In this chapter, we have explored building collaborative filtering approaches such as user-based and item-based approaches in R and Python, the popular data mining programming languages. The recommendation engines are built on MovieLens, and Jester5K datasets available online.
We have learnt about how to build the model, choose data, explore the data, create training and test sets, and evaluate the models using metrics such as RMSE, Precision-Recall, and ROC curves. Also, we have seen how to tune parameters for model improvements.
In the next chapter, we will be covering personalized recommendation engines such as content-based recommendation engines and context-aware recommendation engines using R and Python.