quantitative-finance

A Columbia University paper introduces a strictly causal Hidden Markov Model that adapts to changing market regimes, achieving a 2.18 Sharpe ratio vs 1.18 for SPX buy & hold and reducing max drawdown from -14.62% to -5.43% during the 2025 selloff.

Former Citadel fund manager Brett Caughran summarizes ten key points on how to apply AI agents in investing, with the author noting that points 5 and 6 are especially fair.

A quantitative finance expert systematically explained the practical use of Python in quantitative finance at PyData, covering tools such as NumPy, SciPy, Pandas, Numba, and recommended the open-source library DX Analytics and the resource list awesome-quant.

Discusses the trade-offs of using Kullback-Leibler divergence in quantitative analysis, framing it as a Hamlet-like dilemma for quants.

Goldman Sachs open-sourced its internal quantitative trading toolkit gs-quant, providing institutional-grade derivatives pricing, risk management, and strategy development tools. It has received 11.3K GitHub stars.

A curated list of 10 free GitHub repositories for algorithmic trading and quantitative finance, covering tools for backtesting, data analysis, portfolio optimization, and AI-driven trading strategies.

This thread explores how math/programming Olympiad backgrounds mass-produce tech founders, pointing out that the internalized systematic problem-solving ability, belief, and peer effect from the competition paradigm are the core engine, with quantitative finance as a transfer station, but also reminds that entrepreneurship requires skills beyond problem-solving.

A GitHub repo aggregates free, open-source quantitative finance tools—pricing engines, backtesters, order books, and HFT simulators—typically guarded by firms, including Microsoft's AI quant platform.

XAlpha introduces a memory-driven AI quant researcher that integrates financial knowledge and discovery feedback to automate the full hypothesis-to-code alpha discovery loop, achieving stronger performance on CSI300.

AI Trader is a fully autonomous trading agent now available for free.

The article summarizes the core learning methodology of world-class geometer and quantitative king James Simons: incubation by the subconscious, stripping away noise, and an extreme aversion to rote memorization, emphasizing deep thinking, leaving mental space, and cross-disciplinary learning through leveraging networks of genius.

A tweet highlights Stanford professor Stephen Boyd's free convex optimization course and textbook, noting that Citadel pays $400K for this skill. The course teaches optimal portfolio allocation, but emphasizes that the optimizer only works with a genuine edge in signals.

An educational thread explaining the mathematical foundations used by quantitative trading firms like Renaissance Technologies, covering concepts from Bernoulli to Brownian motion.

This paper introduces OpenFinGym, a unified multi-task gym environment for evaluating large language model agents in quantitative finance, covering forecasting, market generation, real-time trading, and fraud detection with verifiable execution and automated task construction.

Awesome Quant AI is a curated GitHub repository that organizes resources for AI and machine learning in quantitative finance and trading, including strategy design, trading paradigms, and frontier AI topics like LLM agents and time-series foundation models.

This article details how a systematic fund replaced its traditional NLP pipeline with a RAG-based LLM agent architecture, achieving a 340% improvement in alpha generation from unstructured data. It cites recent research (Alpha-GPT 2.0, FinCon, FinAgent) showing significant gains in automated factor discovery and trading performance.

This research tests whether Benjamin Graham's classical value investing rules can act as a mathematical 'low-pass filter' to prevent modern machine learning models (XGBoost, AutoGluon) from overfitting to market noise. Using 20 years of S&P 500 data, the authors find that Graham's rules combined with Random Forest achieve high returns with lower risk than complex AI models alone.

A comprehensive guide explaining the Kalman filter and its application in building smarter trading systems, including mathematical foundations and production-grade examples.

A thread introducing Loop Engineering as a solution to the common problem of quant strategies that backtest perfectly but fail in live trading, emphasizing the need for iterative optimization.

This paper introduces CARLOS, a deep reinforcement learning algorithm that learns continuous-time optimal stopping rules for American-style options using an aggregate deep neural network, effectively closing the Bermudan-American value gap with high computational efficiency.