</> Code with Papers by Syntology

Datasets › BAF

BAF (Bank Account Fraud)

Introduced by Sérgio Jesus et al. in Turning the Tables: Biased, Imbalanced, Dynamic Tabular Datasets for ML Evaluation24 Nov 2022 archive 2025-07-28

Bank Account Fraud (BAF) is a large-scale, realistic suite of tabular datasets. The suite was generated by applying state-of-the-art tabular data generation techniques on an anonymized, real-world bank account opening fraud detection dataset.

Source: Turning the Tables: Biased, Imbalanced, Dynamic Tabular Datasets for ML Evaluation

HomepageBenchmarksPapers JSON

Benchmarks archive 2025-07-28

All 12 leaderboards whose dataset resolves to this page shown (sort by any header). "First row" is the archive's own first row at snapshot, in the archive's row order; nothing here re-ranks and metric direction is not asserted.

First row (archive order)PaperCode
Fraud Detection BAF – Base LightGBM Recall @ 1% FPR 25.2% RIFF: Inducing Rules for Fraud Detection from Decision Trees — 12 Compare
Fairness BAF – Base 1D-CSNN Predictive Equality (age) 99.86% Improving Fraud Detection with 1D-Convolutional Spiking... DylanPerdigao/Bayesian-Optimization-1D-CSNN 2 Compare
Fairness BAF – Variant I 1D-CSNN Predictive Equality (age) 96.87% Exploring Neural Joint Activity in Spiking Neural... DylanPerdigao/Neural-Joint-Activity-in-SNNs 1 Compare
Fairness BAF – Variant II 1D-CSNN Predictive Equality (age) 98.97% Exploring Neural Joint Activity in Spiking Neural... DylanPerdigao/Neural-Joint-Activity-in-SNNs 1 Compare
Fairness BAF – Variant III 1D-CSNN Predictive Equality (age) 98.45% Exploring Neural Joint Activity in Spiking Neural... DylanPerdigao/Neural-Joint-Activity-in-SNNs 1 Compare
Fairness BAF – Variant IV 1D-CSNN Predictive Equality (age) 98.68% Exploring Neural Joint Activity in Spiking Neural... DylanPerdigao/Neural-Joint-Activity-in-SNNs 1 Compare
Fairness BAF – Variant V 1D-CSNN Predictive Equality (age) 99.31% Exploring Neural Joint Activity in Spiking Neural... DylanPerdigao/Neural-Joint-Activity-in-SNNs 1 Compare
Fraud Detection BAF – Variant I 1D-CSNN Recall @ 5% FPR 40.71% Exploring Neural Joint Activity in Spiking Neural... DylanPerdigao/Neural-Joint-Activity-in-SNNs 1 Compare
Fraud Detection BAF – Variant II 1D-CSNN Recall @ 5% FPR 47.08% Exploring Neural Joint Activity in Spiking Neural... DylanPerdigao/Neural-Joint-Activity-in-SNNs 1 Compare
Fraud Detection BAF – Variant III 1D-CSNN Recall @ 5% FPR 41.83% Exploring Neural Joint Activity in Spiking Neural... DylanPerdigao/Neural-Joint-Activity-in-SNNs 1 Compare
Fraud Detection BAF – Variant IV 1D-CSNN Recall @ 5% FPR 35.54% Exploring Neural Joint Activity in Spiking Neural... DylanPerdigao/Neural-Joint-Activity-in-SNNs 1 Compare
Fraud Detection BAF – Variant V 1D-CSNN Recall @ 5% FPR 34.96% Exploring Neural Joint Activity in Spiking Neural... DylanPerdigao/Neural-Joint-Activity-in-SNNs 1 Compare

Papers archive 2025-07-28

4 shown of 4 papers with a leaderboard row on this dataset's benchmarks, newest first. The archive's own "papers using this dataset" list was never published, so this is the benchmark-backed subset; the archive's count for this dataset is 10. The Syntology column is from Syntology's graph (read 2026-09-24), stated per sample; it is not part of any archive number.

DateSamples run Syntology
Exploring Neural Joint Activity in Spiking Neural Networks for Fraud Detection 1 13 17 Nov 2024 not harvested
Improving Fraud Detection with 1D-Convolutional Spiking Neural Networks Through Bayesian Optimization 1 2 16 Nov 2024 not harvested
RIFF: Inducing Rules for Fraud Detection from Decision Trees 0 6 23 Aug 2024 not harvested
Decoupling Decision-Making in Fraud Prevention through Classifier Calibration for Business Logic Action 0 3 10 Jan 2024 not harvested

Dataset loaders archive 2025-07-28

No loader listed in the archive.

Tasks archive 2025-07-28

Fraud DetectionFairness

License archive 2025-07-28

Apache-2.0 license

Modalities archive 2025-07-28

Tabular

Languages archive 2025-07-28

No language tagged.

Variants archive 2025-07-28

  • BAF
  • BAF – Base
  • BAF – Variant I
  • BAF – Variant II
  • BAF – Variant III
  • BAF – Variant IV
  • BAF – Variant V

7 variant names, as the archive lists them.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections