Secure Demand and Price Prediction Model for Ride Hailing Apps Using User Encrypted Data

Rapid development of online ride-hailing services has transformed inner-city transportation which presents new difficulties and opportunities in the allocation of the transportation resources as well as in the pricing scheme. The goal of this paper is to bring together the existing techniques, models, and technologies that are being used to predict demand and price for online riding apps. We investigate different machine learning and statistical tools, such as time series analysis, regression models, neural networks, and deep learning algorithms, in which we discuss the positive effects and the drawbacks of each method. Also, the paper focuses on other factors such as willingness of the drivers, age of the vehicle, location of the passenger, and number of other passengers bought on the ride and their influence on the prediction of passenger demand. The roles of real-time data integration, as well as the application of dynamic pricing algorithms consequently, are discussed. Through a comprehensive review of the present research and the indication of the key directions and voids, the article is expected to direct studies in the future and promote the development of ride-hailing platforms by way of more accurate service and user satisfaction.