Exploring Movie Recommendation System Using Machine Learning Algorithms to Improve TMDb’s Users’ Experience: A Case Study

With an explosion of information, Data and Analytics have become the forefront of every company. This immense technological revolution has powered businesses. Every industry is implementing customer-first and data-first strategies. Machine learning algorithms play a key role in processing this large amount of data and building expert systems to enhance customer experience, be it retail, travel, entertainment, or healthcare. Recommendation Systems are built on these machine learning algorithms which suggest products to customers based on numerous factors, such as their past searches, purchase history, preferences, or shopping behavior. This helps the customers to find products personalized to their liking and helps in decision-making.  

This paper outlines the concepts of the two main machine learning recommendation algorithm methods, ‘Content Based’ Recommender and ‘Collaborative Filtering’, for recommending movies to TMDb customers. TMDb, like IMDb, is a popular open-source database for movies and TV shows. The two systems will be studied and compared to understand their approach, limitations, and challenges during their applications on TMDb’s data. With the findings from this research, future studies will be planned to formulate methods for improved algorithms. This study will benefit TMDb by providing better recommendations to its users, strengthening its user base, and maximizing its profits. This paper starts with the introduction of these two models, and their objectives, followed by a literature review, then, the methodologies for designing these models, exploration of the findings and results obtained, challenges faced, and future directions to develop methods to improve these systems. 

 The main goals of this paper are: 

1. To inform the reader about how recommendation systems are useful and how machine learning algorithms are used to design these recommendation systems.
2. Review and assess prior research and literature on the main machine learning algorithms used to build recommendation systems.
3. Study the data science methods, machine learning algorithms, and recommendation techniques to recommend movies to TMDb’s users, the challenges faced, and their limitations.
4. Plan future research directions to develop methods to overcome these challenges and limitations.