Inductive Logic Programming for a Fraud-Rule Discovery Pilot
Overview
What this challenge is about.
Use inductive logic programming to discover fraud rules from a labeled fintech dataset, compare against a LightGBM baseline, and earn a verifiable certificate.
The scenario
The fintech (around 110 people, around EUR 8 billion in annual transaction volume) loses around EUR 1.2 million per year to fraud and faces a regulator that increasingly requires explanations of fraud-flag decisions to flagged customers.
The Brief
What you'll do, and what you'll demonstrate.
Quantify whether Inductive Logic Programming surfaces useful, auditable fraud rules that complement a gradient-boosted baseline.
Earning criteria — what you'll demonstrate
- Apply Inductive Logic Programming to a real labeled dataset
- Discretize continuous features for symbolic learners
- Evaluate rule-based ML on precision, recall, and readability
- Reason about combining symbolic and statistical models in production
Program Fit
Where this fits in your program.
Sharpens the same skills your degree expects you to demonstrate.
Aligned coursework coming soon.
Skills
Skills you'll demonstrate.
Each one shows up on your verified credential.
- Inductive Logic Programming
Apply inductive logic programming to solve real industry problems and demonstrate production-level capability.
- Symbolic Ai
Apply symbolic ai to solve real industry problems and demonstrate production-level capability.
- Rule Learning
Apply rule learning to solve real industry problems and demonstrate production-level capability.
- Prolog
Apply prolog to solve real industry problems and demonstrate production-level capability.
- Fraud Detection
Apply fraud detection to solve real industry problems and demonstrate production-level capability.
- Evaluation
Apply evaluation to solve real industry problems and demonstrate production-level capability.
Careers
Career paths this challenge builds toward
Completing this challenge demonstrates skills that transfer directly to these roles:
ML Researcher
Applying symbolic ML methods to a labeled dataset and writing the production-fit memo is the kind of methodology work ML researchers ship in industry research labs.
This challenge sharpens
- inductive-logic-programming
- symbolic-ai
- rule-learning
Data Scientist
Combining symbolic rule-learning with a GBM in a fraud-detection stack is exactly the day-one work of a data scientist at any fintech with regulator pressure.
This challenge sharpens
- fraud-detection
- evaluation
- rule-learning
AI Safety Researcher
Surfacing auditable rules to complement a black-box model is the AI safety craft of building accountable ML systems.
This challenge sharpens
- symbolic-ai
- rule-learning
- fraud-detection