ADIA Lab Causal Discovery Challenge - RECEIVE $100,000 FROM THE LAB
CAUSALITY IS THE NEXT FRONTIER IN
MACHINE LEARNING
Join our machine learning challenge to connect the dots between cause and effect.
Help solve one of the most critical challenges of modern data science and go beyond mere correlation
ADVANCES IN MACHINE LEARNING
UNDERSTANDING ‘WHY’?
A QUEST ON causal discovery
WHO CAN JOIN?
Whether you are a seasoned researcher, a data science enthusiast, or an AI innovator, this competition is your chance to make a significant impact in the world of machine learning and causal discovery.
WHAT IS CAUSAL DISCOVERY?
Discovering the causal structure that governs the relationships among variables from their observations is a challenging and valuable problem in many domains of application, like healthcare, economics, social sciences, environmental science, education, etc. In this competition, the basic building block that you are given is a dataset of observations of a set of variables and your task is to discover the causal directed acyclic graph (DAG) that defines the causal relationships between them.
WHAT ARE DIRECT ACYCLIC GRAPHS?
A directed acyclic graph (DAG) is a graphical model used in causal inference to represent presumed causal relationships between variables. Nodes represent variables, and directed arrows indicate direct causal effects, with the direction denoting the flow of causality. Crucially, DAGs have no feedback loops, reflecting the assumption that causality progresses forward in time. DAGs offer a rigorous, visual framework for mapping causal context, identifying confounding, and guiding statistical analysis to estimate causal effects by representing relationships in terms of counterfactuals.
ADVANCES IN MACHINE LEARNING
UNDERSTANDING ‘WHY’?
A QUEST ON causal discovery
WHO CAN JOIN?
Whether you are a seasoned researcher, a data science enthusiast, or an AI innovator, this competition is your chance to make a significant impact in the world of machine learning and causal discovery.
WHAT IS CAUSAL DISCOVERY?
Discovering the causal structure that governs the relationships among variables from their observations is a challenging and valuable problem in many domains of application, like healthcare, economics, social sciences, environmental science, education, etc. In this competition, the basic building block that you are given is a dataset of observations of a set of variables and your task is to discover the causal directed acyclic graph (DAG) that defines the causal relationships between them.
WHAT ARE DIRECT ACYCLIC GRAPHS?
A directed acyclic graph (DAG) is a graphical model used in causal inference to represent presumed causal relationships between variables. Nodes represent variables, and directed arrows indicate direct causal effects, with the direction denoting the flow of causality. Crucially, DAGs have no feedback loops, reflecting the assumption that causality progresses forward in time. DAGs offer a rigorous, visual framework for mapping causal context, identifying confounding, and guiding statistical analysis to estimate causal effects by representing relationships in terms of counterfactuals.
ADVANCES IN MACHINE LEARNING
They Designed
the competition
DR. HORST D. SIMON
Director, ADIA Lab
Prof. Marcos Lopez de PradO
Global Head of Quantitative R&D at ADIA
Prof. Guido Imbens
2021 Nobel Prize in Economics laureate
WITH PROF. GUIDO IMBENS
2021 Nobel Prize in Economics laureate
Conversation
on CAUSAL AI
47,000 datasets representing
47,000 hypothesized
caUSAl relationships
of 5 to 10 variables
observed at regular intervals.
In the area of causal discovery, an innovative approach consist in leveraging the powerful capabilities of supervised and unsupervised machine learning techniques to accurately identify and classify each component within a causal system, thereby automatically reconstructing causal graphs at unprecedented scale and facilitating large-scale classification of potential causes and effects.
This not only improves our understanding of complex systems, but also paves the way for more informed decision making and further causal understanding of the systems being analyzed.
WITH PROF. MARCOS LOPEZ DE PRADO
Exclusive interview
WE EXPECT DATA SCIENTISTS TO COMPETE BY SHARING CODE OF THEIR MODELS
Competition phases
WEEK
1-12
CODE SUBMISSION
In the first phase, participants are required to submit either a Python notebook (.ipynb) or Python script (.py) file. This file should contain the necessary code to build, load, or update their models and / or trained it on out-of-sample data.
The code will be executed by the Crunch platform on a secure data old out. Participants can either use static models, trained only once on the initial training set, or dynamic models that update or retrain themselves on the unseen data, as explained further in the documentation.
WEEK
15
AWARDS
Crunchers can compete for a share of $100,000 in this causal discovery challenge. The top entry wins $40,000, with prizes awarded to the ten best submissions. The competition seeks to advance the field through creative problem-solving.
More importantly, it's an opportunity for participants to showcase their skills and unique analytical solutions, regardless of demographics or academic background. The challenge welcomes innovative approaches to causal discovery from all corners.
Prize
1
$40,000
Prize
2
$20,000
Prize
3
$10,000
Prize
4
$5,000
Prize
5
$5,000
Prize
6
$5,000
Prize
7
$5,000
Prize
8
$3,500
Prize
9
$3,500
Prize
10
$3,000
ABOUT ADIA LAB
ADIA Lab is an independent Abu Dhabi-based institution engaged in basic and applied research in Data Science, Artificial Intelligence, Machine Learning, and High-Performance and Quantum Computing, across all major fields of study. This includes exploring applications in areas such as climate change and energy transition, blockchain technology, financial inclusion and investing, decision making, automation, cybersecurity, health sciences, education, telecommunications, and space. For more information, please visit www.adialab.ae or contact us at info@adialab.ae
CODE SUBMISSION
An AMA will take place to answer all your questions.
CODE SUBMISSION
Webinar on Factor Investing
CODE SUBMISSION
Masterclass with Prof. Marcos Lopez De Prado
COMPETITION TIMELINE
.png)
04:59 CET
05:00 PM UTC
ABOUT CRUNCH LAB
Crunch Lab is a quant boutique that helps large companies, investment firms, and financial institutions extract more value from their data. Crunch Lab works with data-rich companies to host Crunches, which are global ML competitions for the best and brightest in the CrunchDAO community.