A MINI PROJECT

On
AN ADAPTIVE GENETIC ALGORITHM FOR PERSONALIZED ITINERARY PLANNING
RECOMMENDATION-MACHINE LEARNING
BACHELOR OF TECHNOLOGY
IN
COMPUTER SCIENCE AND ENGINEERING
BY
BUDDIGA RUTHVIK AKASH - 20VE1A05J8
GOTTIMUKKULA CHATURYA - 20VE1A05L2
SEETHA SMITHI - 20VE1A05N9
PONNALA VAMSHI - 21VE5A0522
Under the Guidance of
Mr. N SANTHOSH RAMCHANDER - Associate professor
Department of CSE
ACADEMIC BATCH: (2020-2024)
AN ADAPTIVE GENETIC ALGORITHM FOR
PERSONALIZED ITINERARY PLANNING
RECOMMENDATION
-MACHINE LEARNING

CONTENTS
● Abstract
● Problem Statement
● Existing System
● Disadvantages
● Proposed System
● Advantages
● Literature Survey
● Queries
ABSTRACT
Traveling as a very popular leisure activity enjoyed by many people all over the world. Typically, tourists
have different kinds of preferences about their itineraries, limited time budgets, unfamiliar with the wide
range of Points-of-Interest (POIs) in a city, so that planning an itinerary is quite tedious, time-consuming,
and challenging for them. In this project, we propose an adaptive genetic algorithm for personalized
itinerary planning for travelers to plan their itineraries better. Firstly, desired starting POIs (e.g., POIs that
are close to their hotels and destination POIs (e.g., POIs that are near train stations or airports) are
considered in our approach. Secondly, we also take some general factors into account that travelers would
consider in their preferences of an itinerary, which are mandatory POls, the total number of POls, the overall
POI popularity, the overall cost, and the overall rating. Thirdly, we view this kind of recommendation task
as a Multi-Objective Optimization problem, and we propose an adaptive genetic algorithm with the
crossover and mutation probabilities (AGAM) for solving this problem to better find the best global
solution.
Fourthly, we allocate different weights to every factor which considered in our project to generate a
personalized itinerary recommendation for better meet many kinds of preferences of tourists. Finally, we
compare our approach against baselines on real-world datasets which include six touristic cities, and the
experimental results show that the AGAM achieves better recommendation performance in terms of the
mandatory POIs, total POI visits, overall POI popularity, total travel time (including travel time and visit
duration), overall cost, and overall rating.
PROBLEM STATEMENT
The project aims to address the challenges faced by tourists while planning personalized itineraries for
their leisure travels. Tourists often have diverse preferences, limited time budgets, and are unfamiliar with
the multitude of Points-of-Interest (POIs) in a city. Planning an itinerary that optimizes their preferences
and constraints becomes tedious, time-consuming and challenging.
To tackle this problem, the project proposes an adaptive genetic algorithm for personalized itinerary
planning. The algorithm considers the following key factors in generating itineraries:

● Desired Starting POIs: POIs that are close to the tourists' hotels, ensuring convenient and efficient
travel arrangements.
● Destination POIs: POIs located near train stations or airports, enhancing travel logistics for reaching
their destinations.
● General Factors: Several factors are taken into account, which are significant in travelers' itinerary
preferences:
a. Mandatory POIs: Places that must be included in the itinerary.
b. Total number of POIs: The overall number of POIs to be visited during the trip.
c. Overall POI popularity: Popularity ratings of POIs, considering the appeal of different attractions.
d. Overall cost: Budget considerations for the trip.
e. Overall rating: Ratings reflecting the overall quality of POIs.
The project treats the personalized itinerary planning as a Multi-Objective Optimization problem. By

employing the adaptive genetic algorithm with carefully tuned crossover and mutation probabilities (AGAM),

the aim is to find the best global solution efficiently.To cater to diverse preferences, the project assigns

different weights to each factor considered during itinerary generation. This customization ensures that the

recommended itineraries align more closely with various tourists' preferences.To evaluate the effectiveness of

the proposed approach, the project conducts experiments on real-world datasets from six touristic cities. The

AGAM is compared against baseline methods, and the results showcase superior recommendation

performance in terms of mandatory POIs, total POI visits, overall POI popularity, total travel time (including

travel time and visit duration), overall cost, and overall rating.

