Variational Autoencoder for Synthetic Tabular Banking Data
Overview
What this challenge is about.
Train a VAE on 500K banking transactions, generate synthetic data, and evaluate privacy and utility. Get a verifiable certificate.
The scenario
The startup (around 35 staff, Series A) has signed 4 data-sharing MOUs with EU research partners that are stalling on its inability to deliver useful synthetic data; closing the gap unlocks the partner pipeline.
The Brief
What you'll do, and what you'll demonstrate.
Train a VAE on banking transactions and demonstrate that it generates synthetic data that is more useful and at least as private as a histogram baseline.
Earning criteria — what you'll demonstrate
- Build and train a VAE with per-column likelihoods on mixed-type tabular data
- Apply utility metrics (TSTR) and privacy metrics (MIA) to evaluate synthetic data
- Reason about the privacy/utility trade-off in generative models
- Communicate generative-model results to a non-ML data-sharing committee
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.
- Variational Inference
Apply variational inference to solve real industry problems and demonstrate production-level capability.
- Deep Generative Models
Apply deep generative models to solve real industry problems and demonstrate production-level capability.
- Synthetic Data
Apply synthetic data to solve real industry problems and demonstrate production-level capability.
- Privacy Evaluation
Apply privacy evaluation to solve real industry problems and demonstrate production-level capability.
- Pytorch
Apply pytorch to solve real industry problems and demonstrate production-level capability.
- Tabular Data
Apply tabular data 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
Designing a privacy-aware generative model with rigorous utility/privacy evaluation is the kind of project that opens doors at applied-research teams in finance, health, and government.
This challenge sharpens
- variational-inference
- deep-generative-models
- synthetic-data
Applied AI Scientist
Trading off privacy and utility on real banking data is the day-to-day reality of applied AI scientists at regulated startups.
This challenge sharpens
- deep-generative-models
- synthetic-data
- privacy-evaluation
Machine Learning Engineer
Productionizing a VAE training + evaluation pipeline that another engineer can rerun is core MLE craft.
This challenge sharpens
- pytorch
- tabular-data
- synthetic-data