International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395-0056 Volume: 11 Issue: 05 | May 2024
www.irjet.net
p-ISSN: 2395-0072
Developing a smart travel recommendation system through AI-enhanced software engineering Sweety Rajeshkumar Dhabaliya1, Prof. Bhoomi Mansukhlal Bangoria2 1PG Scholar, Computer Science and Engineering, Dr. Subhash University, Gujarat, India 2Assistant Professor, Information Technology, Dr. Subhash University, Gujarat, India
--------------------------------------------------------------------------***------------------------------------------------------------------------directions in the field. By leveraging AI technologies, Abstract
recommendation systems continue to evolve, recommending more appropriate and individualized material to clients.
Travel recommendations has always been an essential part of human life, going back to the earliest days of civilization when people traveled for a variety of reasons. Initially, recommendations were based on the collective experiences of the community. The development of modern recommender systems corresponded with as information technology advances, it is influencing every industry and service sector, including travel and tourism. Generic recommender engines were the first on the path, followed by personalized recommender systems and contextualized personalization with the development of artificial intelligence. The use of social media is also on the rise in the modern day, and big data from these platforms is becoming a crucial resource for many analytics, recommender systems included. This study's features, limits, and evolution of travel recommender systems are all covered in length in this publication. We also used the algorithms which are used in classification and recommendation systems, also metrics which can be used to assess how well the algorithms—and hence the recommenders—perform.
A travel recommendation system is a technological tool designed to assist users in finding personalized travel suggestions based on their preferences, constraints, and historical behavior. These systems leverage different techniques from machine learning, data mining, and artificial intelligence to analyze large amounts of data, including user profiles, destination information, reviews, and ratings. Through collaborative filtering, content-based filtering, or hybrid approaches, these systems can generate tailored recommendations, such as destinations to visit, accommodations to stay in, activities to engage in, and even transportation options. By considering factors like user demographics, past travel experiences, interests, budget, and time constraints, these systems aim to provide relevant and accurate suggestions to improve the overall travel planning experience. Additionally, incorporating features like real-time updates, social interactions, and location-based services can further enrich the recommendation process, ensuring that users receive timely and contextually relevant suggestions. Travel recommendation systems plays an important role in simplifying travel decision-making, optimizing itinerary planning, and ultimately enhancing the overall travel experience for users.
KEYWORDS:
Recommender System, Artificial Intelligence, Destination Recommendation, Hybrid recommender system
1. Introduction and Background In rapidly developing countries such as India, the travel and tourism industry has grown to be one of the largest service sectors in recent years. Now a days Artificial Intelligence can be very useful for recommendation. Artificial Intelligence (AI) has revolutionized recommendation systems by enabling them to analyze large amounts of data and provide personalized recommendations. AI-powered recommendation systems use machine learning algorithms to understand user preferences and behavior, thereby raising the recommendations’ effectiveness and accuracy. This paper explores the role of AI in recommendation systems, including the algorithms used, challenges faced, and future
© 2024, IRJET
|
Impact Factor value: 8.226
Research in recommender systems faces several key challenges and areas for improvement. One significant issue is the lack of high-quality and exclusive recommender systems capable of providing personalized recommendations across diverse domains. This limitation restricts the ability of recommender systems to offer tailored suggestions, impacting user satisfaction and engagement. Additionally, the limited availability and quality of datasets for evaluating recommender system performance pose a significant challenge. Without access to comprehensive and high-quality datasets, IT could be difficult for researcher to evaluate their recommender’s
|
ISO 9001:2008 Certified Journal
|
Page 1474