Movie-Teller: Predicting Movies’ and TV Shows’ Popularity at the Planning Stage

Client Company

Major Russian media channel producing TV and video content

Solution Description

A system that predicts TV series’ popularity at the idea stage and enables one to choose the TV series with the highest potential.

Technology background

Inventale’s massive experience in working with Big Data and accounting numerous events and adjustments is the basis of this project (apart from data mining and machine learning).

The steps made to implement the project include:

  • Compilation and processing of data on movies and series from IMDb website
  • Training of various Random Forest combinations
  • Analysis of the resulting hundreds of parameters such as:
    • genres and settings;
    • cast and film directors;
    • the correlation between the year of release and the film or series rating;
    • the temporal genre popularity;
    • actors, screenwriters, directors ratings, depending on the genre;
    • socio-demographic perception, etc.
  • Inclusion of external factors into the forecast:
    • seasonality;
    • the competition of major projects and TV shows between channels;
    • competition with significant scheduled events (like Super Bowl or the World Cup), etc.;

Results and Current Status

A back-test was conducted on more than 80,000 cinema projects with a result accuracy of more than 85%.