Systematic Quantitative Trading

Where Precision Meets Performance

Auroxyl Capital deploys fully automated, machine-learning-driven strategies across U.S. equities and ETFs, executing via Interactive Brokers (IBKR). Currently operating as a private fund — not accepting investors, open to collaboration only.

View Track Record

Track Record

Auditable Performance

Combined 60/40 portfolio — 60% ETF Rotation + 40% ML Prediction. Backtested Feb 2022 – Dec 2025. All returns are gross of fees, computed on a mark-to-market basis. Executed via Interactive Brokers.

122.0%

CAGR

Feb 2022 – Dec 2025

7.41

Sharpe Ratio

Annualised

-11.5%

Max Drawdown

Peak to trough

22.3x

Cumulative Return

3.9 years

10.63

Calmar Ratio

CAGR / MDD

70.7%

Win Rate

Daily

+1.60%

Mean 5-Day Return

Per holding period

4 / 4

Positive Years

Every calendar year

Growth of $1 Invested

Feb 2022 – Dec 2025 | Hover to inspect

Year	Return
2022	+40.3%
2023	+110.8%
2024	+181.9%
2025	+167.6%

Investment Approach

Multi-Strategy Architecture

Capital is allocated 60/40 across complementary strategies that adapt to market regimes in real time. Every decision is systematic. Every trade is fully automated.

Equity Alpha (40%)

Machine-learning ensemble ranks thousands of U.S. equities daily on proprietary alpha factors, selecting top-conviction names for short-horizon overlapping cohort rotation.

ETF Rotation (60%)

Regime-aware allocation across broad market and sector ETFs. A Bayesian risk model dynamically shifts between full exposure and capital preservation based on macro conditions.

Fully Automated

End-to-end automation from data ingestion and signal generation to order routing and portfolio reconciliation. Zero manual intervention required — the system operates 24/7 with built-in circuit breakers.

Infrastructure

Built for Precision

Institutional-grade infrastructure engineered for reliability, speed, and transparency.

Machine Learning Ensemble

Multi-seed gradient boosting models trained on proprietary alpha factors. Walk-forward validation ensures out-of-sample robustness across all market cycles.

Autonomous Execution

Smart order routing with limit-order logic, partial-fill management, and TWAP scheduling. Every trade is tracked with full audit trail including signal time, decision price, and fill attribution.

Real-Time Risk Engine

Continuous position monitoring with margin checks, circuit breakers, and automated stop-loss management. Regime detection adapts exposure within minutes of market shifts.

Adaptive Retraining

Quarterly automated model retraining with incremental data updates. Statistical validation gates prevent model degradation from entering production.

Auroxyl Trader — Portfolio Dashboard

Auroxyl Execution Platform — Real-Time Portfolio Dashboard

Auroxyl Trader — Positions

Position Management — Grouped by Strategy with Live P&L

Auroxyl Trader — Trade History

Auroxyl Trading Platform — Trade History

Trade History — Full Audit Trail with P&L Attribution

Risk Framework

Defence in Depth

Multiple independent safeguards operate at every layer of the system, from individual position limits to portfolio-wide circuit breakers.

Circuit Breakers

Automatic trading halt on anomalous conditions, stale data, or consecutive failures

Position Limits

Daily trade caps, per-position sizing rules, and margin utilisation guardrails

Regime Detection

Bayesian risk model identifies bear regimes and shifts to capital preservation in real time

Full Audit Trail

Every signal, order, and fill is logged with timestamps, prices, and slippage metrics

Important

Risk Warning

Small-Cap Exposure

The ML prediction strategy primarily trades small and micro-cap stocks with low liquidity. This limits viable capital deployment — large position sizes will incur significant market impact and slippage.

Capacity Constrained

Due to the low-liquidity nature of the equity alpha signals, the strategy does not scale beyond small account sizes. Performance may degrade materially with increased capital.

Past ≠ Future

All performance shown is backtested and does not guarantee future results. Trading involves substantial risk of loss. Invest only what you can afford to lose.

Important Disclosure

Past performance is not indicative of future results. The performance data presented represents backtested results and may not reflect actual trading outcomes. All returns are gross of fees and transaction costs unless otherwise stated. The ML prediction strategy trades small and micro-cap stocks with limited liquidity — it is capacity constrained and not suitable for large capital deployment. Investing involves risk, including the possible loss of principal. This fund does not accept investors and is open to collaboration only. All trading is executed via Interactive Brokers.