In this notebook, we show how you can use a data-driven approach to cricket analytics.
<p>Technology is continuing to play an integral part in sports. In cricket too, there are many areas where technology can be used. Machine learning will play an important role in Sports Analytics. </p> <p> We believe that we can use Machine Learning to analyze the historical cricket games, and use this to continuously improve the Duckworth Lewis Method of computing target scores in rain-shortened matches. </p> <p> Current D/L method is a mathematical formulation and initially designed for ODIs (50/50). We believe we can use historical Twenty20 data to derive an always up-to-date D/L table that takes into account trends in recent games, etc. </p> <p> In this jupyter notebook, you will learn how we analyze the T20 ball-by-ball data from cricsheet.org, and apply curve-fitting with constraints techniques to derive an improved DL table that takes into account the trends observed in recent T2O games. </p>