In summary, the project seeks to provide a solution that alleviates the challenges of itinerary planning for

travelers, offering personalized recommendations that balance preferences, constraints, and convenience,

ultimately enhancing the overall travel experience.

EXISTING SYSTEM
Recent works have shown the effectiveness of geotagged photos in improving the itinerary
recommendation performance. In particular, the main idea of these approaches is to learn a sequence of
POIs and consider many factors such as user interest, POI popularity, POI category, and trip constraints
like time and cost for constructing the itinerary planning models. However, most of these works are
proposed based on the Orienteering Problem (OP) or traveling salesman problem (TSP) variants.
Besides, they usually indicate the attraction of a single POI and consider user interest based on the
review rating or the number of times a user has visited a place. The itinerary planning problems have
been proved to be NP-hard and challenging.
This is why the evolution approaches such as Genetic Algorithms (GA) have received increasing
attention in this area recently. The previous works on the itinerary recommendations use GA to solve
such search and optimization problems. The robustness of GA is due to its capacity to locate the
optimum in a multimodal landscape. Even GA is a powerful stochastic optimizer specialized in
planning. Nevertheless, it still exhibits the shortcomings of the fixed crossover and mutation
probabilities.
DISADVANTAGES
● This system indicates the attraction of a single POI and considers user interest
based on the review rating or the number of times a user has visited a place.
● The itinerary planning problems have been proved to be NP-hard and
challenging.
● The planning becomes complicated while working through travelling
salesman problem or even Orienteering Problem
● However,evolution approaches such as Genetic Algorithms (GA) have
received increasing attention in this area ,but this also exhibits the
shortcomings of the fixed crossover and mutation probabilities.
PROPOSED SYSTEM
To address gaps in existing works, we formulate our personalized itinerary recommendation problem as a
MultiObjective Optimization (MOO) problem. An itinerary is defined as a path, which connected by specified starting
POI and ending POI, and at least one other POI is contained. A good personalized itinerary planning is to recommend
a tour that contains as many mandatory POIs and other POIs as possible, makes user’s visit duration maximized
within a time budget, makes overall popularity and overall rating maximized, and keeps user’s cost on POI entrance
as less as possible. Hence, mandatory POIs are the term of the most popular and special POIs that a tourist must be
visited for a successful tour. We also determine the measure of the popularity of POI from the average photo
frequency at each POI and the measures of the user interest and the visit duration of all POIs from the average photo
frequency of the user by leveraging the large collection of geotagged photos available online. We propose a novel
approach named AGAM, which is based on an adaptive genetic algorithm with the crossover and mutation
probabilities, for solving our personalized itinerary recommendation problem. The factors for consideration should be
given not only to the cost budget, time limitations, and starting/ending POIs, but also regards all the factors that
tourists are interested in. All the above factors including mandatory POIs, the distance between POIs, and the length
of the tour are considered to support tourists’ demands.
Especially, the popularity of POIs and user interest by the user’s photo average photo frequencies from the Flickr
photos, the rating of POIs in the sight reviews from the TripAdvisor, the time/distance between POIs from the
Google Maps, and POIs list from the Wikipedia, these factors convey useful information regarding users’
interests and habits. We try to make realistic itineraries and satisfy the tourists’ demands as much as possible.
ADVANTAGES

● We overcome the crossover and mutation probabilities existing in the previous

system,thus eliminating the chances of any tamperings in the accurate results
LITERATURE SYSTEM

● An Adaptive Genetic Algorithm for Personalized Itinerary Planning

- P.Yochum, Liang Chang, Tianlong Gu, Manli Zhu, Hongliang Chen
Published 2020
QUERIES ?