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.

168,657 papers · 148 categories

Trend · papers per month

count % of corpus

← all fields·6 papers on “deep learning” in Quant Finance · 1 month

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 ↗

Deep Learning for Dynamic Programming with Recursive Utility Using First-order Conditionsq-fin.CP

CEFOL uses deep learning for dynamic programming with recursive utility.

problem Challenges in solving dynamic programming problems with recursive utility.

method Introduces a separate neural network for certainty equivalent, uses first-order optimality conditions to learn value and policy functions.

result CEFOL achieves high accuracy in learning value and policy functions, matching VFI benchmarks.

dynamic programming recursive utility deep learning first-order conditions certainty equivalent

2026-07-10abs ↗pdf ↗

Learning Predictive Ambiguity Sets for Decision-Focused Distributionally Robust Optimizationcs.LG

Proposes a method to learn adaptive ambiguity sets for robust optimization.

problem Misspecification in distributionally robust optimization (DRO).

method Learned predictive ambiguity sets (LPAS) using deep contextual models.

result Significantly improves portfolio optimization performance compared to baselines.

distributionally robust optimization ambiguity sets deep learning portfolio optimization robust decision-making

2026-07-10abs ↗pdf ↗

Deep Learning for Dynamic Programming with Recursive Utilityq-fin.CP

Deep learning solves dynamic programming with recursive utility.

problem Challenges in solving high-dimensional discrete-time dynamic programming problems with recursive utility.

method Certainty Equivalent Learning (CEL) algorithm that learns certainty-equivalent value directly with neural networks.

result Accurate value and policy approximations in high-dimensional problems, comparable to VFI in some cases.

Deep Learning Dynamic Programming Recursive Utility Certainty Equivalent Neural Networks

2026-07-05abs ↗pdf ↗

Heads, Not Backbones: Output Heads Dominate Architectures on Fat-Tailed Returnscs.LG

Deep forecasting models show output heads significantly improve performance on fat-tailed financial returns.

problem Improving deep learning models for forecasting fat-tailed financial returns.

method Comparison of backbone architectures and output heads (point, Gaussian, Gaussian mixture) on S&P 500 monthly log-returns.

result Switching from point to Gaussian heads improves CRPS by about 1.3 percent, and from Gaussian to mixture adds another 2.4 percent.

deep learning financial forecasting fat-tailed returns CRPS Gaussian mixture

2026-06-29abs ↗pdf ↗