A Study of Machine Learning Based Approach for Hotels’ Matching

Abstract

AbstractHotels’ matching is a big challenge faced by the actors of the business of selling hotels such as online travel agencies (OTAs), tour operators (TO) and Business to Business (B2B) companies. Nowadays, machine learning classification is used for numerous tasks and it can help to classify a pair of hotels as identical or different. In this paper, we described different approaches and techniques applied in hotel data matching and we proposed a solution which combines machine learning classification and text similarity algorithms. The machine learning algorithms used in this study are logistic regression (LR), naive Bayes (NB), support vector machine (SVM), k-nearest neighbours (KNN), decision tree (DT) and random forest (RF). The obtained results show the performance of our model in terms of accuracy, precision, recall and F1 score. The best results were obtained with the help of random forest and decision tree classifiers where all performance metrics values are greater than 99%.KeywordsHotel matchingEntity resolutionMachine learningText similarity