Skip to content

KaushikNITK/Research-rehashed

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

26 Commits
 
 
 
 
 
 

Repository files navigation

Research-rehashed Prediction of win in League of Legends

IEEE xplore classical machine learning Paper CML04

In this research paper, Qiyuan Shen has made an attempt to predict the outcome of an esports event of League of Legends by using machine learning algoritms League of legends is a MOBA game like DOTA 2, with 2 teams red and blue playing against each other to take down opponents' bases and towers. Each team will have spawners of heralds, dragons, elite monsters and wards to be placed and destroyed. There are factors like experience, levels and gold which are generated by killing mobs or by destroying towers.

By keeping all of these in mind we plot graphs and analize them to check for depending facors and non-depending factors. We train a model by one of the different algorithms like Logistic regression, Decision trees, SVM, KNN .... In this we did by Logistic regrssion.

The dataset to be trained must have its features resemble those in the given sample dataset(high_diamond_ranked_10min.csv).

Accuracy of our implementation is around 73.3%.

Team name - Xg Overloaders

implemented by Kalva Kaushik, Gauri Aggarwal and Akhilesh

About

Paper CML04 by Xg overloaders

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors