Sep 26, 2022
No image
Completed
Movie-Teller: Predicting Movies’ and TV Shows’ Popularity with AI
$50,000+
4-6 months
United Kingdom
6-9
Service categories
Service Lines
Artificial Intelligence
Big Data
Software Development
Web Development
Domain focus
Media & Entertainment
Subcategories
Artificial Intelligence
Machine Learning
Big Data
Data Mining
Challenge
Predict a TV series’ popularity at the stage of its creation for a large media channel producing TV and video content.
Predict a TV series’ popularity at the stage of its creation for a large media channel producing TV and video content.
Solution
Inventale’s massive experience in working with Big Data and accounting numerous events and adjustments is the basis of this project (apart from DM and ML).
The steps made to implement the project include:
— compilation and processing of data on movies and series from IMDb;
— training of various Random Forest combinations using H2O in R;
— analysis of the resulting hundreds of parameters: genres and settings; cast and film directors; the correlation between the year of release and the film/series rating; the temporal genre popularity; actors; screenwriters; 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, etc.
Inventale’s massive experience in working with Big Data and accounting numerous events and adjustments is the basis of this project (apart from DM and ML).
The steps made to implement the project include:
— compilation and processing of data on movies and series from IMDb;
— training of various Random Forest combinations using H2O in R;
— analysis of the resulting hundreds of parameters: genres and settings; cast and film directors; the correlation between the year of release and the film/series rating; the temporal genre popularity; actors; screenwriters; 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, etc.
Results
A back-test was conducted on more than 80,000 cinema projects with a result accuracy of more than 85%.
2 TV-series are now being filmed based on the Movie-Teller’s popularity analytics and forecasting results, that helped to:
— confirm relevance of the chosen genres and settings to the specified time period;
— choose the optimal cast, based on social-demographic perception and actors’ genre ratings;
— evaluate production cost-effectiveness, based on internal client’s statistics (budgets, gross revenues, expenditures);
— estimate average user ratings and the number of positive and negative reviews;
— choose the optimal launch period, based on the known competitors’ plans and other planned future events.
A back-test was conducted on more than 80,000 cinema projects with a result accuracy of more than 85%.
2 TV-series are now being filmed based on the Movie-Teller’s popularity analytics and forecasting results, that helped to:
— confirm relevance of the chosen genres and settings to the specified time period;
— choose the optimal cast, based on social-demographic perception and actors’ genre ratings;
— evaluate production cost-effectiveness, based on internal client’s statistics (budgets, gross revenues, expenditures);
— estimate average user ratings and the number of positive and negative reviews;
— choose the optimal launch period, based on the known competitors’ plans and other planned future events.