About the Client

The client is a Global Media and Entertainment conglomerate with a strong presence across television broadcasting, movies, music, live entertainment and digital businesses. Spread over 173 countries, connecting and entertaining over 1.3 billion people globally. 

Business Challenges

  • The client wanted to launch a reality tv show 
  • The market for reality TV is has a lot of competition. It produces massive hits and flops 
  • A significant component of the marketing for such a show is done on social media 
  • The client wanted to understand the impact of various social media marketing strategies on viewership of the reality TV show 


We picked a popular reality TV show as a case study. The social media data for that reality TV show was analysed. Based on the social media Centelon built an AI based model to predict the marketing strategies that has maximum impact. The key solution component included: 

  • Automatic data cleaning as the data included images, special characters, and slang 
  • AI based classification of social media posts into marketing strategies such as promotion, gossip, news, poll. These posts types were taken as input to the prediction model 
  • The social media handle type (e.g. TV Show participant, host, channel agent) and the post volumes were also taken as the input to the prediction model. 
  • Some other variables that were factored in the model were day of the week and the actual activities performed by the show participants done during the show 
  • The predictive model was built using a combination of AI algorithms.  
  • The model also predicted the strategies that has maximum impact on the viewership 


  • The marketing team of the client was able to decide on precise social media strategy which included hashtags, post volumes by week, number of handles, post content and gender targeting