入门资料整理：1.多因子股票量化框架开源教程 2.学界和业界的经典资料收录 3.AI + 金融的相关工作，包括LLM, Agent, benchmark(evaluation), etc.

An open-source, lightweight, and blazing-fast financial machine learning library built with Numba. Process raw trades, generate advanced bars, features, and labels for quantitative research.

QuantMind is an intelligent knowledge extraction and retrieval framework for quantitative finance.

Autonomous quantitative trading research platform that transforms stock lists into fully backtested strategies using AI agents, real market data, and mathematical formulations, all without requiring any coding.

Course Website Repo for JOURN 8006: Quantitative Research Methods in Journalism

UNMAINTAINED | R-package providing access to fundamental data and valuation metrics for thousands of publicly traded companies worldwide.

End-to-end RL trading framework with PPO agent, self-attention neural network, custom Gym environment, and advanced backtesting.

Official public repository of Berlin Quant Lab (BQλ), the quantitative finance initiative of the Berlin Investment Group (BIG). Featuring quantitative finance research, algorithmic trading strategies, market analyses, educational materials, and open-source projects.

A new era of cloud-native quantitative trading covering the complete pipeline of quant research + trading with automation at scale

Real-time forex trading system with modular architecture, multi-timeframe signal generation, GMM-based regime detection, Kelly-based risk management, and CLI tools for backtesting, monitoring, and performance analysis.

This repository contains the code for analyzing LGTBIQ-phobia on Twitter, focusing on Spanish tweets from June 28th (Pride Day) between 2015 and 2024, with a special focus on the impact of Elon Musk's acquisition of the platform. It includes data collection, toxicity classification using the Perspective API, statistical analysis, and visualization

Quantitative research of the Consumer Discretionary sector in the NYSE and NASDAQ exchanges to find an optimal pair of automotive stocks for use in a pairs trading strategy.

Extracted financial data(equity, commodity) via APIs and web scraping. Created technical indicators(MA, MACD, RSI) and conducted fundamental analysis. Designed, backtested and assessed trading strategies to calculate KPIs(Sharpe, Sortino etc.). Implemented ML strategies to achieve full automation

End-to-end quantitative finance portfolio demonstrating skills in financial modeling, risk analysis, and data-driven investment research.

This project investigates the nature of black hole singularities and the fate of an infalling observer. We explore the existence of strong and weak singularities, challenging the prevailing notion of a singularity as an unavoidable annihilation point.

Euro Macromechanica (EMM) Backtesting Ecosystem — EUR/USD M5 quant strategy backtest results across the full retail-broker trading era (since 2001; euro introduced 1999, cash 2002). Baseline 2003–Aug 2025; stress 2001–2002. Integrity: SHA-256, GPG, OTS; live run video proofs. Implemented ~10-15% of the full strategy—minimal yet self-sufficient.

A modular Python toolkit for advanced options pricing, volatility modeling, Greeks computation, and risk analysis. Includes Monte Carlo and Black-Scholes models, machine learning volatility surfaces, and interactive visualizations via Streamlit.

A production-ready, agentic AI pipeline that uses Google Gemini in a feedback loop with WorldQuant BRAIN to automatically generate, backtest, and refine quantitative trading signals.

The model focuses on predicting the impact of trading activities on stock prices using order flow imbalance, trading volume and price change