IBM/TabFormer

Code & Data for "Tabular Transformers for Modeling Multivariate Time Series" (ICASSP, 2021)

52
/ 100
Established

This project helps data scientists and machine learning engineers analyze complex patterns in sequences of events. It takes in structured tabular data, like credit card transactions or air quality measurements over time, and applies advanced transformer models to identify relationships and predict future events. The output is a trained model that can be used for tasks like anomaly detection or forecasting.

360 stars. No commits in the last 6 months.

Use this if you are a data scientist working with event sequences and need to build sophisticated models to understand or predict behavior from detailed, multi-dimensional records.

Not ideal if you are looking for an off-the-shelf application to solve a business problem directly, as this provides foundational model building tools for developers.

fraud-detection financial-transactions air-quality-analysis time-series-modeling predictive-analytics
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 24 / 25

How are scores calculated?

Stars

360

Forks

90

Language

Python

License

Apache-2.0

Last pushed

Sep 17, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/IBM/TabFormer"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.