This repository features a collection of in-depth quantitative trading strategies, as well as strategies based on technical analysis.

A pairs trading strategy using BTC and ETH, incorporating moving averages, Z-Score, and the Kelly Criterion for optimal trade sizing and risk management.

A collection of small quantitative finance projects written in Python and Go, covering a range of topics such as image recognition using TensorFlow, Kalman filtering, the Kelly Criterion, Monte Carlo simulations, pairs trading strategies, and portfolio optimization techniques.

An exposition of a simple pairs trading strategy on two stocks (Bajaj Finserv and Indian Bank) in the Nifty500, at the one-minute time frequency, in order to demonstrate some of the core ideas of statistical arbitrage strategies.

An algorithmic approach to select pairs of stocks for pairs trading.

Built a pairs trading strategy in emerging markets using a rolling Kalman-filter beta and spread half-life, with z-score position sizing, and comprehensive back-testing with liquidity adjustments and transaction cost analysis for enhanced risk management

Statistical arbitrage algorithms implemented in python

Algorithmic pairs trading sniffer.

On-going project: I will be implementing a combination of pairs trading strategies in attempt to see which type performs best after backtesting. The main ideas involve cointegration, kalman filter, copulas, and machine learning approaches. Since it is a market-neutral strategy, we will analyse the performance on its alpha rather than sharpe ratio.

The project aims to design and implement a pairs trading algorithm to identify and exploit temporary mispricing opportunities between correlated assets in financial markets.

This project involves using a combination of statistics along with financial thoery to demonstrate a popular trading strategy used in equity markets: Pairs Trading.

Non-Linear Cointegration in Pairs Trading

The notebook with the experiments to replicate and enhance the stock clustering proposed by Han(2022) for alogtrading, with KMeans Optimization

Design your own Trading Strategy

Applying Machine Learning Techniques To Assess Whether A Country’s Currency Can Predict The Movement Of Their Respective Stock Market Index

A pairs trading strategy

Using Copulas model to capture non-linear relationship between stock pairs and conduct statistical arbitrage by pairs trading strategies.

RESTful API for trading stocks (single or pairs), deployed on Heroku

jquants-pairs-trading is a python library for backtest with japanese stock pairs trading using kalman filter, J-Quants on Python 3.8 and above.