AI- Powered Itinerary generator with route optimization

A Major Project Review Report-2

Submitted By:
(21BT04003) Aditya Pasari
(21BT04004) Ahir Nidhikumari Maganbhai
(21BT04045) Ayaz Memon

In partial fulfillment of the requirement for the award of

the degree
of
Bachelor of Technology In
Semester VIII-Computer Science and Engineering(AI/ML)
At

Department of Computer Science and Engineering

School of Technology

GSFC University,
Vigyan Bhavan, P. O. Fertilizer Nagar,
Vadodara - 391750, Gujarat, India
November 2024
 ABSTRACT

This project focuses on developing an AI-powered itinerary generator that helps travelers create
personalized and optimized travel plans. The system considers various factors such as user
preferences, location data, time constraints, and budget to provide a well-structured itinerary. By
integrating machine learning techniques and optimization algorithms, the tool efficiently
prioritizes destinations and schedules activities to enhance the travel experience.

A key feature of the system is route optimization, achieved using the Traveling Salesman
Problem (TSP) algorithm, which helps minimize travel distance and time while ensuring
maximum convenience. The AI adapts dynamically to real-time changes, such as traffic
conditions, delays, or user modifications, making the itinerary more flexible and efficient.

This intelligent travel planner is designed to assist both tourists and frequent travelers by offering
a cost-effective and time-saving solution. With an intuitive interface and real-time adaptability,
the system enhances trip planning, reduces unnecessary travel efforts, and ensures a seamless and
enjoyable journey.

SOT/CSE/MAJORPROJECT/IDP/UDP/2024-25/33
2
 INDEX

CHAPTER 1 : INTRODUCTION................................................................................................4
CHAPTER 2 : PROBLEM STATEMENT..................................................................................5
1. Objective................................................................................................................................ 5
2. Need for Solution...................................................................................................................6
CHAPTER 3 : LITERATURE REVIEW....................................................................................7
CHAPTER 4 : UML DIAGRAMS............................................................................................... 9
1. Use case diagram................................................................................................................. 10
2. Use case scenarios................................................................................................................10
3. Class diagram.......................................................................................................................12
CHAPTER 5 : TOOLS AND TECHNOLOGY TO BE USED............................................... 13
1. Programming Language:......................................................................................................13
3. APIs & Web Services:......................................................................................................... 13
4. Optimization Algorithm:......................................................................................................13
5. Data Handling & Storage:....................................................................................................13
6. Regular Expressions (Regex):..............................................................................................14
7. Automation & Requests Handling:......................................................................................14
8. Development Environment:................................................................................................. 14
CHAPTER 6 : CONCLUSION.................................................................................................. 15

SOT/CSE/MAJORPROJECT/IDP/UDP/2024-25/33
3
 CHAPTER 1 : INTRODUCTION

Travel planning is an essential yet challenging task that requires careful consideration of multiple
factors, such as selecting destinations, optimizing routes, managing time effectively, and staying
within budget. Traditional methods of itinerary planning often involve manual research and
scheduling, which can be tedious and inefficient. Travelers frequently struggle with deciding the
best order in which to visit places, estimating travel times, and adjusting plans dynamically when
unexpected changes occur. These challenges highlight the need for an intelligent system that
simplifies and optimizes the process.

This project introduces an AI-powered itinerary generator with route optimization, designed to
create efficient, personalized travel plans based on user preferences, time availability, and
financial constraints. By leveraging Artificial Intelligence (AI) and machine learning algorithms,
the system analyzes various factors, including user interests, location data, and real-time
constraints, to generate an optimized itinerary that ensures a seamless travel experience.

A key aspect of this system is route optimization, achieved through the Traveling Salesman
Problem (TSP) algorithm. This algorithm helps determine the shortest and most efficient route
between multiple destinations, reducing unnecessary travel time and improving overall trip
efficiency. Additionally, the system adapts dynamically to real-time conditions such as traffic
congestion, weather changes, or modifications in user preferences, ensuring an optimal and
flexible travel schedule.

The proposed solution aims to provide significant benefits for both tourists and frequent travelers
by enhancing convenience, reducing planning efforts, and ensuring cost-effective travel. Whether
a user is exploring a new city for leisure or planning a business trip with tight schedules, the
system offers an intuitive and intelligent way to manage travel plans efficiently.

By integrating AI-driven decision-making and optimization techniques, this project seeks to

revolutionize the way individuals plan and experience travel. The system’s ability to generate
adaptive, data-driven itineraries ensures that users can make the most of their trips without the
hassle of manual planning. This review report explores the design, methodology,
implementation, and impact of the AI-powered itinerary generator, highlighting its effectiveness
in transforming travel planning into a smarter and more user-friendly process.

SOT/CSE/MAJORPROJECT/IDP/UDP/2024-25/33
4
 CHAPTER 2 : PROBLEM STATEMENT

1. Objective

The objective of this project is to develop an AI-powered itinerary generator with route
optimization to assist travelers in planning efficient and personalized trips. The system aims to
automate the travel planning process by considering user preferences, time constraints, budget,
and real-time conditions.

