Title : Predicting the Impact of Disruptions to Urban Rail Transit Systems
Author : Pradeep Burri, P.Mohan, Kanipakam Bhanu Moorty, K.Vishnu Vardan Varma
Abstract :
This study primarily aims to assess two different methods for estimating the cost of train tickets: a Decision Tree & a Novel Random Forest. Procedures and Materials: Decision Tree (DT) and Random Forest (RF) are the two categories that make up this research. The six iterations for each group were determined using ClinCal with the following parameters: alpha = 0.05, beta = 0.2, Gpower = 0.8, and a 95% confidence interval. We used Kaggle's 215909-item train ticket price prediction dataset. In comparison to Decision Tree's accuracy rate of 78.18%, Random Forest's algorithm achieves a much higher rate of 88.01%. The Decision Tree as well as the Novel Random Forest approach differ considerably from each other (p=0.001), according to the findings for the t-test on independent samples (p<0.05). Findings: When comparing the two models, Random Forest outperforms Decision Tree when it comes to forecasting the price of train tickets. Machine learning, decision trees, insu
