THOR: A Hybrid Recommender System for the Personalized Travel Experience

Abstract

One of the travelers’ main challenges is that they have to spend a great effort to find and choose the most desired travel offer(s) among a vast list of non-categorized and non-personalized items. Recommendation systems provide an effective way to solve the problem of information overload. In this work, we design and implement “The Hybrid Offer Ranker” (THOR), a hybrid, personalized recommender system for the transportation domain. THOR assigns every traveler a unique contextual preference model built using solely their personal data, which makes the model sensitive to the user’s choices. This model is used to rank travel offers presented to each user according to their personal preferences. We reduce the recommendation problem to one of binary classification that predicts the probability with which the traveler will buy each available travel offer. Travel offers are ranked according to the computed probabilities, hence to the user’s personal preference model. Moreover, to tackle the cold start problem for new users, we apply clustering algorithms to identify groups of travelers with similar profiles and build a preference model for each group. To test the system’s performance, we generate a dataset according to some carefully designed rules. The results of the experiments show that the THOR tool is capable of learning the contextual preferences of each traveler and ranks offers starting from those that have the higher probability of being selected.

Adaptive KNN-Based Extended Collaborative Filtering Recommendation Services

“…Collaborative filtering techniques are commonly employed by recommendation systems to provide personalized recommendations based on the prior behavior of users and their preferences [1][2][3][4]. However, recent studies have identified several drawbacks and challenges that need to be addressed.…”

“…One significant problem is the cold start issue, where the system struggles to make recommendations for new items or users with no prior interaction history, resulting in poor performance and usability for novice users [5,6]. To overcome this challenge, innovative strategies such as a hybrid recommendation system combining collaborative filtering with content-based algorithms and performance enhancements are being developed [2,4,5]. Another challenge faced by collaborative filtering is the sparsity problem, where there are not enough overlapping user-item interactions to produce reliable recommendations, which can occur in large datasets or for specialized products that are not widely used.…”