsel and leadership throughout my research
journey. His advice was crucial in refining the direction of this project.

Lastly, I would like to extend my deepest thanks to everyone who has helped
me, directly or indirectly, in bringing this seminar work to fruition. Your support
has been essential in making this endeavour a success, and for that, I am
sincerely grateful.

Kaushal Vyas (3327)


TE Computer A

3
Abstract

Flight price prediction has historically been a significant challenge due to the volatile and
unpredictable nature of the aviation industry. Numerous factors, like fluctuating demand, fuel
rates, competition, and even geopolitical events, make it difficult to predict airfare accurately.
In response to these challenges, this technical report dives into the application of Generative
Artificial Intelligence (GenAI) to enhance the accuracy and reliability of flight price
predictions. The focus is on five key components that make this possible: Generative AI,
Deep Learning, Real-Time Forecasting, Long Short-Term Memory (LSTM), and Recurrent
Neural Networks (RNN).

Generative AI serves as the backbone of the system by analyzing vast amounts of historical
airfare data, learning from intricate pricing patterns and market behavior, and generating
highly accurate predictions. Through the use of GenAI, the model becomes adept at
identifying trends, anomalies, and cyclical patterns within the data, allowing it to forecast
future prices with greater precision. The deep learning aspect, particularly through the
integration of LSTM and RNN architectures, plays a crucial role in processing sequential and
temporal data, which is essential for capturing the time-sensitive nature of price fluctuations
in the airline industry.

LSTM and RNN models are designed to handle the complexities of time-series data by
retaining information over extended periods, allowing the system to remember past pricing
trends and apply them to future predictions. This adaptability is vital in a market where
conditions change rapidly and unpredictably. For instance, LSTM networks can remember
long-term dependencies, while RNNs excel at understanding short-term variations, making
this hybrid architecture highly effective for dynamic pricing environments like airline fare
prediction.

Incorporating real-time forecasting capabilities further enhances the system's effectiveness by


ensuring that it continuously updates its predictions based on the most current market data.
This feature is critical in an industry where prices can change by the minute due to demand
surges, seat availability, or changes in external factors like fuel prices or weather conditions.
By integrating real-time data streams, the system can provide dynamic and accurate fare
predictions that reflect the latest market trends, offering substantial value to airlines, travel
agencies, and customers alike.

Overall, by combining GenAI with LSTM, RNN, and real-time forecasting, this approach
effectively tackles the inherent volatility of the aviation market. This report aims to provide
valuable insights for key stakeholders in the travel industry, including airlines looking to
optimize their pricing strategies, travel agents seeking to provide better booking options, and
customers hoping to find the best time to purchase tickets at competitive prices.

Keywords: Generative AI, Deep Learning, Real-time Forecasting, Long Short-Term Memory
(LSTM), Recurrent Neural Network, Airfare Prediction, Dynamic Pricing.

4
Contents

Abstract…………………………………………………………………………………………….. 4

1. INTRODUCTION 7
1.1 Introduction………………………………………………………………………... 7
1.2 Challenges with Traditional Price Prediction Models…………………………….. 7
1.3 Advancements in Artificial Intelligence and Deep Learning……………………... 8
1.4 The Role of LSTM and RNN Architectures………………………………………. 8
1.5 Importance of Real-Time Forecasting…………………………………………….. 9
1.6 Motivation and Approach…………………………………………………………. 9
1.7 Objective…………………………………………………………………………... 9

2. LITERATURE SURVEY
2.1 Generative AI for Real-Time Flight Price Prediction……………………………... 10
2.2 Hybrid Models for Time-Series Forecasting……………………………………… 10
2.3 Energy Forecasting and Its Implications for Airfare Prediction…………………... 10
2.4 Handling Price Spikes in Dynamic Environments………………………………... 11
2.5 Optimal Flight Ticket Purchase Timing Using Learning to Rank Methods………. 11
2.6 Holistic Approaches to Airfare Prediction Using Machine Learning……………... 11
2.7 Survey on Flight Pricing Prediction Using Machine Learning……………………. 11
2.8 Framework for Predicting Airfare Prices Using ML……………………………… 12
2.9 Flight Fare Prediction Using XGBoost……………………………………………. 12
2.10 Optimal Purchase Timing Models for Airline Tickets…………………………….. 12
2.11 Airfare Analysis and Prediction Using Data Mining……………………………… 12
2.12 Flight Fare Prediction System Using ML…………………………………………. 13
2.13 Research Paper Analysis…………………………………………………………... 13
2.14 Conclusion of Literature Survey…………………………………………………... 21

3. METHODOLOGY 22
3.1 Search Strategy……………………………………………………………………. 22
3.2 Inclusion Criteria………………………………………………………………….. 22
3.3 Data Extraction and Analysis……………..………………………………………. 23

4. RESULTS 24
4.1 Overview of the Selected Studies…………………………………………………. 24
4.2 Identified Problems in Implementation…………………………………………… 27

5. DISCUSSION 28
5.1 Synthesis of Findings……………………………………………………………… 28
5.2 Implications for Practice…………………………………………………………... 28

5
5.3 Solutions to the Identified Problems………………………………………………. 29
5.4 Future Research Directions………………………………………………………... 30

6. CONCLUSION 31

7. REFERENCES 32

6
CHAPTER 1 - Introduction

1.1 Introduction

The aviation industry`s dynamic and enormously unstable pricing shape is moderated via way
of means of fluctuating demand, gas rate volatility, aggressive pressures, and complicated
direction logistics. These variables make flight rate prediction a chalenging undertaking for
airways, journey agents, and purchasers. Even minor modifications can appreciably effect
price price tag rates, affecting purchasers trying the first-class offers and airways striving to
maximise sales and optimize seat allocations. With the industry's growth, correct flight rate
forecasting is more and more more crucial. Data-pushed decision-making is vital, making
real-time flight rate predictions crucial for stakeholders. Whether optimizing pricing
strategies, providing the first-class offers, or timing price price tag purchases, predictive
fashions are primary to journey planning, aid allocation, and sales management. Precision in
rate prediction is more and more more important because the aviation marketplace turns into
greater aggressive, appreciably impacting commercial enterprise approach efficiency.

1.2 Challenges with Traditional Price Prediction Models

Traditional techniques for predicting flight charges, which include rule-primarily based
totally structures and statistical fashions, have constantly fallen quick in adapting to the rapid
and unpredictable modifications withinside the aviation marketplace. These techniques
regularly rely upon static variables and ancient trends, failing to account for actual-time
fluctuations and tricky marketplace conditions. As a result, they battle to seize the
complicated pricing styles encouraged with the aid of using elements like gasoline charges,
macroeconomic trends, seasonal tour call for, competitor actions, and route-precise logistics.
This results in suboptimal projections, inflicting airways to overlook sales possibilities and
customers to poorly time their price price tag purchases.

Moreover, those traditional techniques falter while confronted with the nonlinear behaviors
inherent in airfare pricing. For instance, an airline would possibly hike charges in reaction to
growing gasoline fees however later lessen them to stimulate call for on underbooked flights.
Without the capacity to constantly analyze from new data, static fashions are insufficient for
taking pictures those rapid, unpredictable shifts. This hole in forecasting accuracy
underscores the want for greater superior procedures that may adapt to dynamic pricing
environments in actual time.

7
1.3 Advancements in Artificial Intelligence and Deep Learning

Advancements in synthetic intelligence (AI), mainly Generative AI (GenAI) and deep


gaining knowledge of, gift promising answers to the demanding situations of risky airfare
pricing. AI fashions excel at reading and processing tremendous historic statistics, figuring
out styles too complicated for conventional methods. Leveraging deep gaining knowledge of
architectures, those structures research from numerous marketplace factors, which includes
real-time competitor pricing, seasonal call for shifts, and outside monetary events, to generate
greater correct and dynamic fee forecasts.

