Strategies/ML Aggressive

ML Aggressive

Momentum Strategy

ML Aggressive uses the shared LightGBM sector-rotation pipeline to rank 14 tradable ETFs: the 11 SPDR sectors plus QQQ, IWM, and GLD. On each rebalance it selects the top three signals, sizes them with an inverse-volatility and model-confidence blend, and keeps market exposure high because it does not apply the defensive regime-scaling overlay. It is the higher-beta version of the ML stack: same signal engine as ML Defensive, but without the risk-off throttle.

High RiskWeeklyMachine learningTop 3 rotationLive Alpaca account
Analyze Portfolio

What it does

A machine-learning model ranks 14 ETFs every cycle and pushes capital into the top 3 with conviction-weighted sizing.

Best for

Investors who want the ML signal engine in its most aggressive form, with little intentional cash drag and no regime-based de-risking.

What to expect

Higher upside and higher drawdown sensitivity than the defensive variant. Holdings can rotate quickly because the model is always trying to stay near its strongest signals.

Typical Holdings (Dynamic Strategy)

QQQXLKXLC

Representative basket only. The live bot dynamically rotates into the current top 3 model picks from its 14-ETF universe.

Live Account Performance

● Real Alpaca Paper Account

Compare with

Normalised to $10,000 start. Data from live Alpaca paper account — reflects real orders, real fills, and real risk management decisions.

Backtest Simulation · Not Real Trading

5-Year Historical Simulation

Simulated using a multi-timeframe momentum proxy and inverse-volatility sizing — approximates the ML signal engine. Run scripts/generate_ml_backtest.py for exact results.

How It Actually Trades

Pro

Ready to put this strategy to work?

Open a paper position and track it against the market — no real money at risk.

Analyze Portfolio← All Strategies

Live chart: real Alpaca paper account data. Simulation chart: historical price data from Yahoo Finance with representative fixed weights. Past performance does not guarantee future results.