LSTM/RNN model to predict activity on GitHub and to guide repository interaction to success.
This system learns how large-scale collaboration works on GitHub. LSTM neural networks and machine learning models analyze historical GitHub data, learning to predict both a user's future contributions, as well as determine whether a given project is going to be successful. This research project's findings might be used in an AI product manager that assists collaboration by actively managing a project's contributors, organizing them into subteams, finding relevant users to bring into the project, and shaping the work that users do on the project to maximize its success.
Project completed under the auspices of the Harvard Computer Science Department as part of ongoing research in Multi-Agent Systems.