Causal Insights for Learning Paths in Education

In this competition, participants will address two fundamental causal challenges in machine learning in the context of education using time-series data. The first is to identify the causal relationships between different constructs, where a construct is defined as the smallest element of learning. The second challenge is to predict the impact of learning one construct on the ability to answer questions on other constructs. Addressing these challenges will enable optimisation of students' knowledge acquisition, which can be deployed in a real edtech solution impacting millions of students. Participants will run these tasks in an idealised environment with synthetic data and a real-world scenario with evaluation data collected from a series of A/B tests.

Enter now on the competition website!


Tasks

Task 1: Relationship discovery for constructs over time using synthetic time-series data

Task 2: Teaching effectiveness inference using synthetic time-series data

Task 3: Relationship discovery for constructs over time using real-world time-series data

Task 4: Teaching effectiveness inference using real-world time-series data


Team

Craig Barton is the Head of Education at Eedi.

Wenbo Gong is a Researcher at the Machine intelligence group at Microsoft Research Cambridge (MSRC), UK.

Nick Pawlowski is a Senior Researcher at the Machine intelligence  group at Microsoft Research Cambridge (MSRC), UK.

Digory Smith is a Data Scientist at Eedi.

Zichao Wang is a Ph.D. student in Electrical and Computer Engineering at Rice University.

Joel Jennings is a Senior Researcher at the Machine intelligence group at Microsoft Research Cambridge (MSRC), UK.

Simon Woodhead is Head of Research at Eedi.

Cheng Zhang is a Principal Researcher at the Machine intelligence group at Microsoft Research Cambridge (MSRC), UK.

Incentives

Eedi will provide a $5,000 cash prize for the competition. There will be $1,000 prizes awarded to the winning team for each task. In addition, a $1,000 prize for the overall winner across all tasks.

Schedule

June 27, 2022: Tasks 1 and 2 released.
July 27, 2022: Tasks 3 and 4 released.
October 15, 2022: Final submission deadline for all tasks.
November 15, 2022: Results announced, private leaderboards revealed, prize-winners notified.

Submissions will be automatically evaluated on all tasks at time of submission. There is no live/demonstration component to the competition.

A submission website will be released at the start of the competition.