Finance

Read more

Cross-venue highlights ranked by novelty + practical quant relevance + ML depth.

1. OOM-RL: Out-of-Money RL Market-Driven Alignment for LLM-Based Multi-Agent Systems (arXiv) Real-world 20-month study; Sharpe 2.06 via market friction as dense negative reward for MAS alignment.

Read more

A. Most Recent (April 2026)

1. The Self Driving Portfolio: Agentic Architecture for Institutional Asset Management Autonomous multi-agent system for institutional portfolio management with hierarchical decision-making. (2026-04-03)https://arxiv.org/abs/2604.02279

2. Hedging Market Risk and Uncertainty via a Robust Portfolio Ap…

Read more

1. TradeFM: A Generative Foundation Model for Trade-flow and Market Microstructure 524M-parameter generative Transformer learning from billions of trade events across 9K+ equities. Achieves 2-3x lower distributional error than Hawkes baselines, generalizes zero-shot to APAC markets. (2026-02-27) https://arxiv.org/abs/2602.23…

Read more

1. T-KAN for HFT Limit Order Book Forecasting — 19.1% F1 improvement, 132% backtest return (2026-01-14)

2. Variational Quantum Circuit RL for Portfolio Optimization — Quantum-classical hybrid RL (2026-01-30)

3. Deep g-Pricing for CSI 300 Options — Vol trajectories + sentiment (2026-01-30)

4. MarketGANs for Financial Time-Series Augmentation — GAN…

Read more

Finance

Finetuning LLaMA-3-8B for Financial NER with LoRA: The paper shows that using instruction fine-tuning and Low-Rank Adaptation with Meta’s Llama 3 enhances financial named-entity recognition, leading to top performance in converting unformatted reports into organized knowledge. (2026-01-15, shares: 0)

Adaptive Dataflow for Financial Time-Series

Read more

Finance

Interpretable Trading Validation: The authors introduce a walk-forward validation technique for algorithmic trading that focuses on interpretability and robust testing, offering modest gains and strong protection against losses. (2025-12-15, shares: 2)

Static Framework for Pricing: This paper presents a model-free method for pricing fixed-inc…

Read more

Finance

RL for Financial Decisions: Reinforcement learning improves financial decision-making by simplifying complex investment problems, emphasizing clear explanations and strong reliability over complex algorithms. (2025-12-11, shares: 2)

Unified Risk-Neutral Pricing: The paper presents a new approach to pricing zero-coupon bonds that aligns them w…

Read more

Recently Published

Quantitative

Satellite Census of Residential Buildings for Climate Risk: The article recommends using open-source satellite data to conduct a worldwide census of residential buildings. This approach aims to improve understanding of climate risks and their effects on housing and financial stability. (2024-10-07, shares: 30)

Enhanced S…

Read more

Please read the syllabus before enrolling, its quite technical!

ArXiv

LLM News Indicator for Economic Outlook: We build an interpretable, privacy‑friendly sentiment indicator from Swiss news using ML and LLMs…

Read more

Finance

Partial-Information Markets & Divergent Beliefs: Shows how a mathematical model explains why prices and trader biases converge as traders get more information, and gives the best way to combine expert opinions to hunt for arbitrage. (2025-11-03, shares: 5)

Probabilistic Rule Layers for Financial Drift: Presents a simple, interpretable rule-ba…

Read more

Finance

FinCARE: KG+LLM for Financial Causal Discovery: Combines SEC knowledge graphs, LLM reasoning, and causal discovery to build more accurate finance‑grounded causal models. (2025-10-23, shares: 7)

Quantile-Targeted Portfolio Optimization: Finds that investors targeting specific outcome quantiles change volatility exposure (cutting risk to protec…

Read more

Finance

TailSafe Hedging with Reinforcement Learning: The research presents Tail-Safe, a derivative hedging framework that blends reinforcement learning with a safety layer designed for financial constraints, ensuring robust forward invariance of the safe set under limited model mismatch. (2025-10-06, shares: 6)

Diffusion-Augmented RL for Portfolio M…

Read more

Finance

Revisiting Mean-field Theory: The Santa Fe model, used for analyzing the dynamics of the limit order book, is reevaluated using kinetic theory, leading to a new equation for the order-book density profile and identifying a previous error by E. Smith and colleagues. (2025-10-02, shares: 24)

Portfolio Similarity Metric: STRAPSim, a new method f…

Read more

Finance

DeltaHedge: Options Optimization: DeltaHedge, an AI-based framework that combines portfolio management with options trading, outperforms traditional strategies and improves risk-adjusted returns in various market conditions. (2025-09-16, shares: 19)

Historical Context in Financial News Forecasting: The study suggests using large language mode…

Read more

Finance

Market Trough Prediction: The research uses machine learning to identify that the volatility of options-implied risk and market liquidity are key factors causing market lows, challenging simpler models. (2025-09-07, shares: 19)

Optimal Exit in AMMs: The study investigates the best way for a liquidity provider to withdraw liquidity in an autom…

Read more

Finance

Asset Pricing with Attention Models: The study finds that pretrained RNN attention models can effectively derive returns and hedge risks in asset pricing, even during extreme market conditions like the COVID-19 pandemic. (2025-08-26, shares: 16)

ESG Risk Variables Algorithm: The research introduces a Hierarchical Variable Selection algorithm …

Read more

Finance

Stock Selection Analysis: The article investigates the application and effectiveness of role-based multi-agent AI systems in equity research and portfolio management, including their advantages and challenges. (2025-08-15, shares: 56)

Distortion Risk Measures with Partial Information: The study presents two new types of distributional uncerta…

Read more

We’re in 𝗯𝗲𝘁𝗮 and the first report is free! RIG report example

ArXiv

Finance

Time Series Model for Financial Simulator: A new financial model has been developed for an online app that simulates wealth proces…

Read more

Finance

Performative Market Making: The research shows how financial models can shape market processes and influence price changes, enabling market makers to use dominant strategies. (2025-08-06, shares: 5)

LossVersus-Rebalancing: The study introduces a mathematical model that views a CFAMM position as a portfolio of perpetual American CI options, ai…

Read more