Science of Gaming

How machine learning and AI powers the Science of Gaming

Data science and analytics form the DNA behind Games24x7’s operations and the Science of Gaming.
Most people think artificial intelligence (AI) in gaming is all about building the best game playing bot that –
  • either defeat the best human players; and/ or,
  • learns a game online to reach the end goal from a random initial state while surmounting all random obstacles in-between.

Several projections over the years have shaped these perceptions about the application and research in machine learning (ML) and AI in gaming.

For many skill games such as Chess, Go, and Atari, and lately for games like Poker, the quest from AI/ML researchers and industry has been towards creating best superhuman bots. In another extreme, for casual games, the focus has been to develop game characters and elements that learn automatically during the game. We have seen enormous advancements in recent years. Today, modern game development platforms provide the necessary nuggets to the game developers to incorporate the learning capabilities into games, while game AI researchers plug in new innovative learning algorithms to procedurally generate game content. In this regard, games provide an attractive, yet, non-intrusive way for researchers to design and test virtual modelling of reality and agents/bots navigating through reality.

 

Skill-based games played for entertainment with real money

Strict regulations, coupled with a sense of moral responsibility, doesn’t allow gaming companies to create game playing bots. The research community around human-computer interaction has given us fascinating qualitative insights on the behaviour of game users in terms of skill assessment and skill-matching, factors and designs that enhance engagement and retention, among others. The recent proliferation of digital games for commercial, social, and educational purposes has further necessitated a new research direction towards game intelligence and knowledge discovery.

The key quest here is to enable a vision of end-to-end informatics around game dynamics, game platforms, and the players by consolidating orthogonal research directions of game AI, game data science, and game user research. Based on data-driven analysis, we take an evidential and experimental approach towards understanding new business opportunities. The data-driven approach at Games24x7 also enables awesome game playing experiences by solving problems using an AI/ML-first approach — AI/ML becomes the heart of all user journeys and personalization.