Generative AI is mainly awesome for producing sensible predictions through modeling the
complicated interaction of a couple of factors. GenAI structures simulate destiny pricing
situations primarily based totally on historic statistics at the same time as incorporating
real-time changes, permitting airways and tour corporations to make knowledgeable
selections through watching for fee shifts. When mixed with deep gaining knowledge of
strategies like Recurrent Neural Networks (RNNs) and Long Short-Term Memory (LSTM)
networks, AI fashions end up even greater powerful. These architectures are designed to
manner sequential and temporal statistics, critical for taking pictures evolving pricing trends.

1.4 The Role of LSTM and RNN Architectures

LSTM and RNN architectures are specially well-acceptable for the mission of flight rate
prediction due to the fact they may be adept at coping with time-collection data. These
fashions have the precise capacity to "remember" styles from preceding pricing cycles and
follow them to destiny predictions. LSTMs, in particular, are first-rate at keeping long-time
period dependencies, making them best for reading rate developments that span weeks or
maybe months. On the alternative hand, RNNs are noticeably powerful at taking pictures
short-time period fluctuations in pricing data, which include last-minute fare modifications
that would arise because of unexpected shifts in call for or supply.

By combining LSTM and RNN architectures, the AI machine can procedure each long-time
period developments and short-time period variations, permitting it to constantly adapt to
evolving marketplace conditions. This adaptability is particularly crucial withinside the
aviation industry, in which fees can differ more than one instances an afternoon relying on
elements like reserving window and last seat availability. By integrating those architectures,
the AI machine can generate noticeably accurate, real-time forecasts that replicate the
maximum cutting-edge marketplace conditions.

8
1.5 Importance of Real-Time Forecasting

One of the maximum wonderful improvements in AI-pushed structures is their capacity to


forecast in actual time. Traditional fashions, which depend on static historic information,
frequently warfare to conform to unexpected marketplace shifts. In contrast, AI fashions with
actual-time forecasting abilties are continuously up to date with stay information streams,
taking into account on-the-fly prediction adjustments. This is helpful in an enterprise wherein
costs can alternate inside mins because of elements like aggressive pricing or last-minute seat
availability.

For airlines, actual-time forecasting allows dynamic pricing techniques that maximize sales
with the aid of using adjusting costs in reaction to actual-time demand. For consumers, it
approach the danger to stable the fine offers with well timed notifications whilst fares are
predicted to upward thrust or drop. Travel corporations can use those structures to provide
customized pricing recommendations, improving consumer delight and boosting reserving
rates.

1.6 Motivation and Approach

The exponential upward push in air journey is palpable. I`ve clocked greater flights
withinside the final years than withinside the preceding eighteen! Stumbling upon my
number one studies paper on Flight Price Prediction piqued my interest and drove me to
delve deeper into the complex technique of price price tag pricing, the myriad elements
influencing it, and the way AI can play a transformative role.

My method become straightforward: discover the important thing elements affecting airline
pricing, assemble diverse pricing data, behavior a literature survey on present prediction
mechanisms, and discover the gaps that gift possibilities for improvement.

1.7 Objective

This record`s number one goal is to delve into using Generative AI (GenAI) to beautify flight
rate prediction accuracy, highlighting the mixing of deep getting to know fashions like LSTM
and RNN. It examines how those state-of-the-art prediction strategies address the specific
demanding situations of unstable airfare pricing. By using historic data, real-time forecasting,
and adaptable AI frameworks, the proposed machine strives to supply specific and well timed
airfare predictions. These insights are supposed to advantage airlines, journey agencies, and
purchasers with the aid of using refining decision-making processes, optimizing pricing
strategies, and supporting clients steady the great deals. The the rest of the record will cowl
the AI-primarily based totally machine's methodology, software results, and implications for
the aviation industry, imparting an intensive examine how AI can revolutionize flight rate
prediction in a fiercely aggressive and dynamic market.

9
CHAPTER 2 - Literature Survey

The aviation industry`s dynamic and unstable nature has fueled developing hobby in making
use of Artificial Intelligence (AI) and Machine Learning (ML) to flight fee prediction.
Traditional airfare prediction strategies fall brief in shooting the complicated pricing styles
formed with the aid of using fluctuating demand, gas prices, competitor actions, and
route-particular logistics. Consequently, researchers are turning to superior AI techniques,
which includes Generative AI (GenAI), Deep Learning, Recurrent Neural Networks (RNNs),
and Long Short-Term Memory (LSTM) networks, to beautify prediction accuracy in
real-time environments. This literature survey examines the important thing research
withinside the field, highlighting their methodologies, findings, and implications for the
destiny of flight fee prediction.

2.1 Generative AI for Real-Time Flight Price Prediction

In Guan`s (2024) have a look at, the researcher introduces a Generative AI-primarily based
totally internet platform for real-time airfare prediction. This platform makes use of deep
getting to know fashions inclusive of RNNs and LSTMs to manner temporal records. By
leveraging GenAI, the machine can are expecting destiny rate developments with excessive
accuracy, reaping benefits consumers, airlines, and tour groups alike[4,6]. The integration of
interest mechanisms and real-time forecasting talents lets in the machine to dynamically
replace predictions primarily based totally on modern marketplace developments, making it
specifically powerful in addressing the volatility of the aviation industry.

2.2 Hybrid Models for Time-Series Forecasting

Yang et al. (2022) gift a hybrid version for fuel rate forecasting, combining Lasso regression
and Convolutional Neural Networks (CNN) to beautify prediction accuracy[2,3]. Although
the have a look at specializes in fuel prices, the version's ability to manner time-collection
records the usage of Lasso regression for variable choice and CNNs for sample reputation is
adaptable for flight rate forecasting. This combo of strategies gives a sturdy framework for
predicting rate fluctuations in risky markets, showcasing the capacity of hybrid fashions
withinside the aviation sector.

2.3 Energy Forecasting and Its Implications for Airfare Prediction

Hong et al. (2020) offer an intensive assessment of forecasting strategies withinside the
strength sector, emphasizing the achievement of probabilistic fashions and ensemble
strategies. Though targeted on strength markets, the parallels with the airline industry's
dynamic pricing are evident. By integrating probabilistic forecasting with AI, destiny airfare

10
prediction structures may want to extra efficiently manipulate marketplace volatility and the
myriad elements impacting prices, inclusive of outside monetary shifts and gasoline costs.

2.4 Handling Price Spikes in Dynamic Environments

Zhang et al. (2023) address strength marketplace charge spikes the use of frequency
evaluation and oversampling strategies to enhance prediction accuracy[11]. For airfare,
wherein expenses can surge all through top tour seasons or holidays, those strategies should
beautify a version`s functionality to expect and adapt to unexpected charge increases. This
technique should refine real-time flight charge forecasting systems, making sure they
efficiently reply to uncommon however sizable charge fluctuations.

2.5 Optimal Flight Ticket Purchase Timing Using Learning to Rank Methods

Oglakcioglu et al. (2023) have a look at Learning to Rank (LTR) strategies to pinpoint the
satisfactory time to shop for flight tickets. Their studies highlights that variables just like the
range of days till departure and direction-particular behaviors are important for predicting
airfare. This locating helps the perception that flight charge prediction fashions ought to
account for dynamic variables that often extrade because the departure date nears. Therefore,
LTR strategies may be precious for optimizing purchaser choices approximately while to buy
tickets primarily based totally on particular direction conditions.

