click here to download the abstract of ml algorithm
At DataPro, we provide final year projects with source code in python for computer science students in Hyderabad , Visakhapatnam.
ABSTRACT
Cricket is a very familiar and exciting sport that people of all age groups are insane to see and play. For many it’s a billion-dollar market as they speculate financially, hoping to be able to earn profit in the form of gambling and various other ways. In this project, a model using machine learning algorithms is proposed to predict the score of each match and winning team based on past datasets available from 2008 to 2019 IPL matches in Kaggle.
This proposed methodology includes the following steps like Pre-processing of collected datasets, Feature selection from raw data, Conversion of categorical data into numerical data, Partitioning of samples into training and test samples, Training, and classification. Previous papers utilized machine learning algorithms such as Support Vector Machine, Random Forest, and Naive Bayes.
Keywords : IPL, Machine Learning, Match winner prediction, Score Prediction, SVM, kNN, Naive Bayes.
Introduction
Indian Premier League (IPL)
Sports have gained much importance at both national and international level.
The International Cricket Council (ICC) recognizes cricket, marked as the prominent sport in the world, as one of its forms, with T20 being a notable example.
Because of the short duration of time and the excitement generated, T20 has become a huge success. IPL has propelled T20 cricket’s popularity to dazzling heights. It holds the distinction of being the most attended cricket league globally, and in 2010, IPL achieved the milestone of being the first sporting event broadcasted live. Till date, IPL has successfully completed 13 seasons from the year of its inauguration. After the completion of league stages, the top 4 teams in the points table are eligible to the playoffs.
In playoffs, the winner of the 1st vs. 2nd match qualifies for the final. So, The loser gets a second chance to reach the finals by playing against the winner of the 3rd vs. 4th match. In the end, the 2 qualified teams played against each other for the IPL title. The IPL’s unique feature of television timeouts eliminates time constraints for completing innings.
The suggested prediction model makes use of both SVM and KNN to fulfill the objective of the problem stated. Few works have been carried out in this field of predicting the outcomes in IPL. In our survey, we observed that existing work focuses on using Data Mining to analyze and predict match outcomes.
Support Vector Machine (SVM)
● The “Support Vector Machine” (SVM) is a supervised machine learning algorithm capable of addressing both classification and regression challenges.
● However, people mostly use it in classification problems. In the SVM algorithm, we plot each data item as a point in N-dimensional space with the value of each feature being the value of a particular coordinate.
● Then, we perform classification by finding the hyper-plane that differentiates the two classes very well. Support Vectors are simply the coordinates of individual observation.
● So, The SVM classifier is a frontier which best segregates the two classes (hyper-plane/ line).
