In this chapter, we switched our focus to SPSS on Spark with which we processed data on Spark and then built a model for movie recommendations; using this, we produced movie recommendations for individual users.

Specifically, we first selected collaborative filtering as our method as per business needs after we prepared Spark computing with SPSS and loaded in preprocessed data. Second, we worked on data preparation with SPSS Modeler. Third, we implemented model estimation using SPSS Analytic Server. Fourth, we evaluated these estimated models by assessing error ratios. And finally, we deployed our machine learning results with some examples of recommending movies for individual users.

After this chapter, you will have gained a full understanding of how Apache Spark can be utilized to make your work easier and faster in conducting supervised machine learning and also gained a deeper understanding of developing recommendation engines. At the same time, you will have learned how SPSS and Spark can work well together.