2.6 Holistic Approaches to Airfare Prediction Using Machine Learning

Kalampokas et al. (2023) advise a complete technique to airfare prediction through


integrating Machine Learning (ML), Deep Learning (DL), and Quantum Machine Learning
(QML) strategies to beautify accuracy. They underscore the need of the use of numerous AI
strategies to seize the myriad elements affecting flight expenses, consisting of airline
strategies, outside marketplace conditions, and seasonal demand. This technique shows that
destiny airfare prediction fashions might be extensively progressed through combining more
than one AI frameworks, thereby higher dealing with the complexities of dynamic pricing
environments.

2.7 Survey on Flight Pricing Prediction Using Machine Learning

Rajankar et al. (2019) surveyed numerous system gaining knowledge of algorithms for airfare
prediction, consisting of Support Vector Machines (SVM), Naive Bayes, Decision Trees, and
Linear Regression. They observed that at the same time as a few fashions, like SVM, excel in
static environments, they falter with the dynamic nature of real-time airfare prediction. This

11
examine highlights the need for greater superior fashions able to processing real-time
statistics and constantly updating predictions.

2.8 Framework for Predicting Airfare Prices Using ML

Fadhil et al. (2022) advise a framework that makes use of Decision Trees and K-Nearest
Neighbors (KNN) to expect airfare expenses withinside the Indian airline marketplace. Their
findings imply that Decision Trees excel at shooting the non-linear relationships among
variables like departure date, direction competitiveness, and airline pricing strategies. This
examine highlights the importance of non-linear fashions in forecasting flight expenses in
risky markets.

2.9 Flight Fare Prediction Using XGBoost

Sarao and Samanta (2022) examine numerous ML algorithms of their examine and locate that
XGBoost promises the best accuracy for flight fare prediction. XGBoost's capability to
control large-scale datasets and seize complicated variable interactions makes it a perfect
preference for real-time charge prediction systems. The fulfillment of this version shows that
ensemble gaining knowledge of strategies like XGBoost are surprisingly powerful in
dynamic pricing environments, consisting of the airline industry.

2.10 Optimal Purchase Timing Models for Airline Tickets

Noyon et al. (2023) look into the use of regression-primarily based totally fashions to are
expecting the highest quality timing for getting airline tickets. Their look at underscores the
importance of things like supply and destination, wide variety of stops, and airline-unique
behaviors in figuring out the excellent time to buy. Integrating time-touchy variables into AI
fashions is essential for making correct predictions in real-time dynamic environments.

2.11 Airfare Analysis and Prediction Using Data Mining

Chawla and Kaur (2017) make use of statistics mining strategies to research the elements
affecting airfare pricing, which include oil charges, the wide variety of competitors, and days
till departure. Their comparative evaluation of diverse device studying algorithms
underscores the importance of ancient statistics mining for correct fee forecasting. This
shows that integrating statistics from a couple of reassets should decorate destiny fashions`
effectiveness.

12
2.12 Flight Fare Prediction System Using ML

Finally, Bhosale et al. (2022) gift a flight fare prediction device that applies Random Forest,
Decision Trees, and Linear Regression to forecast price price tag charges withinside the
Indian home airline market​[12-14]. Their paintings underscores the ability of ensemble
strategies and emphasizes the want for greater real-time statistics to enhance version
accuracy.

2.13 Research Paper Analysis

Res. Price Deep Neural Gen Merits Demerits Solutions


Paper Prediction Learning Network AI
No.

1 ✔ ✔ ✔ Real-time Computatio Leveraging cloud


airfare nally computing to
forecasting, expensive manage
high accuracy processing costs

2 ✔ ✔ ✔ Hybrid model Model Simplified


improves complexity pre-processing of
accuracy for time series data
gasoline price
prediction

3 ✔ ✔ ✔ Comprehensiv Difficulties Hybrid


e energy in handling approaches using
forecasting very volatile LSTM and CNN
using multiple data for better
sources volatility
handling

4 ✔ ✔ ✔ Short-term Struggles Incorporating


price spikes with external
captured well longer-term macroeconomic
with frequency forecasting indicators for
analysis long-term
forecasting

13
5 ✔ ✔ ✔ Accurate May not Fine-tuning
timing for generalize algorithms for
purchasing well across specific airline
flights using different routes
Learning to airlines
Rank methods

6 ✔ ✔ ✔ Holistic High model Implementing


machine training time efficient training
learning due to deep mechanisms
approach that learning
accounts for complexity
multiple
factors

7 ✔ ✔ Survey Lacks Applying


provides a implementat machine learning
good ion of models to real
foundation for advanced data
understanding algorithms
flight pricing

8 ✔ ✔ ✔ Framework for Limited to Utilizing


airfare historical generative models
prediction is data and for real-time data
detailed and may not adaptation
effective adapt well to
real-time

9 ✔ ✔ ✔ Machine Predictive Incorporating


learning accuracy adaptive learning
effectively reduces with for changing
predicts fares drastic market conditions
based on market
historical changes
trends

10 ✔ Focus on the Limited Extending


importance of details on analysis to
machine model include more
learning in application modern machine
pricing learning models

14
11 ✔ ✔ ✔ Combines data Data quality Use of data
mining with affects augmentation
machine model techniques
learning for performance
accurate
predictions

12 ✔ ✔ ✔ ✔ Clear benefits High Employing


from using computation distributed
neural al demand computing to
networks for lower costs
fare prediction

13 ✔ ✔ Overview of Does not Extend


machine focus application to
learning specifically specific domains,
algorithms in on price such as flight
various prediction pricing
contexts

14 ✔ ✔ ✔ Deep learning Not focused Could combine


algorithms on price delay predictions
predict flight prediction with fare
delays predictions
effectively

15 ✔ ✔ ✔ ✔ CNN-BiLSTM High Simplifying


hybrid model complexity network
improves architectures
accuracy for
stock
prediction

16 ✔ ✔ New method Requires Automating


enhances significant feature extraction
energy market feature with deep
price engineering learning
predictions

17 ✔ ✔ ✔ Good Highly Using synthetic


application of dependent data for training
deep learning on when real data is
in financial high-quality limited
forecasting data

15
18 ✔ Multi-source Complexity Streamlining data
urban data in managing pipelines
improves multi-source
dynamic price data
prediction

19 ✔ ✔ ✔ Public Focused on Adapting


transport public methods to air
pricing transport, transportation
strategies are less relevant
well-optimized for flight
prediction

20 ✔ ✔ Dynamic price Difficult to Incorporating


prediction for adapt to market volatility
ride-on-deman highly indicators
d services volatile
markets

21 ✔ ✔ Forecasts Not focused Extend maritime


maritime on flight methods to air
transportation prices transportation
demand
effectively

22 ✔ ✔ ✔ LSTM neural Requires Use data


networks extensive augmentation or
provide strong training data generative models
price for training
forecasting
abilities

23 ✔ ✔ ✔ Local housing Limited Generalize


prices scalability to models for
predicted with other broader market
LSTM markets use

24 ✔ ✔ ✔ Cooperative Not focused Integrate price


transport on price forecasting with
systems forecasting transport time
enhanced with predictions
deep learning

16
25 ✔ ✔ ✔ Strong deep Not Could adapt
learning applicable to methods for fare
techniques for price predictions
travel time prediction
predictions

26 ✔ ✔ ✔ Framework Limited Generalize


effectively scalability framework to
uses ML for across accommodate
airfare price different more airlines
prediction airlines

27 ✔ ✔ Strong ML Not focused Apply methods to


techniques for on price pricing
emission prediction predictions
prediction in
transportation

28 ✔ ✔ ✔ ✔ Accurate Focused on Could adapt


predictions rail transit, methods to
using deep not directly forecast flight
learning for applicable to prices by
passenger flow flight incorporating
in urban rail pricing. similar deep
systems. learning
techniques.

