Haoyu-tech

Haoyu-tech / An-Avellaneda-Stoikov-market-making-research-project-built-on-real-Binance-Futures-BTCUSDT-L2-data.

Public

An Avellaneda-Stoikov market-making research project built on real Binance Futures `BTCUSDT` L2 data.

12
2
100% credibility
Found Mar 26, 2026 at 12 stars -- GitGems finds repos before they trend. Get early access to the next one.
Sign Up Free
AI Analysis
Python
AI Summary

Research project reproducing Avellaneda-Stoikov market-making backtests on real Binance Futures BTCUSDT order book data, with fees, latency, inventory limits, and HTML visualizations.

How It Works

1
📖 Discover the Research Project

You find this open project about testing a smart trading idea using real Bitcoin market data from a popular exchange.

2
📥 Get Everything Ready

You download the project files to your computer and prepare a simple workspace to run experiments.

3
📊 Capture Live Market Snapshots

You start collecting real-time pictures of the market order book and trades for a few minutes.

4
🚀 Run the One-Click Experiment

With one simple command, you launch the full test that simulates the trading strategy with realistic costs, delays, and limits.

5
⏳ Wait for Results to Appear

The project automatically runs tests under different conditions like fees, delays, and sizes, saving organized folders of outcomes.

6
📈 Open Interactive Charts

You view beautiful animated webpages showing quotes, fills, profits, and market changes over time.

💡 Learn Key Trading Insights

You discover how the strategy performs with real fees and risks, seeing thin edges vanish and the importance of speed.

Sign up to see the full architecture

5 more

Sign Up Free

Star Growth

See how this repo grew from 12 to 12 stars Sign Up Free
Repurpose This Repo

Repurpose is a Pro feature

Generate ready-to-use prompts for X threads, LinkedIn posts, blog posts, YouTube scripts, and more -- with full repo context baked in.

Unlock Repurpose
AI-Generated Review

What is Haoyu-tech/An-Avellaneda-Stoikov-market-making-research-project-built-on-real-Binance-Futures-BTCUSDT-L2-data?

This Python project delivers a complete research pipeline for Avellaneda & Stoikov's market making strategy using real Binance Futures BTCUSDT L2 data. It collects order book snapshots, diff-depth updates, and trades; reconstructs the book; then runs backtests incorporating inventory risk, fees, cash limits, and order/cancel latency. You get structured JSON outputs, HTML visualizations of quotes/fills/equity, and a one-command script to run collection through categorized experiments like fee/latency sweeps.

Why is it gaining traction?

Unlike toy simulators with synthetic data, it uses live Binance BTCUSDT L2 streams for realistic queue modeling and aggTrade replays, revealing how fees and latency often flip gross edges negative. Developers dig the end-to-end automation—collect data, backtest baselines plus variants (zero-fee, size sweeps), and generate animated HTML replays showing target/active quotes, fills, and PnL breakdowns. It's a practical Avellaneda-Stoikov market making GitHub repo that bridges paper theory to executable experiments.

Who should use this?

Quant researchers tuning Avellaneda-Stoikov optimal market making parameters on crypto data. Algo traders prototyping BTCUSDT strategies with inventory/cash constraints. Python devs in HFT firms validating the Avellaneda-Stoikov market making model paper against real Binance conditions before scaling.

Verdict

Grab it for research if you're into Avellaneda-Stoikov market making Python implementations—docs and one-click pipeline shine despite 12 stars and 1.0% credibility score signaling early maturity. Not production-ready, but forkable for longer backtests or tighter queue sims.

(198 words)

Sign up to read the full AI review Sign Up Free

Similar repos coming soon.