This project aims to analyze a dataset of movies and generate insights to help stakeholders understand the current state of the movie industry.
The stakeholders for this project are Microsoft's new movie studio and production team. They are interested in understanding the trends and patterns in the movie industry to make informed decisions about their movie projects. The key business questions for this project include: * What factors contribute to the success of a movie (e.g. budget, rating, etc.)? * What are the most popular genres of movies? * Does the box office revenue change by month?
The source of the data for this project is a publicly available dataset of movies from IMDB, Box Office Mojo, Rotten Tomoatoes, TheMovieDb, and The Numbers. The dataset includes information such as movie title, release year, budget, revenue, rating, and genre, worldwide gross, box office revenue, directors, writers, and critics' reviews.
The data was cleaned and pre-processed to handle missing values and outliers. Then, the data was analyzed using various techniques such as descriptive statistics and data visualization.
Six visualizations that were used in the project are:
* A scatter plot showing return on investment
* A regressional plot showing production investment
* A bar plot showing the most profitable months
* A horizontal bar plot showing top 3 genres by revenue
* A pairplot showing domestic gross, worldwide gross, and production budget
* A distribution plot showing most profitable genres by worldwide gross
Overall, the project provided a comprehensive understanding of the movie industry to the stakeholders, enabling them to make better-informed decisions about their movie projects. The analysis of the movie dataset revealed several insights about the movie industry. Some of the most relevant findings include: * Science Fiction and Fantasy, Action and Adventure, and Kids and Family are the most profitable genres according to Rotten Tomatoes * Action, Adventure, and Comedy are most profitable according to IMDB, BOM, and TN. * There are three noticeably peak times for box office profits. (February, June-July and November-December) * Budget and Revenue are positively correlated, However, high budget does not guarantee high revenue.