29 ✔ ✔ ✔ Machine Limited to Adapt machine


learning public learning methods
provides transportatio to capture pricing
accurate cost n, not easily trends in airline
predictions for generalizabl sectors.
public bus e to airfares.
services.

30 ✔ ✔ ✔ Strong Limited Transfer the


data-driven applicability data-driven
methods for to the airline approach to
price industry. dynamic flight
forecasting, pricing models.
particularly in
energy sectors.

17
31 ✔ ✔ ✔ Deep learning Not focused Methods could be
accurately on airfare applied to
predicts prediction; forecasting flight
day-to-day mainly pricing with
variations in applicable to proper data
travel demand. large-scale adjustments.
transportatio
n networks.

32 ✔ ✔ ✔ Deep learning Not specific Similar methods


applied for to flight can be adapted
large-scale prices. for airline fare
transport prediction.
networks.

33 ✔ ✔ ✔ Reinforcement Focuses on Reinforcement


learning for ride-on-dem learning could be
dynamic price and services. adapted to airfare
prediction. prediction.

34 ✔ ✔ ✔ Prediction of Highly Simplifying the


transportation complex model could
costs using approach. make it
fuzzy analytic applicable to
and neural airfares.
networks.

35 ✔ ✔ ✔ Neural Not focused Adapt energy


network-based on price demand models
demand prediction. to airline pricing.
prediction for
energy in
transport.

36 ✔ ✔ Variable Limited Could focus on


impact application flight prices by
analysis using to airlines. modifying the
neural model.
networks in
transport.

18
37 ✔ ✔ Neural Focus on Extend the model
network financial to consider flight
analysis of markets price prediction.
share prices rather than
for flight prices.
transportation
companies.

38 ✔ ✔ ✔ Application of Does not Apply


neural focus on sustainability-rela
networks in airfare ted insights to
sustainable prediction. airfares.
transport
systems.

39 ✔ ✔ ✔ Route pricing Limited Simplify the


optimization scalability to model for broader
using neural airfares. use in airline
networks. pricing.

40 ✔ ✔ Comprehensiv No specific Extend the review


e review of focus on to include airfare
neural price models.
networks in prediction.
transportation.

41 ✔ ✔ Comparison of Not focused Apply


neural network on price comparison to
frameworks prediction. flight pricing
for public models.
transport.

42 ✔ ✔ ConvLSTM2D Limited Adapt


architecture focus on ConvLSTM2D
for air cargo passenger for flight price
demand airfares. prediction.
forecasting.

43 ✔ ✔ ✔ Graph neural No price Use graph neural


networks for forecasting. networks for
public transit flight price
demand forecasting.
prediction.

19
44 ✔ ✔ Long-term Focuses on Extend CNN to
prediction energy long-term flight
using CNN predictions. price forecasting.
and
optimizers.

45 ✔ ✔ Neural Focuses on Adapt for


network for cargo, not passenger airfare
Australia's air passenger prediction.
cargo demand. prices.

46 ✔ ✔ ✔ Backpropagati Focuses on Incorporate


on neural demand, not pricing alongside
networks for prices. demand
air passenger predictions.
demand.

47 ✔ ✔ ✔ ✔ Neural Focus on Incorporate fare


network for air fleet, not prediction into
cargo fleet fare the model.
assignment. prediction.

48 ✔ ✔ ✔ Forecasting No focus on Combine demand


demand for price forecasting with
low-cost prediction. price prediction
carriers using models.
neural
networks.

49 ✔ ✔ ✔ Forecast of Lacks Incorporate


Australia's pricing pricing alongside
domestic air integration. demand
travel demand. forecasting.

50 ✔ ✔ ✔ ✔ Flight delay No focus on Integrate delay


prediction price and pricing
using deep prediction. prediction for
learning. more robust
models.

51 ✔ ✔ Comprehensiv Focuses on Adapt ML


e review of freight, not methods for
machine passenger passenger airfare
learning for airfares. forecasting.

20
freight
management.

48 ✔ ✔ Forecasting No focus on Combine demand


demand for price forecasting with
low-cost prediction. price prediction
carriers using models.
neural
networks.

49 ✔ ✔ Forecast of Lacks Incorporate


Australia's pricing pricing alongside
domestic air integration. demand
travel demand. forecasting.

50 ✔ ✔ ✔ ✔ Flight delay No focus on Integrate delay


prediction price and pricing
using deep prediction. prediction for
learning. more robust
models.

51 ✔ ✔ ✔ Comprehensiv Focuses on Adapt ML


e review of freight, not methods for
machine passenger passenger airfare
learning for airfares. forecasting.
freight
management.

2.14 Conclusion of Literature Survey

The reviewed literature lays a strong basis for information the capacity and demanding
situations of AI-primarily based totally flight charge prediction structures. The integration of
Generative AI, deep mastering, and real-time forecasting strategies suggests first rate promise
in enhancing prediction accuracy inside dynamic environments. However, full-size
demanding situations persist, together with facts availability, version adaptability, and
computational efficiency. Future studies have to attention on adaptive mastering structures,
real-time facts integration, and growing extra green AI fashions able to dealing with the
complexities of dynamic airfare pricing. With persevered advancement, those structures
should revolutionize the industry, making sure accurate, well timed predictions and
optimizing decision-making for airlines, journey agencies, and consumers.

21
CHAPTER 3 - Methodology

Following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses
(PRISMA) guidelines, the method for this record encompasses 3 key steps: the hunt strategy,
inclusion criteria, and information extraction and analysis. This systematic method ensures
that the reviewed literature is complete and pertinent to the challenge of flight charge
prediction the use of Generative Artificial Intelligence (GenAI) and deep gaining knowledge
of techniques.

3.1 Search Strategy

A complete seek become performed throughout more than one professional databases,
inclusive of IEEE Xplore, Google Scholar, Elsevier, ACM Digital Library, Springer Library,
and Sci-Hub, to accumulate a big range of literature at the challenge. This ensured get entry
to to each well-hooked up and modern-day studies. The seek targeted on figuring out
applicable papers posted among 2020 and 2024, reflecting the maximum latest improvements
in Generative AI, deep gaining knowledge of, and real-time charge forecasting.

Search phrases have been cautiously decided on to seize a wide variety of subjects associated
with flight charge prediction, at the same time as that specialize in AI-pushed solutions.
These phrases protected mixtures such as “Generative Artificial Intelligence,” “Price
Forecasting,” “Deep Learning,” “Neural Networks,” “Flight Cost Analysis,” and “LSTM
(Long Short-Term Memory Networks).”

The seek aimed to make sure that research addressing each foundational AI technology and
precise packages in flight charge prediction have been captured. By using those key phrases,
the evaluation accumulated applicable literature from diverse disciplines, inclusive of gadget
gaining knowledge of, information science, forecasting, and aviation economics. Each
database become searched the use of those mixtures, making sure the inclusion of applicable
peer-reviewed articles and studies papers from conferences.

3.2 Inclusion Criteria

After compiling the quest results, precise inclusion standards have been carried out to pick
out the maximum applicable research for analysis. Research papers have been protected in
the event that they met the following:

> Published in peer-reviewed journals: Ensuring the research` reliability and credibility.

> Publication Year among 2020 and 2024: Capturing the modern day methodologies and
findings because of speedy AI improvements.

22
> Focus on generative AI and forecasting methods: Emphasizing using Generative
AI/different AI-primarily based totally strategies for enhancing forecasting in pricing models.

