Recommendation Engine is a tool with which an application can recommend items to it’s users. There are various strategies to develop a recommendation engine depending upon the use case, but “Collaborative Filtering” is the most popular and widely used technique. With collaborative filtering, an application can find people with similar taste and can look at things they like and combine them to create a ranked list of suggestions which is known as user based recommendation. Or can also find items which are similar to each other and then suggest the items to users based on their past purchases which is known as item based recommendation. The first step in this technique is to find users with similar tastes or items which share similarity. There are various similarity models like Cosine Similarity, Pearson Correlation Similarity, Euclidean Distance Similarity etc. which can be used to find similarity between users or items. In this blog post I am going to discuss an example of how one can develop a basic recommendation engine in Python using Pearson Correlation Similarity.