Project Work

Our Approach

Exploratory Data Analysis

The datasets were cleaned, combined and then visualized to derive insights and patterns from the data. Some of the insights gotten are:

  • Trends in budgets, revenue and profit/loss

  • Monthly movie release and revenue statistics

  • Ratings and Popularity

  • Correlation plots and deductions

  • Genre breakdown and analysis

Trends in budgets, revenue and profit/loss

Revenue margins skyrocketed at the turn of the century. This may be attributed to technological advancement in cinema, record viewership on several paid platforms like Netflix etc. From the second graph Revenue and profit had its peak in 2014 with Revenue topping the chart with a whopping 24.13 billion dollars. It is interesting to note that movies released over the years generally made more than 100% return on investments.

Monthly movie release and revenue statistics

Revenues peaked at targeted months of the year where producers expect more movie audiences. Distributors usually aim for the peak summer season of June and July. With cinema halls full, producers make more money.

The last half of the month of May is also targeted in preparation for the coming holiday, albeit school being in session.

Producers and distributors who are marketing their blockbuster films for both revenues and awards tend to target the winter months of November and December, which also includes the holiday season.

Ratings and Popularity

None of the 10 highest rated movies are on the most popular list. It is therefore not wrong to conclude that popularity doesn't necessary means high rating.

Correlation plots and deductions

There is a high positive correlation between budget and revenue, with films having higher production costs generally generating more revenue. Asides Release Year and Average Vote, all other variables show a positive correlation with revenue and budget.

Genre breakdown and analysis

Drama, comedy and action are the dominant genres comprising of 3003 movies and occupying 62.90% of the entire dataset.

Although outnumbered by non-animated movies, Animated movies cost almost twice that of non animated movies on average and their profits are large as well.

Project Report

Hamoye Open Source Project- Stage G- Movie Success