Key objectives include:

●​ Personalized Itinerary Generation – Create customized travel plans based on user

interests, location, and available time.
●​ Route Optimization – Utilize the Traveling Salesman Problem (TSP) algorithm to
determine the shortest and most efficient travel routes.
●​ Time and Cost Efficiency – Minimize travel time and expenses by optimizing the
sequence of destinations.
●​ Real-Time Adaptability – Adjust itineraries dynamically based on factors such as traffic,
weather, or last-minute changes.
●​ User-Friendly Interface – Provide an intuitive platform that allows users to input
preferences and receive optimized travel plans effortlessly.
●​ Scalability and Versatility – Ensure the system is suitable for different types of travelers,
including tourists, business professionals, and frequent commuters.

By achieving these objectives, the project aims to enhance the overall travel experience by
making trip planning more convenient, efficient, and adaptable to real-world conditions.

SOT/CSE/MAJORPROJECT/IDP/UDP/2024-25/33
5
2. Need for Solution

Travel planning is often a complicated and lengthy process, requiring you to choose a
destination, book transportation, plan your itinerary and manage your budget. Customary
methods, involving manual research and scheduling, frequently lead to inefficiencies like
extended travel times, increased expenses and poorly organized itineraries. Travelers often battle
to find optimal routes and change to unexpected changes while maximizing their time.

AI-powered itinerary generators offer automated, smart and efficient travel planning, thus
solving these problems through route optimization. Several factors account for this system
requirement.

Less effort is also needed.

Substantially improved travel routes.

There is personalization.

Complete real-time adaptability

Thorough and mindful deliberation of cost-effectiveness is analytically important.

Improved travel experiences.

The AI-powered solution improves travel planning by dealing with key challenges, thus
providing greater convenience, efficiency and flexibility. Discerning tourists, busy business
travelers and frequent commuters especially value this tool for its ability to guarantee smooth
and well-organized travel.

SOT/CSE/MAJORPROJECT/IDP/UDP/2024-25/33
6
 CHAPTER 3 : LITERATURE REVIEW

Sr. No Title of Paper Name of Methodology Advantages Disadvantag

Author/Aut used es
hors

1 Enhanced travel Komal Data-driven - Improved - Requires

experience using Londhe, approach decision-ma large
artificial intelligence: Nikita king datasets for
A data-driven Dharmadhik - accuracy
approach ari, Parth Personalized - Privacy
Zaveri, Unal travel concerns
Sakoglu insights regarding
- Optimized user data
travel routes

2 Transforming Erke Aribas, Generative - Highly - Dependence

Personalized Travel Evren AI, personalized on accurate
Recommendations: Daglarli Personality recommenda personality
Integrating Generative Models tions data
AI with Personality - Improved - Potential
Models user biases in
satisfaction AI-generate
- AI-driven d
automation suggestions

3 Transforming Travel Chandra Generative - Optimized -Computation

Planning: The Impact Sekhar AI, itinerary ally
of Generative AI Veluru Itinerary planning expensive
Optimization - - Requires
Cost-effectiv real-time
e travel data for
solutions accuracy
- Enhanced
user
engagement
Models

4 Design of Travel Peilin Chen Artificial - Efficient - Limited

Itinerary Planning Intelligence travel adaptability
System Based on itinerary to sudden
Artificial Intelligence planning changes in

SOT/CSE/MAJORPROJECT/IDP/UDP/2024-25/33
7
 - Automated plans
scheduling - Requires
- AI-driven continuous
route updates
optimization

5 Travel Itinerary Ankita Artificial - Automated - Dependency

Planner Using AI Mudhale, Intelligence itinerary on AI
Madhuri creation accuracy
Shirmale, - - Limited
Vedant Time-saving customizati
Kudalkar, travel on options
Rishikesh planning in some
Motiray, - Reduced cases
Sharique human effort
Ahmad

SOT/CSE/MAJORPROJECT/IDP/UDP/2024-25/33
8
 CHAPTER 4 : UML DIAGRAMS

1. Use case diagram

Here is the use case diagram for the AI- Powered Itinerary generator with route optimization. It
visually represents the interactions between the actors and the various use cases within the
system.

SOT/CSE/MAJORPROJECT/IDP/UDP/2024-25/33
9
2. Use case scenarios
●​ User Inputs Travel Preferences
○​ The user enters trip details like type (Sightseeing, Food, Shopping), budget, and
hotel location.
○​ The system stores this information.

●​ System Recommends Places

○​ The system analyzes user preferences and selects the best places based on ratings,
cost, and type.
○​ It suggests 3 main places and 2 food spots (if needed).

●​ System Optimizes Travel Route

○​ The system gets distances between places using Google Maps API.
○​ It calculates the shortest route using the TSP algorithm.

●​ User Reviews and Confirms Itinerary

○​ The user checks the suggested places and route.
○​ They can modify or confirm the final plan.

