A Recommendation System based on Clustering and Classification for Optimal Trajectory Analysis

Moving objects such as people, animals, and vehicles have generated a huge amount of spatiotemporal data by using location-capture technologies and mobile devices. There is a high demand to analyze this collected data and extract the desired knowledge. In this study, we apply several data mining techniques on a trajectory dataset such as clustering, classification, sequential pattern mining, and time series analysis. Our model can detect the movement patterns of taxi trips in Porto city. We apply the Naïve Bayes classifier to predict the traffic status of each trip. We perform qualitative and quantitative analysis for our clustering method, then we evaluate the accuracy of the Naïve Bayes classifier. Finally, we discuss the implications of our methodology in terms of traffic jams, energy consumption, and air pollution. Our analysis results can be used to build a recommender system which can be beneficial for taxi drivers, passengers, and transportation authorities.