GECA: Audience Prediction with Machine Learning
We are in a time of great changes and transformations that affect transversely the economic activity and society. One of the sectors most affected by this revolution is the audiovisual sector, which has become one of the driving forces behind the transformation of other more traditional activities outside the cultural sphere. Technological advances, the evolution of content, free-to-air broadcasts shared with platforms and social networks, fragmented audiences, niche channels, etc. There are many variables to be taken into account. There are many variables that must be taken into account to predict, anticipate and innovate in the changing audiovisual world. We have developed an automated forecasting service through ML and Azure services to improve conversion rates and know in advance the behavior of consumers. GECA is one of the leading groups in the European audiovisual sector and integrates content, production and audiovisual distribution. It provides the creativity and technical solutions needed to design, produce and distribute any audiovisual or multichannel project.
Taking into account all the variables that come into play in a project like this, it was necessary to create a platform that, through the use of Machine Learning, would carry out a study of the current data and a learning process based on the new data received, in order to create audience predictions for 30-day periods.
The process
The audience prediction tool uses state-of-the-art algorithms and advanced data analysis to provide highly accurate estimates of TV audience behavior.
Through the latest advances in Machine Learning, a study of the current data and a learning through the new data that is being received is carried out. Datasets that include two years of historical data, share data divided by gender, program trawling, etc. are taken into account.
Development with Azure ML, Azure DevOps
This artificial intelligence and machine learning system is capable of analyzing a wide range of factors, such as demographics, viewing preferences, social trends, historical data and content minutes, to deliver robust, agile and actionable forecasts.
The solution is based on a predictive innovation approach with AI.
Automated forecasting service through ML.
“We are particularly proud to have been able to develop this unique and revolutionary tool for international TV. We believe that this solution is key to the TV industry and we are confident that it will enable audiovisual companies to move into new frontiers and achieve optimal results.”
Enrique Lozano, General Manager
Resultados Concretos
- Solid information: The teams responsible for content and programming will obtain accurate data, facilitating decision making.
- Programming optimization: The
- Programming managers will be able to propose different scenarios with their respective projections, helping to optimize resources and maximize audiences.
- Improved advertising investment: Reliable audience projections will help design strategies to maximize advertising effectiveness.
- After a training period, actions can be executed, allowing for improved conversion rates.
- Know in advance the behavior of consumers and the revenues obtained.
We are ready for new challenges