> Written in English: Maintaining consistency and heading off translation issues.

By adhering to those standards, the file ensured that the chosen literature turned into each
applicable and of excessive quality, reflecting the modern day improvements withinside the
field.

3.3 Data Extraction and Analysis

Following the identity and filtering of papers the usage of the inclusion criteria, a
standardized records extraction technique changed into employed. Relevant records from the
chosen research changed into accumulated the usage of a dependent shape designed to seize
key factors of every studies work, making sure uniformity withinside the review. The records
extraction centered on:

> Flight Rate Prediction Techniques: Key methodologies used for predicting flight prices,
consisting of diverse fashions like LSTM, RNN, CNN, and XGBoost, and their implemented
AI techniques.

> Generative AI Solutions: Application of Generative AI fashions inclusive of Generative


Adversarial Networks (GANs) and different deep mastering architectures to decorate
prediction accuracy and reliability.

> Gaps in Current Research: Identification of obstacles in present studies, consisting of


demanding situations in real-time forecasting, troubles associated with records availability or
quality, and version adaptability to marketplace volatility.

The purpose of this evaluation changed into to discover not unusualplace themes, strengths,
and obstacles throughout the research. By systematically reading the records, the document
seeks to spotlight the modern country of AI-primarily based totally flight charge prediction
and discover regions for similarly studies and development. This technique changed into
important for information the effectiveness of GenAI and deep mastering fashions in dynamic
pricing environments and offering suggestions for destiny studies directions.

23
CHAPTER 4 - Results

4.1 Overview of the Selected Studies

1. Yuanyuan Guan`s studies explores the software of Generative AI (GAI) to address the
complexities of flight charge prediction in a risky marketplace. Guan demonstrates that
leveraging GAI permits the version to seize tricky styles in ancient airfare records, main to a
greater unique information of things influencing charge fluctuations. Integrating deep
studying architectures, along with Recurrent Neural Networks (RNNs) and Long Short-Term
Memory (LSTM) networks, permits the machine to manner sequential and temporal records,
adapting to converting marketplace traits and improving prediction accuracy.

Guan emphasizes the importance of real-time forecasting, completed via a web-primarily


based totally platform that connects with stay records streams for non-stop updates. The use
of Generative Adversarial Networks (GANs) complements the machine's cappotential to
generate sensible destiny situations primarily based totally on ancient records, imparting
treasured insights for airlines, journey agents, and consumers. This dynamic method permits
the version to stay conscious of marketplace traits, making it an critical device withinside the
aviation industry.

2. Across the 3 documents [2-4], we derived numerous treasured insights at once applicable
to our flight charge prediction version:

From Hu Yang et al.'s studies on fuel charge forecasting, we discovered the significance of
filtering applicable time collection records the usage of strategies like Lasso regression. The
hybrid Lasso-CNN version they suggest displays out inappropriate records, lowering
overfitting and improving prediction accuracy. This method may be followed to refine our
flight charge forecasting version, specializing in impactful variables like seasonality and
marketplace traits.

In document [2], Hong et al.'s assessment of power forecasting emphasizes leveraging


synthetic intelligence and device studying to perceive styles inside ancient records. Their
cognizance on combining probabilistic forecasting and ensemble strategies to enhance
accuracy may be reflected in our flight charge predictions with the aid of using integrating
one of a kind models (e.g., RNN, LSTM) for greater sturdy results in risky pricing
environments.

Lastly, from Zhang et al.'s paper [4] on energy charge forecasting, we amassed methodologies
for managing charge spikes, an difficulty that would stand up with unexpected flight charge
surges. Their use of frequency evaluation and oversampling to expect each ordinary charges
and charge spikes gives a sturdy framework for enhancing forecast reliability. These insights
advocate that our version should advantage from making use of comparable strategies to
stumble on and control uncommon however large charge fluctuations in flight charges.

24
3. Across the 2 papers [5-6], we accumulated key insights to decorate our flight charge
prediction model:

Oglakcioglu et al.`s research [5] on top-rated flight price price tag buy timing famous the
effectiveness of getting to know-to-rank (LTR) techniques for predicting the exceptional
instances to shop for tickets. Their take a look at highlights that the variety of days till
departure considerably influences pricing, various via way of means of path and destination.
This technique can optimize our model's predictions primarily based totally on precise routes
and markets, presenting tourists customized recommendation on while to buy tickets.

Kalampokas et al.'s holistic technique to airfare prediction [6] demonstrates the utility of
Machine Learning (ML), Deep Learning (DL), and Quantum Machine Learning (QML)
fashions. Their evaluation of various airways and locations suggests that various AI fashions
obtain excessive accuracy (89% to 99%) in predicting airfare. Using a couple of AI strategies
addresses the complexities of diverse routes and airways. Introducing QML fashions, a
unique addition to this domain, ought to similarly enhance prediction accuracy and
adaptability.

These insights advocate that integrating LTR, ML, and probably QML can supply pretty
correct charge predictions whilst supplying customers with top-rated buy timing, thinking
about the dynamic and path-precise nature of airfare pricing.

4. Across documents [7-10], we diagnosed key insights that aid our flight charge prediction
efforts:

From Supriya Rajankar et al.'s survey [7] on flight pricing the usage of gadget getting to
know, we see that elements like departure time, days left till departure, and time of day
considerably effect price price tag prices. They emphasize diverse fashions together with
Naive Bayes, SVM, and Linear Regression, noting that SVM carried out the best accuracy at
80.6%, whilst different fashions additionally confirmed promise. This indicates our technique
ought to gain from checking out a couple of fashions to decide the maximum correct
predictor of charge fluctuations in real-time scenarios.

Heba Mohammed Fadhil et al.'s framework [8] evaluates gadget getting to know strategies
for airfare prediction, highlighting that techniques like Decision Trees and K-Nearest
Neighbors (KNN) excel inside the Indian airline network, with Decision Trees reaching 89%
accuracy. The advice to stability accuracy and performance indicates our machine must
appoint a couple of algorithms to decorate prediction accuracy, specifically for often
converting flight routes.

In Parwaz Singh Sarao and Pushpendu Samanta`s work [9], flight charge prediction the usage
of historic information applied ML fashions like Random Forest, Decision Trees, and
XGBoost, with XGBoost yielding the best accuracy at 84.46%. This helps our selection to

25
apply XGBoost and comparable ensemble techniques because of their effectiveness in taking
pictures charge tendencies throughout diverse airways and seasons.

Finally, Md. Shaim Hosan Noyon et al.'s thesis [10] demonstrates the effectiveness of
regression-primarily based totally fashions like XGBoost and Random Forest for
time-collection forecasting in airfare predictions. By that specialize in variables together with
source, destination, variety of stops, and airways, they advanced accuracy for home flights.
These findings spotlight the capacity of comparable ML fashions in our machine, making an
allowance for fine-tuned predictions that dynamically alter primarily based totally on
elements like layovers and path complexity.

5. From the very last papers [11-12], we derived key insights relevant to our flight charge
prediction version:

Chawla and Kaur`s observe [11] highlights the gain of the usage of historic records and
records mining strategies to expect flight charge variations. They recognized key elements,
along with oil costs, variety of competition, and days till departure, that have an effect on
airfare. Their modeling discovered that flights with fewer competition revel in better charge
fluctuations, at the same time as people with greater competition have strong costs. This
means that our version ought to account for direction opposition and different marketplace
variables to beautify prediction accuracy.

