Quantix
An algorithmic trading module that scans multiple asset markets for statistical price discrepancies, optimizes weights using mean-variance analysis, and places trade signals.
Launch Specifications
Product Overview
Quantix executes automated statistical trading. It calculates cointegration vectors across historical assets, calculates risk metrics, and uses numerical optimization to construct portfolios that maximize Sharpe ratios.
- Real-time asset cointegration scanning.
- Dynamic mean-variance portfolio sizing.
- Automated stop-loss risk management.
- Historical backtesting report runner.
What Quantix Can Generate
Finding historical price-spread relationships.
Sizing trades using Scipy solvers.
Auto-reducing capital size on high volatility.
Saving daily performance vectors.
The Problem
Scoping statistical opportunities across thousands of asset pairs manually is impossible. Standard static portfolios suffer from large drawdowns during volatile structural market shifts.
Our Solution
A automated numerical optimizer that calculates correlation vectors, sizes positions dynamically based on volatility, and executes trades via the MT5 bridge.
Technical Architecture
Quantix executes on a scheduled loop. It pulls prices from Redis, runs correlation tests using NumPy, feeds metrics to Scipy optimization pipelines, and pushes signals into execution vectors.
Arbitrage Scanning & Optimization Pipeline
Tech Stack
Dashboard View Simulation
Cointegration Scanner
Key Engineering Challenges
- •Controlling transaction costs which can eat arbitrage profits.
- •Solving convergence failures in Scipy optimization routines.
- •Mitigating correlation decay during volatile structural shifts.
Key Lessons Learned
- ✓Including transaction costs directly in the solver prevents it sizing micro-trades.
- ✓Dynamic rolling lookbacks track market changes better than static data frames.
- ✓Scaling risk exposure relative to correlation metrics preserves capital.
Development Roadmap
Pair Scanner
Numerical cointegration tests.
Sharpe Optimizer
Scipy mean-variance execution.
Multi-Asset Engine
Extending models to futures and crypto.
Related Products
Every product is built with a focus on solving real problems.
Interested in engineering collaboration, specialized quantitative models, or custom educational AI solutions? Let's connect.