A Novel Advertisement Recommendation System Using Random Forest over K++ Means Algorithms

Authors

  • A.Nanda Kishore
  • L.Rama Parvathy

Keywords:

Machine learning, Novel Random forest, K-Means, Movies, Recommendation, Classifier, Decision tree.

Abstract

Aim: The aim of the work is to evaluate the accuracy in predicting movie recommendation using  Novel Random Forest (RF) Algorithm and K-Mean algorithm. Materials and Methods: The classification algorithm is invoked on a movie  dataset consisting of 5000 records. A framework for movie recommendation prediction has been proposed and developed that compares Novel Random Forest and K-Means Algorithm. Sample size was calculated as 8 in each group using G powers. Sample size was calculated using clinical analysis, with alpha and beta values ​​of 0.05 and 0.5, 95% confidence, 80% pre-test power. Results: The Random Forest algorithm produces an accuracy of 89.98% when predicting movie recommendation on data sets following the root mean square error, while criteria based K-Mean give 86.98% and it is carried out by performing sample T-test with SD and significance value as p=0.002 (p<0.005, 2-tailed). Conclusion: The results show that the performance of the Novel random forest algorithm is better than that of the K-Means in terms of accuracy.

Downloads

Published

2022-12-13