MOVIE RECOMMENDATION SYSTEM USING COLLABORATIVE FILTERING

Abstract

As the demands of the business world continue to surge, there is an ever-growing
reliance on the extraction of valuable insights from vast pools of unprocessed data to
steer business solutions in the right direction. This heightened reliance on data
analysis is equally applicable to the digital recommendation systems that have
become commonplace in consumer-driven industries such as literature, music,
fashion, cinema, news, local services, and more. These systems actively gather and
analyze user data to refine their recommendations for future interactions. In this
research, we aim to elucidate the practical implementation of a movie
recommendation system. We achieve this by employing two collaborative filtering
algorithms, facilitated by the capabilities of Apache Mahout. Additionally, our study
delves into the realm of data analysis, using the Matplotlib libraries in Python to
uncover valuable insights within the movie dataset. This dual approach not only
enhances the efficiency and accuracy of movie recommendations but also provides a
deeper understanding of the underlying data trends and patterns.