Philosophy
Capture the Upside, Control the Downside
We believe disciplined, evidence-based investing outperforms emotion. Our process is fully systematic: the same rules are applied the same way every month.
Losses and gains are not symmetric. A 30% decline requires a 43% gain to recover. We believe limiting drawdowns while staying invested in equities is one of the most dependable paths to long-term compounding. Apex QuantumAlpha aims to outperform the S&P 500 over full market cycles while managing downside risk.
How the Process Works
1. Broad Universe
Each month we evaluate approximately 1,000 U.S. large-cap stocks.
2. Deep Factor Library
Every stock is measured across dozens of technical and fundamental factors, calculated over multiple time horizons. We look beyond whether a company is good and ask whether its stock is positioned to outperform now.
3. Proprietary Neural Network
Our AI engine is a neural network built to identify patterns in the factor data that are associated with future returns. It uses a layered design in which each stage learns from what the previous stage missed. The forecasts are then combined into a single score for every stock.
Like any quantitative model, our neural network is built on historical data and may not perform as expected in future markets. Models can contain errors, and patterns found in past data may weaken or disappear. No model can, by itself, reliably determine which securities to buy or sell.
4. Risk-Controlled Portfolio Construction
The model identifies opportunity, and the optimizer determines how much risk to take. Using a proprietary risk model, we build a portfolio of 40–60 of the highest-ranked stocks. The optimizer seeks the highest expected return within strict constraints:
Sector and position size limits
Beta targets
Tracking error limits relative to the S&P 500
Liquidity requirements
Turnover limits
5. Monthly Rebalancing
Portfolios are rebalanced on the second business day of each month.
What Makes Apex Different
Institutional pedigree: our investment team has led quantitative equity and asset allocation strategies at GMO, Guggenheim Partners, Mellon Capital, and other leading firms.
Neural Network: a proprietary neural network trained on factor data drives stock selection, rather than a simple screen.
Disciplined risk management: risk controls are built into portfolio construction, not added afterward.
Transparency: separately managed accounts at Charles Schwab give you full visibility into every holding.