Experimental scenario analysis for real-life events forecasting with Codex or Claude

DeepMarket is a framework for performing Limit Order Book simulation with Deep Learning. This is also the official repository for the paper 'TRADES: Generating Realistic Market Simulations with Diffusion Models'.

High-performance C++ matching engine with unified market simulation, live market data streaming, and a browser-based dashboard

Rust Market Simulation Library with a Python API

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

A back-tester for testing stock trading strategies on historical data

MarketGPT: Developing a Pre-trained transformer (GPT) for Modeling Financial Time Series

Contingency Random Number Generator — numbers with controllable fat tails, volatility clustering, and scale convergence

{Frontend/Backend} Simulate stock trading and investment strategies with real-time data and portfolio management features.

SHS: Signal Herding Strength ABM for studying prediction-market signals and trader herding

SHS: Signal Herding Strength ABM for studying prediction-market signals and trader herding

Agent-based market adoption simulator with Bass diffusion model and JTBD analysis

Code for paper "Gradient-assisted calibration for financial agent-based models"

Interactive crypto market simulator that demonstrates how news, panic, and investor psychology can affect price movements.

A simple GUI for bristol stock exchange a minimal simulation of a limit order book financial exchange

AHMAPPO_LLM is an AI trading system using ML and RL to predict stocks. It processes data via ingestion, cleaning, and feature engineering. The reproducible pipeline enables end-to-end trading strategy development. Important files - model trainer, builder, AHMAPPO AI agent building, etc. are in private repo to preserve originality.

Energy market backtesting framework for European power trading. Purpose-built for DA auctions and intraday continuous markets with 15-minute MTU support. Write once, run in backtest, paper, and live modes without code changes.

bid/ask market engine

A hardened version of ABIDES-JPMC, with reworked API, configuration, and performance

Deterministic, Event-driven Core, with explicit risk management, Order & Intent state machines, and Queue semantics, aligning Backtesting and Live.