Ola Data Analysis for Dynamic Price Prediction Using Multiple Linear Regression and Random Forest Regression

Abstract

This research aims to create the most efficient and accurate cab fare prediction system using two machine learning algorithms, the Multiple linear Regression algorithm and the random forest algorithm, and compare parameters r-square, Mean Square Error (MSE), Root MSE, and RMSLE values to evaluate the efficiency of two machine learning algorithm. Considering Multiple linear Regression as group 1 and random forest algorithms as implemented, the 2 group process was to predict prices and get the best accuracy to compare algorithms. The algorithm should be efficient enough to produce the exact fare amount of the trip before the trip starts. The sample size for implementing this work was N=10 for each group considered. The sample size calculation was done with clincle. The pretest analysis was kept at 80%. The sample size is estimated using G-power. Based on the statistical analysis significance value for calculating r-squared, MSE was 0.945 and 0.266(p>0.05), respectively. The Multiple linear algorithms give a slightly better accuracy rate with a mean r-squared percentage of 71.69%, and the Random forest algorithm has a mean r-square of 71.29%. Through this, prediction is made for online booking of cabs or taxis, and the Multiple linear algorithms give a slightly better r-squared value than the Random forest algorithm.