Tutorials on algorithmic trading#
Here is a collection of blog posts and tutorials that are relevant for algorithmic trading in Python.
Financial Models and Numerical Methods#
A collection of Jupyter notebooks based on different topics in the area of quantitative finance.
Gallery of Jupyter Books#
Multiple data research and quantative finance books for Python and Jupyter
Teddy Koker’s blog#
Articles on trading, gambling and machine learning.
Backtesting option strategy with Backtrader#
An example tutorial.
ML Algotrading Wiki#
A wiki website with research and various news sources.
MLTraders’ Algotrading and Machine Learning work for everybody..
Pair Trading: A market-neutral trading strategy with integrated Machine Learning#
The primary goal in an investment endeavor is the implementation of strategies that minimize the risk while also maximizing the financial gain or return from the said investment. While there have been many popular strategies and techniques developed over the years that point towards the same goal, the ‘Pairs-Trading’ strategy is one that has been used to great extent in modern hedge-funds, for its simplicity and inherent market-neutral qualities.
Dead Simple 2-Asset Portfolio that Crushes the S&P500#
This is an update to the original blog series that explored a simple strategy of being long UPRO and TMF in equal weight, inverse volatility and inverse-inverse volatility. This strategy crushed the cumulative and risk-adjusted returns of the benchmark SPY etf.
Didact AI#
The anatomy of an ML-powered stock picking engine.
Trend following regime filter with HMM#
In this article the Hidden Markov Model will be utilised within the QSTrader framework as a risk-managing market regime filter. It will disallow trades when higher volatility regimes are predicted. The hope is that by doing so it will eliminate unprofitable trades and possibly remove volatility from the strategy, thus increasing its Sharpe ratio.
Uniswap v3 and Aave delta hedged strategy#
A blog outlining an example trading strategy creating Uniswap V3 liquidity provision position which is delta hedged using Aave lending protocol.
Read post. 30 Industry-Relevant Quant Finance Projects ——————————————-
A curated list of 30 project ideas, ranging from intermediate to advanced, aimed at candidates targeting quant research, market risk, model validation, derivatives pricing, or credit roles. The projects are grouped by domain and are designed to demonstrate depth rather than surface familiarity: build them end to end and they double as portfolio pieces for interviews.
The list spans six areas. Market Risk covers historical-simulation and parametric VaR (EWMA/GARCH), Monte Carlo VaR with full revaluation, stress testing (2008, COVID-19, inflation shock) and VaR backtesting (Kupiec, Christoffersen, Basel traffic light). Derivatives Pricing runs from Black-Scholes and binomial trees (CRR, Leisen-Reimer) through Monte Carlo for Asian/barrier/lookback options, finite-difference schemes (explicit, implicit, Crank-Nicolson) and implied-volatility-surface / SVI calibration. Volatility Modeling includes GARCH/EGARCH/GJR-GARCH, Heston, Dupire local volatility, SABR and realized-volatility forecasting from high-frequency data. Fixed Income covers SOFR/OIS and Treasury curve construction, bond risk (duration, convexity, key-rate duration), swap pricing, and Hull-White/Vasicek short-rate models. Credit Risk spans PD models (logistic regression, XGBoost), IFRS 9 expected credit loss, LGD via Jacob-Frye, CreditMetrics portfolio VaR and survival analysis (Kaplan-Meier, Cox). Quantitative Research closes with cointegration pairs trading, multi-factor investing, ML return prediction (XGBoost, LightGBM, LSTM), ARIMA/SARIMA/VAR forecasting and a reinforcement-learning trading agent (DQN/PPO) with transaction costs. A bonus tier lists advanced systems used at hedge funds and banks — XVA engines, copula portfolio risk, Longstaff-Schwartz exotics, Black-Litterman, HMM regime detection, and limit-order-book microstructure analysis.
Mentioned by Mehul Mehta (Lead Quant at OCC) in this LinkedIn discussion, where he advises building projects that demonstrate depth rather than just familiarity.
By Mehul Mehta.