Introduction

I've often pondered over the mechanics behind YouTube, Amazon, and Netflix's video recommendations tailored to my preferences. Similarly, my curiosity extends to comprehending the inner workings of Twitter and HackerRank algorithms. Through my studies, I've unveiled that constructing these systems isn't an enigma; rather, it relies on the application of machine learning, deep learning, and advanced mathematical principles commonly taught at the graduate level.

Let’s Understand what is a recommendation system

A recommendation system is a technology that suggests relevant items, products, content, or actions to users based on their preferences, historical behaviors, and patterns. It leverages algorithms and data analysis to make personalized recommendations, helping users discover new items of interest and enhancing their overall experience. These systems are widely used in various domains such as e-commerce, content platforms, social media, and more to improve user engagement and satisfaction.

Types of recommendation system

Collaborative Filtering:

• Collaborative filtering recommends items based on the preferences and behaviors of similar users. It assumes that users who liked similar items in the past will continue to like similar items in the future.
• I have to make a project that is Book Recommendation System using collaborative filtering and popularity.

Book Recommendation System

Detailed explanation and code can be found on GitHub.

GitHub Link

**https://github.com/Khannooman/book_recomendation_system/tree/master**

Content-Based Filtering:

• Content-based filtering recommends items based on their attributes and features. It focuses on analyzing the characteristics of items users have interacted with and suggests items with similar attributes.
• I have to make a project that is Movie Recomendation System using collaborative filtering and popularity.

Movie Recomendation System