Bhosale et al.'s research [12] emphasizes the usage of device gaining knowledge of
algorithms like Random Forest, Decision Trees, and Linear Regression to decide the highest
quality timing for price price tag purchases. Their observe confirmed that positive routes, in
particular business-heavy ones, showcase a non-lowering charge fashion because the
departure date nears, at the same time as different routes display charge dips at particular
times. Incorporating those insights into our version can enhance suggestions for price price
tag buy timing via way of means of that specialize in direction-particular behaviors and
charge patterns.

By integrating those findings, our version can similarly beautify its predictive skills via way
of means of thinking about outside elements like oil costs and opposition at the same time as
tailoring predictions primarily based totally on direction-particular developments and
aggressive behaviors withinside the airline industry.

26
4.2 Identified Problems in Implementation

Here are 3 key demanding situations and destiny guidelines for imposing AI-primarily based
totally prediction structures in actual-time dynamic environments:

1. Data Availability and Quality: Many research spotlight barriers in facts availability,
mainly for actual-time and whole datasets, inclusive of unsold seats, actual-time competition,
or airline-particular algorithms. The absence of essential functions can lessen prediction
accuracy, as cited in papers suffering with incomplete or behind schedule facts sources
[10-11]. Future AI fashions would require extra complete actual-time facts integration from
more than one sources, like airline inventories, competitor behavior, and outside financial
indicators, to make certain correct and well timed predictions.

2. Model Adaptability to Market Volatility: Several papers imply the undertaking of


adapting AI fashions to risky pricing environments, wherein flight charges are prompted with
the aid of using numerous, unexpectedly converting elements like competitor behavior, gas
charges, and marketplace demand. Even the excellent fashions warfare with sudden
marketplace shocks or non-linear events, inclusive of surprising gas charge hikes or
geopolitical events [8, 12]. Future studies must cognizance on growing adaptive fashions that
may react to those shifts, doubtlessly with the aid of using integrating reinforcement
mastering or hybrid fashions that may constantly research from new facts.

3. Computational Efficiency and Real-Time Processing: In a dynamic environment, the


undertaking lies in making actual-time predictions at the same time as retaining excessive
accuracy. Many fashions require tremendous computational resources, and going for walks
them in actual time might also additionally introduce latency. Algorithms like XGBoost,
Random Forest, and Decision Trees, at the same time as correct, are computationally
intensive, complicating actual-time implementation [7, 8]. Future AI structures want to
stability computational performance with prediction accuracy, probable with the aid of using
growing lighter, quicker algorithms or enhancing cloud-primarily based totally infrastructures
that guide actual-time facts processing.

27
CHAPTER 5 - Discussion

5.1 Synthesis of Findings

Across the reviewed papers, numerous not unusualplace topics emerged concerning
AI-primarily based totally flight fee prediction structures:

1. Effectiveness of ML Models: Studies always display that device getting to know (ML)
fashions like XGBoost, Random Forest, Decision Trees, and Support Vector Machines
(SVMs) expect flight fees with vast accuracy. These fashions correctly examine from historic
statistics, pick out fee patterns, and expect primarily based totally on elements along with
departure date, direction competitiveness, oil fees, and the variety of stops. Route-unique
behaviors are critical; for instance, commercial enterprise routes generally tend to observe
non-lowering fee traits toward departure, whilst much less aggressive routes show off extra
variable patterns.

2. Challenges with Data Availability and Quality: A tremendous venture is the provision
and great of statistics, which frequently limits prediction accuracy. Many research lack get
admission to to real-time statistics on unsold seats or airline-unique pricing algorithms,
ensuing in predictions that won't absolutely seize dynamic airline pricing strategies.
Additionally, AI fashions battle to deal with unexpected marketplace shifts, along with
sudden spikes in gas fees or adjustments in call for because of outside events, indicating a
want for extra adaptive getting to know structures.

3. Real-Time Integration: Integrating those effective algorithms into real-time dynamic


environments, along with the airline industry, affords each technical and infrastructural
challenges. Most ML fashions require tremendous computational resources. While they carry
out nicely in simulated environments, real-time processing—wherein flight fees can alternate
inside minutes—needs quicker and extra green structures.

By addressing those topics, AI-primarily based totally flight fee prediction structures may be
in addition delicate and made extra powerful for real-international applications.

5.2 Implications for Practice

The findings from those research have profound implications for the tour industry, reaping
rewards airlines, tour businesses, and clients alike. For airlines, incorporating AI-primarily
based totally prediction structures into sales control techniques permits for greater correct call
for forecasting, optimized seat pricing, and real-time records-pushed pricing adjustments.
This dynamic pricing method maximizes sales at the same time as balancing deliver and call
for.

28
For tour businesses, AI-primarily based totally prediction gear beautify purchaser pleasure
via way of means of presenting correct fare forecasts and advising at the high-quality
instances to buy tickets. This builds purchaser agree with and loyalty, giving businesses a
aggressive edge.

Consumers additionally gain from AI-powered gear, which enhance price price tag charge
transparency. Systems that notify customers of greatest buy instances primarily based totally
on ancient developments and real-time situations assist vacationers keep away from charge
hikes and shop money, making the reserving manner greater consumer-friendly. These AI
fashions also can be carried out to inn bookings, vehicle rentals, and different dynamic
pricing environments, providing a unified platform for tour fee optimization.

However, the constraints highlighted, which includes records availability and the complexity
of integrating AI fashions into real-time structures, imply those technology aren't but
completely mature. Airlines and tour structures ought to put money into higher records
infrastructure, like real-time monitoring of price price tag sales, and beautify computational
performance to completely leverage AI`s ability in real-time charge prediction.

5.3 Solutions to the Identified Problems

1. Data Availability and Access:

> Partner with airways and tour structures to get admission to real-time statistics on unsold
seats, consumer behavior, and last-minute pricing strategies.

> Establish regulatory frameworks for secure, privacy-compliant statistics sharing amongst
competition to decorate statistics availability and prediction accuracy.

2. Model Adaptability:

> Integrate reinforcement mastering (RL) into AI fashions to permit non-stop mastering and
edition to new statistics.

> Develop hybrid AI fashions that integrate deep mastering and probabilistic forecasting to
control each ordinary traits and unpredictable marketplace shifts.

3. Computational Efficiency:

> Optimize algorithms for quicker real-time processing via way of means of growing lighter
AI fashions or utilising cloud computing infrastructure for large-scale statistics managing.

> Implement modular AI structures that separate prediction tasks (e.g., managing charge
spikes independently) to lessen standard computational needs and boost up processing.

29
4. Data Integration:

> Integrate real-time statistics from more than one reassets together with gasoline prices,
competitor prices, and consumer call for traits to decorate prediction accuracy.

5. Consumer-Friendly AI Systems:

> Develop transparent AI models that provide users with insights into how predictions work,
enabling consumers to make informed decisions by real-time price forecasts.

5.4 Future Research Directions

1. Adaptive Learning Systems: Develop reinforcement gaining knowledge of and


self-enhancing neural networks that constantly adapt to converting marketplace situations in
actual time.

2. Efficiency in Real-Time Processing: Optimize light-weight AI fashions for actual-time


environments and discover quantum computing for faster, complicated information
processing.

3. Data Privacy and Ethics: Ensure moral AI use through shielding customer privateness
even as accumulating enough information for correct predictions. Design obvious AI
structures that permit customers to govern how their information is used.

4. Cross-Industry Applications: Apply findings from airfare prediction studies to different


dynamic pricing fashions, which include motel bookings, ride-sharing, and e-commerce.

5. Real-Time Data Enhancement: Investigate actual-time information collecting strategies


and combine IoT (Internet of Things) gadgets to enhance actual-time information series and
prediction fashions throughout sectors.

6. Improving Interpretability: Make AI fashions extra interpretable so stakeholders can


recognize and accept as true with predictions, facilitating wider adoption throughout
industries.

