Summary

In this chapter, we learned how to extract K-nearest neighbors for a given data point from a given dataset. We then used this concept to build the K-nearest neighbors classifier. We discussed how to compute similarity scores such as the Euclidean and Pearson scores. We learned how to use collaborative filtering to find similar users from a given dataset and used it to build a movie recommendation system. Finally, we were able to test our model and run it against data points that the system had not previously seen.

In the next chapter, we will learn about logic programming and see how to build an inference engine that can solve real-world problems.