Booking Prediction Models for Peer-to-peer Accommodation Listings using Logistics Regression, Decision Tree, K-Nearest Neighbor, and Random Forest Classifiers

摘要: Background: Literature in the peer-to-peer accommodation has put a substantial focus on listings' price determinants. Developing prediction models related to demand for listings is vital revenue management because accurate and forecasts will help determine best responses. Objective: This study aims develop booking likelihood of listings. Methods: Using an Airbnb dataset, we developed four machine learning models, namely Logistics Regression, Decision Tree, K-Nearest Neighbor (KNN), Random Forest Classifiers. We assessed using AUC-ROC score model development time by ten-fold three-way split cross-validation procedures. Results: In terms average score, Classifiers outperformed other evaluated models. three-ways procedure, it had 15.03% higher than 2.93 % KNN, 2.38% Regression. 26,99% 4.41 3.31% Regression.  It should be noted that Tree lowest but smallest time. Conclusion: The performance random forest predicting most superior. can used owners improve their