Optimizing Flight Booking Decisions through Machine Learning Price

Predictions

Table of Contents
1 INTRODUCTION
1.1 Overview
A brief description about your project
1.2 Purpose
The use of this project. What can be achieved using this.
2 Problem Definition & Design Thinking
2.1 Empathy Map
Paste the empathy map screenshot
2.2 Ideation & Brainstorming Map
Paste the Ideation & brainstorming map screenshot
3 RESULT
Final findings (Output) of the project along with screenshots.
4 ADVANTAGES & DISADVANTAGES
List of advantages and disadvantages of the proposed solution
5 APPLICATIONS
The areas where this solution can be applied
6 CONCLUSION
Conclusion summarizing the entire work and findings.
7 FUTURE SCOPE
Enhancements that can be made in the future.

8 APPENDIX
A. Source Code
Attach the code for the solution built.
 Optimizing Flight Booking Decisions through Machine Learning Price
Predictions

1. INTRODUCTION

People who work frequently travel through flight will have better knowledge on

best discount and right time to buy the ticket.

1.1 Overview

Currently, everyone loves to travel by flights. Going along with the study, the

charge of travelling through a plane change now and then which also includes the day and

night time. Additionally, it changes with special times of the year or celebration seasons.

There are a few unique elements upon which the cost of air transport depends. The

salesperson has data regarding each of the variables, however, buyers can get confined

information which is not sufficient to foresee the airfare costs. Considering the provisions,

for example, time of the day, the number of days remaining and the time of take-off this

will provide the perfect time to purchase the plane ticket.

1.2 Purpose

For the business purpose many airline companies change prices according to the

seasons or time duration. They will increase the price when people travel more. Estimating

the highest prices of the airlines data for the route is collected with features such as

Duration, Source, Destination, Arrival and Departure. Features are taken from chosen

dataset and in the price where in the airline price ticket costs vary overtime. A Flight price

prediction application which predicts fares of flight for a particular date based on various

parameters like Source, Destination, Stops & Airline.

 Optimizing Flight Booking Decisions through Machine Learning Price
Predictions

2. Problem Definition & Design Thinking

2.1 Empathy Map

 Optimizing Flight Booking Decisions through Machine Learning Price
Predictions

2.2 Ideation & Brainstorming Map

Data Collection
& Preparation

Data Pre-processing

Data Analysis

Model Building

Test Data Train Data

KNN, SVR, DecisionTree

Models

Hypertune the Modes

Validation - RandomSearch CV

Performance Evaluation
 Optimizing Flight Booking Decisions through Machine Learning Price
Predictions

3. RESULT

The dataset for flight price prediction is collected from the URL

https://www.kaggle.com/code/anshigupta01/flight-price-prediction/data. The

project is implemented in Python.

Optimizing Flight Booking Decisions through Machine Learning Price
Predictions
 Optimizing Flight Booking Decisions through Machine Learning Price
Predictions

4. ADVANTAGES & DISADVANTAGES

Advantages

Nowadays, the number of people using flights has increased significantly. It is

difficult for airlines to maintain price since price change dynamically due to different

conditions. Hence, machine learning algorithms solving this issue by predicting flight

price.

It helps the customers to predict the flight prices and plan their journey accordingly.

Disadvantages

Many of the flight price predictor algorithms heavily rely on historical flight data to

make their predictions of cheap flights and ticket prices.

The accuracy of the machine learning algorithms vary based on the training and

testing data.

5. APPLICATIONS

 Airlines predict the price of the flight.

 Customers can predict the flight prices

6. CONCLUSION

The Machine Learning models can be used to predict prices of flights based on

earlier data more correctly. The presented project reflects the dynamic change in the cost of

flight tickets from which one can get the information about the increase or decrease in the

price as per the days, weekends, and the time of the day. With the ML algorithm applied on

flight datasets, better results can be obtained for prediction. RandomForestRegression

method yielded the highest accuracy of 68.74%.

 Optimizing Flight Booking Decisions through Machine Learning Price
Predictions

7. FUTURE SCOPE

The accuracy of the model can be further increased by applying neural network

models including CNN.

8. APPENDIX A.

Source Code