30
CHAPTER 6 - Conclusion

This record delves into the improvement and implementation of AI-primarily based totally structures
for flight charge prediction, emphasizing how Generative AI, gadget gaining knowledge of fashions,
and real-time forecasting strategies deal with the complexities of dynamic pricing withinside the
airline enterprise. By synthesizing findings from 12 key studies, the record highlights the
effectiveness of AI structures in appropriately predicting airfare tendencies via historic statistics,
adaptive gaining knowledge of algorithms, and superior strategies like XGBoost, Random Forest, and
Reinforcement Learning. Despite those advancements, demanding situations like statistics availability,
version adaptability, and computational performance want to be tackled to absolutely harness AI`s
capacity in real-time environments.

For sensible applications, AI structures can substantially advantage airways, tour agencies, and
customers via way of means of improving sales management, dynamic pricing strategies, and
knowledgeable price price tag purchasing. Overcoming cutting-edge limitations, which include
integrating greater real-time statistics and growing faster, greater green AI fashions, is important for
dealing with the speedy fluctuations in airfare pricing.

Proposed answers encompass reinforcement gaining knowledge of, modular AI structures, and
partnerships with statistics vendors to enhance prediction accuracy and adaptability. Future studies
have to prioritize adaptive gaining knowledge of structures, quantum computing, statistics privacy,
and cross-enterprise applications. Extending AI-pushed charge prediction fashions past airways to
sectors like hotels, ride-sharing, and e-trade also can provide tremendous benefits.

In conclusion, even as AI-primarily based totally flight charge prediction structures are effective, their
complete capacity lies in ongoing improvement and refinement. By addressing statistics quality,
real-time processing, and version adaptability demanding situations, destiny AI fashions can offer
greater unique and dynamic predictions, reworking charge forecasting in swiftly converting markets.

31
CHAPTER 7 - References

[1] Y. Guan, "Flight Price Prediction Web-Based Platform: Leveraging Generative AI for Real-Time
Airfare Forecasting," in Journal of Web Engineering, vol. 23, no. 2, pp. 299-314, March 2024, doi:
10.13052/jwe1540-9589.2325.
keywords: {Costs;Generative AI;Atmospheric modeling;Predictive models;Rendering (computer
graphics);Real-time systems;Stakeholders;Flight price prediction;generative artificial
intelligence;deep learning;real-time forecasting},

[2] H. Yang, X. Tian, X. Jin and H. Wang, "A Novel Hybrid Model for Gasoline Prices Forecasting
Based on Lasso and CNN," in Journal of Social Computing, vol. 3, no. 3, pp. 206-218, September
2022, doi: 10.23919/JSC.2022.0012.
keywords: {Couplings; Social computing; Oils; Time series analysis; Neural networks; Predictive
models; Linear programming; gasoline prices; forecasting; Lasso-CNN; multiple time series},

[3] T. Hong, P. Pinson, Y. Wang, R. Weron, D. Yang and H. Zareipour, "Energy Forecasting: A
Review and Outlook," in IEEE Open Access Journal of Power and Energy, vol. 7, pp. 376-388, 2020,
doi: 10.1109/OAJPE.2020.3029979.
keywords: {Forecasting;Wind forecasting;Load forecasting;Wind power generation;Probabilistic
logic;Industries;Open Access;Energy forecasting;load forecasting;electricity price forecasting;wind
forecasting;solar forecasting},

[4] C. Zhang, Y. Fu and L. Gong, "Short-Term Electricity Price Forecast Using Frequency Analysis
and Price Spikes Oversampling," in IEEE Transactions on Power Systems, vol. 38, no. 5, pp.
4739-4751, Sept. 2023, doi: 10.1109/TPWRS.2022.3218712.
keywords: {Predictive models;Support vector machines;Market research;Artificial neural
networks;Time-frequency analysis;Training;Electricity supply industry;Extended discrete Fourier
transform;price spikes;short-term price forecast;variational mode decomposition},

[5] K. Oglakcioglu, Y. S. Can and F. Alagoz, "Prediction of Optimal Flight Ticket Purchase Timing by
Using Learning To Rank Methods," 2023 Innovations in Intelligent Systems and Applications
Conference (ASYU), Sivas, Turkiye, 2023, pp. 1-6, doi: 10.1109/ASYU58738.2023.10296726.
keywords: {Training;Visualization;Machine learning algorithms;Atmospheric modeling;Urban
areas;Pricing;Predictive models;machine learning;flight ticket price;learning to rank;regression.},

[6] T. Kalampokas, K. Tziridis, N. Kalampokas, A. Nikolaou, E. Vrochidou and G. A. Papakostas, "A


Holistic Approach on Airfare Price Prediction Using Machine Learning Techniques," in IEEE Access,
vol. 11, pp. 46627-46643, 2023, doi: 10.1109/ACCESS.2023.3274669.
keywords: {Airline industry;Atmospheric modeling;Predictive models;Companies;Feature
extraction;Prediction algorithms;Pricing;Airfare price;artificial intelligence;deep learning;machine
learning;prediction model;pricing models;regression;quantum machine learning},

[7] Supriya Rajankar, Neha Sakharkar, 2019, A Survey on Flight Pricing Prediction using Machine
Learning, INTERNATIONAL JOURNAL OF ENGINEERING RESEARCH & TECHNOLOGY
(IJERT) Volume 08, Issue 06 (June 2019),

[8] Heba Mohammed Fadhil; Mohammed Najm Abdullah; Mohammed Issam Younis. "A Framework
for Predicting Airfare Prices Using Machine Learning". IRAQI JOURNAL OF COMPUTERS,

32
COMMUNICATIONS, CONTROL AND SYSTEMS ENGINEERING, 22, 3, 2022, 81-96. doi:
https://doi.org/10.33103/uot.ijccce.22.3.8

[9] Gupta, Shikha & Gupta, Nishi & Publication Hub, Tjcse. (2024). Flight Fare Prediction Using
Machine Learning.

[10] Noyon, Md. Shaim Hosan, Islam, Tanzidul, Islam, Solaiman, Reejon, Md. Refayet Islam, Flight
fare prediction using machine learning, http://hdl.handle.net/10361/23256,

[11] Chawla, Bhavuk, and Ms Chandandeep Kaur. "Airfare analysis and prediction using data mining
and machine learning." Int J Eng Sci Invent (IJESI) 6.11 (2017): 10-17.

[12] Sarao, Parwaz, and Pushpendu Samanta. "Flight Fare Prediction Using Machine Learning."
Available at SSRN 4269263 (2022).

[13] Mahesh, Batta. ”Machine Learning Algorithms-A Review.” International Jour nal of Science and
Research (IJSR).[Internet] 9 (2020): 381-386.

[14] Yazdi, Maryam Farshchian, et al. ”Flight delay prediction based on deep learning and
Levenberg-Marquart algorithm.” Journal of Big Data 7.1 (2020): 1-28.

