Fantasy-Points-Prediction-and-Dream-Team-Formation

Collected Data from open source resources that have over 100 Parameters for predicting cricket player performance. Created piplelines to funnel data from RDBMS. Collected Batting and Bowling Statistics and created functions to calculate fantasy points of cricket players from actual match data across t20 and Odi formats. Created models to predict player performance using Deep Learning and Time Series Approaches. After Predicting Performances, Collected all 22 Player data (predicted) and Performed multi-objective optimization using NSGA-II (Evolutionary/Genetic Algorithms) Got an accuracy of around 65% in various frontiers and created splendid vizualizations for comparision of results and displayed vizual results as to why we have selected various hyperparameters. A paper has been published for the following work in Data Insights Journal (Elviser) in addition to a detailed study of literature in the domain of sports analytics. The paper is titled as " PrOBML: A machine learning approach to Predict, Optimise & Build fantasy Cricket teams using evolutionary algorithm " For more details please check my kaggle page @ https://www.kaggle.com/akarshsinghh/cricket-player-performance-prediction