DUCKQUANT / THE QUANT & AI DIRECTORY
1,177 resources, ranked by in-directory PageRank
docker based platfrom for developing algo trading strategies. Very interesting combinations of open source components were used including for backtest…
dataflow programming framework. Similar and probably replaceable by sklearn.pipeline module. Uses for visiualization though not maintained with last commit…
Deep learning framework for HFT algorithmic trading strategy development
We introduce the first end-to-end Deep Reinforcement Learning based framework for active high frequency trading.
Built a trading algorithm in Python for the Tesla stocks returning in 39% higher returns than a simple buy and hold strategy, over a…
Course Material for the machine learning in financial context bootcamp
This is my github repository where I post trading strategies, tutorials and research on quantitative finance with R, C++ and Python. Some of the…
unofficial repo based on . It's incomplete and not updated
Hard fork of and form the trading strategy as a classification problem with -1 (sell) 0 (hold) 1 (buy). Models used are…
Technical experimentations to beat the stock market using deep learning :chart with upwards trend
Firstly, multiple effective factors are discovered through IC value, IR value, and correlation analysis and back-testing. Then, XGBoost classification model is…
Reinforce Your Career: Machine Learning in Finance. Extend your expertise of algorithms and tools needed to predict financial markets.
Boilerplate/Starter code for trading on binance using Machine Learning. Provides a basic pipeline for data gathering, feature creation, training, testing and…
A walkthrough of using the gym-anytrading environment for reinforcement learning applications leveraging custom datasets.
MATLAB example on how to use Reinforcement Learning for developing a financial trading model
base framework trading bot for crypto. Stores data in local mongodb instance and supports backtest and live trading on and which are 12-15th ranked…
Reinforcement Learning for finance.
This is code for Multi-period Learning for Financial Time Series Forecasting (MLF, published in KDD 2025), which incorporates multiple inputs with varying.
Trained an automated stock trading model with companies' fundamental data using FinRL, a Deep Reinforcement Learning library developed by AI4Finance.
PyTorch Implementation of "FinTSB: A Comprehensive and Practical Benchmark for Financial Time Series Forecasting" (FCS & ICAIF 2025 Workshop Best Paper).
Publication: Statistical Learning with Sublinear Regret of Propagator Models. Published Jan 12, 2023.
Publication: Deep Learning for Digital Asset Limit Order Books. Published Oct 3, 2020.
Publication: Learning to simulate realistic limit order book markets from data as a World Agent. Published Sep 26, 2022.
Publication: Learning who is in the market from time series: market participant discovery through adversarial calibration of multi-agent simulators. Published Aug 2, 2021.
Publication: An Offline Learning Approach to Propagator Models. Published Sep 6, 2023.
Publication: Spatio-Temporal Momentum: Jointly Learning Time-Series and Cross-Sectional Strategies. Published Feb 20, 2023.
Publication: Certified Alpha Capacity: Statistical Arbitrage When Learning Takes Time. Published Oct 1, 2026.
Publication: Jacobian Rank Collapse in Decision-Focused Learning. Published Sep 30, 2026.
Publication: Pushing the Efficiency-Regret Pareto Frontier for Online Learning of Portfolios and Quantum States. Published Feb 6, 2022.
Publication: Adversarial Training for Deep Hedging in Nonstationary Markets. Published Oct 5, 2026.
Publication: Deep Hedging: Learning to Remove the Drift under Trading Frictions with Minimal Equivalent Near-Martingale Measures. Published Nov 15, 2021.
Publication: Transfer Learning (Il)liquidity. Published Dec 12, 2025.
Publication: Statistical Learning of Value-at-Risk and Expected Shortfall. Published Sep 14, 2022.
Publication: A data-driven merit order: Learning a fundamental electricity price model. Published Jan 6, 2025.
Publication: DoubleAdapt: A Meta-learning Approach to Incremental Learning for Stock Trend Forecasting. Published Jun 16, 2023.
Publication: Robo-advising: Learning Investors' Risk Preferences via Portfolio Choices. Published Nov 5, 2019.