[15] Lu, W., Li, J., Wang, J. et al. A CNN-BiLSTM-AM method for stock price prediction. Neural
Comput & Applic 33, 4741–4753 (2021). https://doi.org/10.1007/s00521-020-05532-z

[16] Homayoun Ebrahimian, Saeed Barmayoon, Mohsen Mohammadi & Noradin


Ghadimi (2018) The price prediction for the energy market based on a new method, Economic
Research-Ekonomska Istraživanja, 31:1, 313-337, DOI: 10.1080/1331677X.2018.1429291

[17] Hu, Z.; Zhao, Y.; Khushi, M. A Survey of Forex and Stock Price Prediction Using Deep
Learning. Appl. Syst. Innov. 2021, 4, 9. https://doi.org/10.3390/asi4010009

[18] Suiming Guo, Chao Chen, Jingyuan Wang, Yaxiao Liu, Ke Xu, Daqing Zhang, and Dah Ming
Chiu. 2018. A Simple but Quantifiable Approach to Dynamic Price Prediction in Ride-on-demand
Services Leveraging Multi-source Urban Data. Proc. ACM Interact. Mob. Wearable Ubiquitous
Technol. 2, 3, Article 112 (September 2018), 24 pages. https://doi.org/10.1145/3264922

[19] Branda, F.; Marozzo, F.; Talia, D. Ticket Sales Prediction and Dynamic Pricing Strategies in
Public Transport. Big Data Cogn. Comput. 2020, 4, 36. https://doi.org/10.3390/bdcc4040036

[20] Guo, S., Chen, C., Wang, J. et al. Fine-grained Dynamic Price Prediction in Ride-on-demand
Services: Models and Evaluations. Mobile Netw Appl 25, 505–520 (2020).
https://doi.org/10.1007/s11036-019-01308-5

[21] Wei Huang, Jing Hu, Shaorui Zhou, min Zhao, Demand prediction and sharing strategy in
resilient maritime transportation: Considering price and quality competition, Ocean & Coastal
Management, Volume 242, 2023, 106676, ISSN 0964-5691,
https://doi.org/10.1016/j.ocecoaman.2023.106676.

33
[22] Zhang, Kexian, et al. "Forecasting crude oil price using LSTM neural networks." Data Sci.
Financ. Econ 2 (2022): 163-180.

[23] Kim, Hyunsoo, Youngwoo Kwon, and Yeol Choi. "Assessing the impact of public rental housing
on the housing prices in proximity: Based on the regional and local level of price prediction models
using long short-term memory (LSTM)." Sustainability 12.18 (2020): 7520.

[24] M. -Y. Chen, H. -S. Chiang and K. -J. Yang, "Constructing Cooperative Intelligent Transport
Systems for Travel Time Prediction With Deep Learning Approaches," in IEEE Transactions on
Intelligent Transportation Systems, vol. 23, no. 9, pp. 16590-16599, Sept. 2022, doi:
10.1109/TITS.2022.3148269.

[25] Liu, Yanjun, et al. "Understanding urban bus travel time: Statistical analysis and a deep learning
prediction." International Journal of Modern Physics B 37.04 (2023): 2350034.

[26] Wang, Tianyi, et al. "A framework for airfare price prediction: a machine learning approach."
2019 IEEE 20th international conference on information reuse and integration for data science (IRI).
IEEE, 2019.

[27] Ji, Tianbo, et al. "Urban transport emission prediction analysis through machine learning and
deep learning techniques." Transportation Research Part D: Transport and Environment 135 (2024):
104389.

[28] Xiong, Zhi, et al. "Passenger flow prediction of urban rail transit based on deep learning
methods." Smart Cities 2.3 (2019): 371-387.

[29] Amicosante, Andrea, et al. "Predicting costs of local public bus transport services through
machine learning methods." Expert Systems with Applications (2024): 125396.

[30] Patel, Harsh, and Manan Shah. "Energy consumption and price forecasting through data-driven
analysis methods: A review." SN Computer Science 2.4 (2021): 315.

[31] Cheng, Qixiu, et al. "Analysis and forecasting of the day-to-day travel demand variations for
large-scale transportation networks: a deep learning approach." Transportation Analytics Contest,
Tech. Rep (2016).

[32] Cheng, Qixiu, et al. "Analysis and forecasting of the day-to-day travel demand variations for
large-scale transportation networks: a deep learning approach." Transportation Analytics Contest,
Tech. Rep (2016).

[33] Guo, Suiming, et al. "Seeking in Ride-on-Demand Service: A Reinforcement Learning Model
With Dynamic Price Prediction." IEEE Internet of Things Journal (2024).

[34] Singh, Akash, et al. "Prediction of transportation costs using trapezoidal neutrosophic fuzzy
analytic hierarchy process and artificial neural networks." IEEE Access 9 (2021): 103497-103512.

34
[35] Maaouane, Mohamed, et al. "Using neural network modelling for estimation and forecasting of
transport sector energy demand in developing countries." Energy conversion and management 258
(2022): 115556.

[36] Abdou, Hussein A., et al. "A variable impact neural network analysis of dividend policies and
share prices of transportation and related companies." Journal of International Financial Markets,
Institutions and Money 22.4 (2012): 796-813.

[37] Abdou, Hussein A., et al. "A variable impact neural network analysis of dividend policies and
share prices of transportation and related companies." Journal of International Financial Markets,
Institutions and Money 22.4 (2012): 796-813.

[38] Nandal, Mohit, Navdeep Mor, and Hemant Sood. "An overview of use of artificial neural
network in sustainable transport system." Computational Methods and Data Engineering: Proceedings
of ICMDE 2020, Volume 1 (2021): 83-91.

[39] Du, Yu-Ang. "Research on the route pricing optimization model of the car‐free carrier platform
based on the BP neural network algorithm." Complexity 2021.1 (2021): 8204214.

[40] Dougherty, Mark. "A review of neural networks applied to transport." Transportation Research
Part C: Emerging Technologies 3.4 (1995): 247-260.

[41] Heghedus, Cristina, Antorweep Chakravorty, and Chunming Rong. "Neural network frameworks.
comparison on public transportation prediction." 2019 IEEE International Parallel and Distributed
Processing Symposium Workshops (IPDPSW). IEEE, 2019.

[42] Anguita, Juan Gerardo Muros, and Oscar Díaz Olariaga. "Air cargo transport demand forecasting
using ConvLSTM2D, an artificial neural network architecture approach." Case Studies on Transport
Policy 12 (2023): 101009.

[43] Li, Can, et al. "Graph neural network for robust public transit demand prediction." IEEE
Transactions on Intelligent Transportation Systems 23.5 (2020): 4086-4098.

[44] Yao, Shunyu, Yi-Peng Xu, and Ehsan Ramezani. "Optimal long-term prediction of Taiwan’s
transport energy by convolutional neural network and wildebeest herd optimizer." Energy Reports 7
(2021): 218-227.

[45] Baxter, Glenn, and Panarat Srisaeng. "The use of an artificial neural network to predict
Australia’s export air cargo demand." International Journal for Traffic and Transport Engineering 8.1
(2018): 15-30.

[46] Chen, Shu-Chuan, et al. "Improving the forecasting accuracy of air passenger and air cargo
demand: the application of back-propagation neural networks." Transportation Planning and
Technology 35.3 (2012): 373-392.

[47] Ye, Choong-Yeol. "A neural network approach to air cargo fleet assignment." Proceedings of the
KOR-KST Conference. Korean Society of Transportation, 2001.

35
[48] Srisaeng, Panarat, Glenn S. Baxter, and Graham Wild. "Forecasting demand for low cost carriers
in Australia using an artificial neural network approach." Aviation 19.2 (2015): 90-103.

[49] Srisaeng, Panarat, Glenn Baxter, and Graham Wild. "Using an artificial neural network approach
to forecast Australia's domestic passenger air travel demand." World Review of Intermodal
Transportation Research 5.3 (2015): 281-313.

[50] Yu, Bin, et al. "Flight delay prediction for commercial air transport: A deep learning approach."
Transportation Research Part E: Logistics and Transportation Review 125 (2019): 203-221.

[51] Barua, Limon, Bo Zou, and Yan Zhou. "Machine learning for international freight transportation
management: A comprehensive review." Research in Transportation Business & Management 34
(2020): 100453.

36

You might also like