On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,742 papers · 148 categories

Trend · papers per month

count % of corpus

← all fields·2 papers on “deep learning” in Quant Finance · 1 week

Prediction of bank transaction fraud using TabNet an adaptive deep learning architectureq-fin.GN

TabNet improves fraud detection in bank transactions.

problem Detecting fraudulent bank transactions using deep learning.

method TabNet, SMOTE, EDA, 5 deep learning architectures, 3-fold cross-validation.

result TabNet achieved 97.39% accuracy and 0.9739 ROC-AUC.

bank fraud TabNet deep learning fraud detection financial decision-making

2026-07-21abs ↗pdf ↗

AlphaZeroBeta: Deep Reinforcement Learning for Market-Neutral Portfoliosq-fin.PM

AlphaZeroBeta uses deep reinforcement learning for market-neutral portfolios, outperforming traditional methods.

problem Traditional portfolio management methods often fail during market regime shifts or when assumptions break down.

method Combines a composite reward function and CNN-GRU policy trained end-to-end via Recurrent PPO.

result Achieves higher Sharpe ratios than baselines while maintaining near-zero benchmark correlations.

deep reinforcement learning market-neutral portfolios reinforcement learning portfolio management deep learning

2026-07-20abs ↗pdf ↗