Runtime Based Recommendations on Netflix Data using SBE-XGBoost model
Rajeswari Nakka, G. V. S. N. R. V. Prasad, Reddi Kiran Kumar · Solid State Technology · 2020
Recommendation Systems (RS) are developed and improved to provide meaningfulrecommendations of a products or services or items to a set of users who might seek attention towards it. ManyRS were developed for the use by various real world companies like Amazon, Netflix, Spotify and some socialmedia websites etc, which uses it to make profits. The paper focuses on applying machine learning techniquesto offer recommendations on Netflix dataset by implementing Runtime based Recommendations. A runtimecomputation technique was designed to overcome the data sparsity, curse of dimensionality problem, memoryand computational issues for larger datasets. Here the experiments are performed in Google Colab platform forcomputing and analysing the large datasets. The proposed approach is a combination of Surprise BaselineEstimator (SBE) and eXtreme Gradient Boosting (XGBoost). The designed runtime computation techniqueoutperformed Matrix Factorization approaches Singular Value Decomposition (SVD) and Truncated SVD. Theproposed model SBE-XGBoost evaluated with novelistic approach by combining SBE and XGBoost model toevaluate the training and test data which gave good prediction results on test data compared to the existingsystem.