Understanding regional characteristics through crowd preference and confidence mining in P2P accommodation rental service

This research intends to look at the regional characteristics through an analysis of crowd preference and confidence, and investigates how regional characteristics are going to affect human beings at all aspects in a scenario of sharing economy. The purpose of this paper is to introduce an approach to provide an understandable rating score. Furthermore, the paper aims to find the relationships between different features classified in this study by using machine learning methods. Furthermore, due to the importance of performance of methods, the performance of the features is also improved.

The Rating Matching Rate (RMRate) approach is proposed to provide score in terms of simplicity and understandability for all features. The relationships between features can be extracted from accommodation data set using decision tree (DT) algorithms (J48, HoeffdingTree, and REPTree). Usability of these methods was evaluated using different metrics. Two techniques, “ClassBalancer” and “SpreadSubsample,” are applied to improve the performance of algorithms.

Experimental outcomes using the RMRate approach show that the scores are very easy to understand. Three property types are very popular almost in all of selected countries in this study (“apartment”, “house”, and “bed and breakfast”). The findings also indicate that “Entire home/apt” is the most common room-type and 4.5 and 5 star-rating are the most given star-rating by users. The proposed DT algorithms can find the relationships between features significantly. In addition, applied CB and SS techniques could improve the performance of algorithms efficiently.

This study gives precise details about the guests’ preferences and hosts’ preferences. The proposed techniques can effectively improve the performance in predicting the behavior of users in sharing economy. The findings can also help group decision making in P2P platforms efficiently.