Binge On!: A Machine Learning Analysis Tool to Examine the Success Rate of Movies
Project Author
Issue Date
2023-05-05
Authors
Solis, Adriana
Loading...
Embargo
First Reader
Bonham-Carter, Oliver N.
Additional Readers
Ormiston, Russell A.
Keywords
Movies , Machine learning , Data analysis , Streamlit , Movie success , Movie recommendation system dashboard
Distribution
Abstract
Through looking at the emerging trends in the movie industry, it is inferred that individuals are increasingly becoming interested in the multifaceted per- sonalization of their movie choices. Most streaming platforms utilize differ- ent algorithms that keep track of user’s choices to recommend movies, which further perpetuates the need for unique streaming choices. However, the re- search done thus far has only touched on the different factors affecting movie production, which doesn’t include much reference to how these factors would also apply to movie streaming services and their comprehensive data. This knowledge gap requires one to explore different ways that streaming services and other sectors of the movie industry make a profit so that success-based movie recommendations can be made available to users. This is where the research conducted in this paper comes in, as the analysis of streaming plat- forms (Netflix, Hulu, etc.), movie production (actors, budget, directors, etc.), and overall revenue is used to determine what exactly makes a movie suc- cessful in order to build a movie recommendation system. This paper will serve as a comprehensive analysis of different determinants of movie success. These determinants will be analyzed with a Logistic Regression algorithm, where the results will then be put into a machine-learning model. Once the model is appropriately trained and tested, then the resulting application will be displayed on a Streamlit-based web application.
Description
Chair
Major
Computer Science
Economics
Economics
Department
Business and Economics
Computer Science
Computer Science