●​ User Receives Final Plan

○​ The system provides a detailed itinerary with places, routes, and estimated time.
○​ The user can download or share the plan.

●​ Real-time Adjustments (Future Feature)

○​ If traffic or weather changes, the system suggests an updated route.
○​ The user gets notifications and can adjust the plan.

SOT/CSE/MAJORPROJECT/IDP/UDP/2024-25/33
10
3. Class diagram

Here is the class diagram for the AI- Powered Itinerary generator with route optimization. Which
shows the core system that recommends places and generates optimal travel routes, Place that
Represents a tourist location or restaurant, with attributes like cost, rating, and type,
RouteOptimizer that handles travel route optimization using distance matrix and TSP algorithm,
User that represents the traveler providing preferences and budget details.

SOT/CSE/MAJORPROJECT/IDP/UDP/2024-25/33
11
4. Timeline Diagram

Here is the timeline diagram for the AI- Powered Itinerary generator with route optimization. It
shows the time-details of the projects. It shows the timeline or we can say the start time and end
time for the project for different deliverables of the project.

SOT/CSE/MAJORPROJECT/IDP/UDP/2024-25/33
12
5. Sequence Diagram

This sequence diagram shows the flow of interactions between objects in the AI- Powered
Itinerary generator with route optimization over time. This diagram shows how different
components of this system communicate with each other. The sequence diagram shows how the
different components of the project will interact with each other as well as the user.

SOT/CSE/MAJORPROJECT/IDP/UDP/2024-25/33
13
6. Activity Diagram

This activity diagram of AI- Powered Itinerary generator with route optimization shows
step-by-step process how the system will work from start to end. It is helpful in understanding
the whole process of the system. This diagram is also known as process flow diagram, this
diagram explains the whole process for the system which will be followed at time of user
interaction.

SOT/CSE/MAJORPROJECT/IDP/UDP/2024-25/33
14
 CHAPTER 5 : TOOLS AND TECHNOLOGY TO BE USED
1. Programming Language:

Python – Python serves as the core engine for our itinerary generation logic. It was responsible
for tasks such as loading and processing data, interacting with APIs, computing travel times,
managing time slots (like meals or breaks), and ultimately generating optimized travel
sequences. We selected Python due to its simplicity, wide ecosystem of libraries, and suitability
for rapid data processing and prototyping.

.2. Data Processing & Analysis:

Pandas – Used extensively to handle structured data stored in CSV files — including places of
interest, ratings, categories, and estimated costs. Pandas allowed for flexible filtering, sorting,
and grouping of data based on user preferences.

NumPy – Although not the centerpiece, NumPy was used for efficient handling of numerical
operations behind the scenes, especially when working with arrays or time-based calculations.

3. APIs & Web Services:

Google Maps API (Directions API) –This API will play a crucial role by supplying route details,
travel times, distances, and traffic-adjusted ETAs between each waypoint. These responses
formed the backbone of our itinerary timing logic.

Google Places & Geocoding APIs – We will integrate to enrich place details (like photos,
cuisines, and tags) and to convert user-supplied addresses into precise geographic coordinates.

4. Optimization Algorithm:

Traveling Salesman Problem (TSP) Algorithm – We will implement a simplified version of the
Traveling Salesman Problem to determine the most efficient route through a list of selected
destinations. While not brute-force (to avoid excessive API calls), the algorithm balanced route
optimality with responsiveness.

5. Data Handling & Storage:

CSV Files – We will use CSV files as a lightweight and transparent form of data storage. All
points of interest, their metadata (name, type, cost, rating), and timing estimates were stored
here.This method simplified collaboration and version control for our team, especially during
initial development phases.

SOT/CSE/MAJORPROJECT/IDP/UDP/2024-25/33
15
6. Regular Expressions (Regex):

re module (Python) – Regex will be used to parse and clean strings returned from the Google
Maps API (e.g., "1 hour 25 mins"). These were then converted into structured time formats (in
minutes) for calculations related to arrival/departure planning.

7. Automation & Requests Handling:

Requests Library (Python) – This library was used to handle all communication with external
APIs. We built logic around request retries, error handling, and response caching to ensure stable
and efficient data fetching.

8. Development Environment:

Colab – is invaluable in the initial phases of backend development. It will allow the team to
collaborate on code, experiment with data analysis, and visualize results (maps, charts) quickly
and effectively.

SOT/CSE/MAJORPROJECT/IDP/UDP/2024-25/33
16
 CHAPTER 6 : CONCLUSION
The AI-Driven Itinerary Generator makes travel planning easy and efficient. It helps users find
the best places based on their interests, budget, and time constraints. Using Google Maps API
and the TSP algorithm, the system ensures the shortest and most cost-effective route.

By automating itinerary creation, it saves time, reduces travel costs, and enhances the overall
travel experience. This tool is useful for tourists and frequent travelers, providing a smooth and
optimized journey. In the future, it can be improved with real-time adjustments based on traffic
and weather updates.

SOT/CSE/MAJORPROJECT/IDP/UDP/2024-25/33
17