Forecasting IPL Player Auction Prices Using Machine Learning Techniques
摘要
This study presents a predictive model that uses machine learning algorithms to forecast both the runs and salary of players in the Indian Premier League (IPL) based on historical auction data and key player performance metrics. By considering attributes such as role, strike rate, number of centuries, total runs, and other relevant factors, the model aims to predict a player’s performance (in terms of runs) and their corresponding auction price. The model is developed using the XGBoost algorithm, which captures the complex relationships between these features and player valuations. Our findings highlight the potential of predictive analytics in accurately estimating both player performance and salary, offering a more data-driven approach to IPL auction predictions. Additionally, this research explores various aspects of auction design and valuation strategies, providing valuable insights into the evolving landscape of sports analytics.