Open AccessImplementation of Classification Algorithms in Neo4j using IPL data
Author(s) -
Surajit Medhi,
Hemanta K. Baruah
Publication year - 2021
Publication title -
international journal of engineering and computer science
Language(s) - English
Resource type - Journals
ISSN - 2319-7242
DOI - 10.18535/ijecs/v10i11.4635
Subject(s) - computer science , naive bayes classifier , artificial intelligence , machine learning , python (programming language) , random forest , cricket , bayes' theorem , graph , algorithm , data mining , bayesian probability , theoretical computer science , support vector machine , programming language , ecology , biology
The main objective of this paper is to implement the classifications algorithms in Neo4j graph database using cypher query language. For implementing the classification algorithm, we have used Indian Premier League (IPL) dataset to predict the winner of the matches using some different features. The IPL is the most popular T20 cricket league in the world. The prediction models are based on the city where the matches were played, winner of the toss and decision of the toss. In this paper we have implemented Naïve Bayes and K-Nearest Neighbors (KNN) classification algorithms using cypher query language. Different classifiers are used to predict the outcome of different games like football, volleyball, cricket etc, using python and R. In this paper we shall use cypher query language. We shall also compare and analysis the results which are given by Naïve Bayes and K-Nearest Neighbors algorithms to predict the winner of the matches.