Duckworth-Lewis-Stern Method Comparison with Machine Learning Approach

TL;DR

This paper compares the traditional DLS method with machine learning models for predicting cricket match results, optimizes the DLS resource table, and introduces an Unpredictability Index to rank nations by match unpredictability.

Contribution

It introduces a machine learning approach to enhance cricket result prediction and optimizes the DLS resource table for better accuracy, along with a novel Unpredictability Index.

Findings

Machine learning models outperform DLS in prediction accuracy.

Optimized DLS resource table improves predictive power.

Unpredictability Index effectively ranks nations by match unpredictability.

Abstract

This work presents an analysis of the Duckworth-Lewis-Stern (DLS) method for One Day International (ODI) cricket matches. The accuracy of the DLS method is compared against various supervised learning algorithms for result prediction. The result of a cricket match is predicted during the second inning. The paper also optimized DLS resource table which is used in the Duckworth-Lewis (D/L) formula to increase its predictive power. Finally, an Unpredictability Index is developed that ranks different cricket playing nations according to how unpredictable they are while playing an ODI match.