You will help to develop an AI-driven chess engine with the following features:
Run alongside every user game to point out obvious threats and opportunities (minimum 1 move deep)
Get a score for any move
Generate metadata from user games (for future analysis, and creating chess puzzles)
In addition, you will help to program “AI Bosses” with increasing difficulty to help users master multiple openings over time. If possible, the goal is to generate custom puzzles from scratch with a specific learning focus and difficulty level.
Chess puzzles present a particular scenario on a chess board and challenge a player to perform a particular task with it.
The project milestones
Collect public game data (e.g. from LiChess.org and other online locations) and organize it into a useful data blob in ram in the cloud somewhere.
Use this to train our engine; note that we also may adapt an open-source chess engine (e.g. stockfish, etc.) and customize it to our specific needs.
Generate a roadmap to extend our AI chess engine to satisfy future ChessX platform functions. For example, we want to try and create a PvP matchmaking system that matches players not just by rank but based on thousands of subtle differences in individual strengths and weaknesses to increase everyone’s learning speed on our platform (this would require a method to independently measure “learning speed” for any given user in a database of users and games).
Why join? The uniqueness of Omdena Innovation Challenges
A collaborative experience you never had in your working life! For the next eight weeks, you will build AI solutions to make a real-world impact and go through an entire data science project lifecycle. This covers problem scoping, data collection, preparation, and modeling for deployment.
And the best part is that you will join a global and collaborative team of changemakers. Omdena AI Innovation Challenges are not a competition or hackathon but a real-world project that will take your experience of what is possible through collaboration to a new level.