HFTFramework utilized for research on " A reinforcement learning approach to improve the performance of the Avellaneda-Stoikov market-making algorithm "

Implemented the Avellaneda-Stoikov market-making strategy in an automated trading algorithm. Completed as part of the Optiver Ready Trader Go competition.

Repository for market making ideas

Real-time adaptive market-making system using Hawkes processes + deep learning to predict order flow toxicity and avoid adverse selection. Avellaneda-Stoikov + MHLOBT neural network + LOBSTER L3 data.

Sentiment-driven market making with Avellaneda–Stoikov pricing, dynamic risk limits, and Streamlit dashboard.

Optimal control of risk aversion in Avellaneda Stoikov high frequency market making model with Soft Actor Critic reinforcement learning

GPU-Accelerated Limit Order Book Simulator with Formally Verified Market Making

Implementation of HFT backtesting simulator and Stoikov strategy

aAvellaneda-Stoikov HFT market making algorithm implementation

Python code for High-frequency trading in a limit order book by Marco Avellaneda and Sasha Stoikov