click here to download project abstract/base paper
ABSTRACT
Ride-on-demand (RoD) services are becoming more and more common, such as Uber and OLA cabs. To help both drivers and customers, RoD services use dynamic pricing to balance supply and demand in an attempt to increase service quality. Dynamic prices, however, often generate problems for passengers: often “unpredictable” prices prevent them from easily making fast decisions. In order to address this problem, it is therefore important to give passengers more detail, and forecasting dynamic prices is a feasible solution. Taking the Rapido dataset as an example in this paper, we focus on the estimation of dynamic prices, forecasting the price for each individual passenger order. Predicting prices will help passengers understand whether they could get a lower price in nearby locations or in a short period of time, thus alleviating their concerns. By learning the relationship between dynamic prices and features derived from the dataset, the prediction is carried out. As a representative, we train one linear model and test its output based on real service data from various perspectives. Furthermore, we view the contribution of features based on the model at different levels and find out what features contribute most to dynamic prices. Finally, we predict dynamic prices using an efficient linear regression model based on evaluation results. Our hope is that the study helps to make passengers happier as an accurate forecast.
