A Novel Approach to Predicting IPL Player Value and Score Using XGBoost and Ridge Regression
M Sakthimohan, Elizabeth Rani G, P Gnanapriya, Muthuswamy Jayanthi, K. Karthigadevi, Sanjeevi Kumar.
Abstract
The primary readership for this paper is fans of the Indian Premier League. The IPL is an annual cricket event that takes place in the summer. Players from various nations are chosen to play for several teams in an auction. This was created primarily for users to apply machine learning techniques to anticipate outcomes more accurately. The primary page of this service offers two options to users. Using previously gathered data, one predicts the IPL score, while the other predicts player worth. Ridge regression and extreme gradient boost regression are two methods utilized in this study to apply the concept of predictive analysis. The main focus of this study revolves around a user-friendly service that allows IPL enthusiasts to make predictions using gathered data. The service offers two distinct options: one for predicting IPL scores and the other for estimating player worth. To achieve this, the researchers employ two prominent predictive analysis methods: Ridge regression and extreme gradient boost regression.This paper targets fans of the Indian Premier League (IPL), an annual cricket event held during the summer, where players from various nations are auctioned to play for different teams. The study aims to provide IPL enthusiasts with a user-friendly service that applies machine learning techniques to predict IPL match scores and estimate player worth. The predictive analysis utilizes two methods: Ridge regression and extreme gradient boost regression.