Trend Identification And Product
Recommendation Engine

Challenges and Industry

An international gaming company approached GFAIVE with the goal of gaining a better understanding of trends and customer needs in order to use that information while planning and designing new games and models. The client had already been collecting player data through various games for over 3 years and was now eager to start leveraging this data for the creation of new features and adaptation of existing ones, and for monitoring brand reputation.


The challenge for GFAIVE was to create an all-encompassing tool that could not only provide predictions and recommendations based on each customer segment, but also monitor what was being said about the company in real-time.



Games are a major source of data that can uncover unexpected insights on customer behavior and preferences. For this reason, GFAIVE suggested an analysis based on clients’ existing gaming data. By first analyzing the users’ gaming activities, their preferences of used items and components, time spent on different levels of the game and so on, GFAIVE’s machine learning algorithm was able to identify main trends and needs for each customer

Next, to transform one of the client's applications into a more family-centric one, GFAIVE enhanced the customer intelligence solution by integrating a recommendation engine that enabled highly accurate predictions as to what activities and products should be recommended to each user based on their profile and preferences.

Finally, as the client was also interested in brand reputation monitoring, GFAIVE team leveraged natural language processing technologies to monitor what was being said about the company on social media, review sites, blogs and news outlets. The tool then provided the client with an overview of its brand sentiment, notifications of game
reviews that needed attention and suggested responses.



Following the integration of GFAIVE’s Customer Intelligence tool, the client was able to add new features to his existing games that were so well received by the customers that positive online reviews increased by 35%.

Also, by leveraging the recommendation engine, in-app purchases increased by 17% as the recommendations and offers provided to each unique customer became highly personalized and relevant.

Technologies Used

© 2021 by GFAIVE - ML demand forecasting for fashion retail. Privacy Policy

  • Instagram - White Circle
  • GFAIVE LinkedIn page
  • GFAIVE Facebook page
  • Twitter - White Circle
  • YouTube - White Circle