ADIA Lab and Crunch Lab Launch Structural Break Challenge
ADIA Lab, in partnership with Crunch Lab, is launching its third machine learning competition: the ADIA Lab Structural Break Challenge.
This year’s data competition challenges participants to detect structural breaks in univariate time series data. Given a time series with approximately 1,000 to 5,000 values and a designated point in it, the task is to determine whether a structural break occurs at that point, indicating a change in the data-generating process from that moment on.
Participants will have access to a large, labeled dataset of tens of thousands of time series for training. The problem holds significant relevance in fields such as climatology, finance, industrial settings, and healthcare, where detecting such breaks can signal critical events—from climate anomalies and equipment failures to market shifts and medical emergencies.
Competitors are encouraged to explore techniques such as statistical tests, feature extraction, time series modeling, and deep learning approaches to build robust detection algorithms.
Key details:
Total prize pool: $100,000 USD
Top prize: $40,000 USD for the overall winner
Additional prizes for the top 10 entries
Competition period: May 14 - September 15, 2025
ADIA Lab invites data scientists and machine learning researchers to participate in this challenge as contributions will help advance structural break detection in time series data and its real-world applications.