Recommendation Algorithm based on Blending Learning

Recommendation systems in today's world are extremely important for any business and users. Matrix Factorization is extensively researched and widely used for recommendation purposes. But it uses the dot product which does not satisfy the inequality property. Therefore, different techniques are proposed to solve the problem such as Metric Factorization. Although the results of Metric Factorization improved, but there is always welcome for new research work. Therefore we use a multi-model ensemble technique called blending. This Technique consists of two steps. First we train several base models and get the predicted rating of movies, then use a linear regression to combine these results as a second-layer model to get a final rating of movies. The metrics RMSE and MAE are used for evaluation for different models. Our experimental results indicate that new blending approach is superior to other used techniques.