Movie Recommendation System
🧿
A. The Motivation
What a nice output that is 🤩
Movie Recommendation Engine
https://www.codeheroku.com/static/movies/index.html
B. Introduction
Let's discuss briefly, you have 3 ways to build a recommendation system
- Trending
- Content Based
- Collaborative Filtering Method
But generally,
Let's see pictorially,
Collaborative Filtering is divided into 2 parts
- User to User CF
- Item to Item CF
🎯
Item to Item CF is widely used, as it is more convenient and scientific.
C. More About CB Filtering & CF
1. Content Based Filtering Method
temp-159843341779507346
Those 3 sentences, i.e. My name is Debmalya My country name is India In my class there is no-one named as Debmalya are evaluated here! Evaluation Method Firstly, for the 1st sentence these 13 columns are poltted on 13-dimension space, same goes for 2nd sentence.
https://content-based-filtering.netlify.app/
2. Collaborative Filtering Method
temp-159843330656815
In the correlation matrix, the +ve value near to 1 is denoting that those 2 movies are too much related to each other. On other hand, the -ve value near to -1 is denoting that those 2 movies are related in the negative sence.
https://collaborative-filtering-method.netlify.app/
D. Various Types Of Distances
There are 2 kinds of distances
- Euclidean Distance
- Angular Distance
E. When to use which distance
Here, use Angular Distance.
🎯
In Recommendation Engines (RE), the Angular Distances is used.