Movie Analytics on Marvel Vs. DC Comics


Few moths ago we (mathminers) have written article on Batman vs. Superman, where we have used Sentimental analysis to predict which character is more popular.  Now, we are taking one step ahead to discuss Marvel vs DC Comic movies. We used Time Series Analysis (ARIMA) to forecast comic movie revenue for next 5 years and the results are astonishing.

In the past, there were few modes of entertainment such as radio, comic reading, family reunion (celebrating festivals) and so on. But now the trend has changed completely, people will go for vacations, socially active, watching movies either on Television or in Theaters, very few people will like to read comic. However, more people are interested in movies based on comic books such as Batman v/s Superman, Captain America, and The Dark Knight etc. In the past 16 years (since 2000), four studios such as 20th Century Fox, Warner Bros., Marvel and Dc have introduced many comic movies and have generated revenue of $23 Billions in the box offices.

We (mathminers) have downloaded the data of all the movies from IMDB and ran time series analysis (ARIMA) to forecast revenue of comic movies for the future. The forecasted revenue for next 3 years for comic book movies is more than $50 billion. We did more analysis on the IMDB data to derive more insight of the movie success in future.

In the past 16 years, Marvel & DC production house had made more than 34 movies.  On  an average 1 movie cost around $6 billion, but the profit these movies are making as high as $23 billions almost 6 times its production cost. But interesting fact to know is that around 58% revenue was generated outside the United States. It means only 42% was generated inside the States. This clearly shows that these movies have more fans outside USA.


The above first graph shows revenues generated by marvel & DC production houses. The blue color shows revenue generated within United States and the red is for revenue outside the States.  In the second graph one can see that dark color represents % revenue generated (Outside USA) and light color represents % revenue generated (Inside USA).

More characters or Better quality with less characters

In any movie especially the superhero ones, the most important part is the number of characters. There is always a dilemma for producers whether they include more heroes and villains in the movie. There are advantages and disadvantages of both the aspect. More number of characters will provide more action for example Avengers. However, the characters will get less time to play in the movies. This will become disadvantage with more characters movies. In short, all we want to say is that any producers should include less character in the movies (the popular ones/ used in previous movies) and focus more on quality rather than quantity.

As per one of the research done in an online magazine called as online behavior magazine, many characters have an increase in the revenue. However, more new characters (used old ones as compare to new) had lowered the revenue. Following is a Scatter diagram, which proves the above statement