π― Algorithm Suite
Our trading platform implements three complementary algorithm families optimized for different market conditions:
π Regime Detection
Hidden Markov Models identify market states (trending, mean-reverting, volatile) in real-time.
β Adapts strategy selection dynamically
π€ Agent-Based Models
Chiarella Multi-Agent simulates heterogeneous traders (fundamentalists, chartists, noise).
β Predicts price impact & volatility
β‘ Adaptive Execution
CARA/Risk Parity/Sparse optimize portfolio allocation under risk constraints.
β Maximizes Sharpe with controlled drawdowns
π Regime Detection via HMM
We use a 3-state Hidden Markov Model to classify market conditions:
States
π Trending
Characteristics:
- High autocorrelation
- Low mean reversion
- Positive momentum
Strategy: Breakout/Momentum
βοΈ Mean-Reverting
Characteristics:
- Negative autocorrelation
- Fast reversion (Ο < 5 min)
- Stable volatility
Strategy: Pairs/Stat Arb
π₯ Volatile
Characteristics:
- High variance
- Low predictability
- News/event-driven
Strategy: Reduce exposure
Implementation
Performance: 85% accuracy on S&P 500 data (2018-2024), < 100ΞΌs latency per update.
π€ Chiarella Agent-Based Model
Simulates market microstructure with 3 trader types:
π Fundamentalists
Mean revert to fair value. Stabilizing force.
π Chartists
Follow trends. Destabilizing (momentum).
π² Noise Traders
Random demand. Liquidity providers.
Price Dynamics
p(t)
Calibration: Fit \( \alpha_F, \alpha_C, w_i \) to historical order flow. Use case: Predict impact of large orders (>1% ADV).
β‘ Adaptive Portfolio Strategies
Three optimization frameworks for different objectives:
1. CARA (Constant Absolute Risk Aversion)
Closed-form solution: \( \mathbf{w}^* = \frac{1}{\gamma} \boldsymbol{\Sigma}^{-1} \boldsymbol{\mu} \) (rescaled to sum to 1).
Best for: Short-term mean-reversion strategies with stable covariance.
2. Risk Parity
Equalizes risk contribution across assets. Best for: Diversified portfolios with heterogeneous volatilities.
3. Sparse Optimization (L1 Penalty)
Promotes sparsity (few non-zero positions). Best for: High transaction costs, limited capital.
Without Sparse Penalty (Ο=0)
With Sparse Penalty (Ο=0.05)
π Integration: Adaptive Pipeline
Data β Regime Detection (HMM)
Market Data (1-min bars) β Viterbi Algorithm β State: {Trending, Mean-Reverting, Volatile}
Regime β Strategy Selection
Trending β Momentum Β· Mean-Reverting β Stat Arb Β· Volatile β Risk-Off
Strategy β Chiarella Simulation
Ξ±_F=0.5, Ξ±_C=0.3, w_F=0.6, w_C=0.3, w_N=0.1 Β· 1000 paths (Ξt=1s, horizon=5min)
Position Sizing β Adaptive Optimization
High Costs β Sparse (L1) Β· Low Costs β Risk Parity Β· Mean-Reversion β CARA (Ξ³=2.0)
Execution β Trade Signals
Generate orders β TWAP/VWAP slicing β Send to broker β Monitor fills β Loop
π Performance Metrics
Sharpe Ratio
2.8
Annualized (2023-2024 backtest)
Max Drawdown
-8.2%
Controlled by risk parity
Win Rate
62%
On 10,000+ trades
Regime-Specific Performance
π Trending
Sharpe: 3.2
Strategy: Momentum (breakout)
Avg Hold: 12 hours
βοΈ Mean-Reverting
Sharpe: 4.1
Strategy: Stat Arb (pairs)
Avg Hold: 45 minutes
π₯ Volatile
Sharpe: 0.9
Strategy: Reduced exposure
Avg Hold: N/A (mostly flat)
π Ressources & Documentation
π Interactive Notebooks
π Unlock interactive Jupyter notebooks with an Educational or Professional account.
Try it out live by subscribing to a Hobbyist tier and access the interactive Streamlit platform.
Available notebooks:
β’ Regime Detection (HMM)
β’ Kalman Filter Market Making
β’ Mean Field Games Portfolio
β’ Differential Evolution
β’ Sparse Mean Reversion
π Theoretical Documentation
Hidden Markov Models theory with Forward-Backward and Viterbi algorithms
π Chiarella Agent-Based Model
Multi-agent market microstructure with heterogeneous traders (Fundamentalists, Chartists, Noise)
βοΈ Adaptive Portfolio Strategies
Risk Parity, Sparse L1 optimization, and CARA utility maximization
π Try it Live
π― Streamlit Interactive Platform
Test algorithms on real market data with an interactive interface
π³ View Pricing & Subscription Tiers
From Hobbyist (β¬9/month) to Professional (custom pricing)
π Free Beta Access
Try the platform with limited features. No credit card required.
Launch Beta β