Mining Software Repositories

Course Description

CISC 880: Software engineering data (such as code bases, execution traces, historical code changes, mailing lists, and bug databases) contains a wealth of information about a project's status and history. This course will introduce state-of-the-art data mining techniques (including deep learning) that could be applied to analyze large software data for understanding of software development practices, and utilize software data for intelligent software development.

Course Information

  • Instructor: Dr. Yuan Tian, yuan.tian at
  • Classroom: Goodwin 521
  • Times: Monday 17:00-20:00
  • Office: Goodwin 635
  • Course Materials: OnQ


  • 15% Assignments - we will have 3 assignments.
  • 10% In-class participant
  • 20% In-class paper presentation
  • 55% Project (proposal 15% + presentation 20% + final report 20%)
  • Up to 5% Bonus points - based on novelty and completeness of individual project.
CISC880 Fall2019