Research
Long-form analysis and frameworks for systematic traders, allocators, and quants. Published when ready, not on a calendar.
- Research·Methodology
Out-of-Sample Testing: Protocols That Actually Work
Most "out-of-sample" tests are contaminated by researcher iteration. The protocols that actually work share three features: pre-registration, hold-out segregation, and one-shot evaluation.
·8m - Research·Allocation
In-House vs Allocator-Managed Quant: A Total-Cost Analysis
Build a quant team in-house or allocate to an external systematic manager. The total-cost analysis usually favors allocation for sub-billion AUMs and in-house for sufficient scale.
·6m - Research·Methodology
Backtest vs Walk-Forward vs Paper Trading: When to Use Which
Three distinct evaluation regimes serve three distinct purposes. The mistake is treating them as alternatives rather than as a sequence.
·6m - Research·Metrics
Sharpe vs Sortino vs Calmar: Choosing the Right Metric
Three risk-adjusted return metrics; three different stories. Knowing which to lead with for a given strategy and audience is the difference between honest reporting and selective reporting.
·6m - Research·Methodology
Discretionary vs Systematic: A Hybrid Framework
The discretionary-vs-systematic debate is mostly false framing. The actual question is which decisions to systematize and which to leave human-judgment-driven.
·6m - Research·Allocation
Single Strategy vs Ensemble: The Diversification Math
Running one strong strategy or a portfolio of weaker strategies. The math favors ensembles in most cases — but only if the diversification is real.
·6m - Research·Methodology
Meta-Labeling: Filtering Primary Signals With a Secondary Model
Meta-labeling is a two-stage modeling pattern: a primary signal generator emits trade ideas, and a secondary model filters which ideas to act on. The technique improves precision at the cost of recall.
·7m - Research·Methodology
Monte Carlo for Strategy Validation: Walk-Throughs and Traps
Monte Carlo simulation is a useful sanity check on strategy robustness — and a popular tool for fooling yourself if applied carelessly. Three legitimate uses, two common traps.
·7m - Research·Risk
Correlation Decay: When "Uncorrelated" Strategies Converge in Stress
Strategy correlations are not stable. The strategies you diversified into during normal markets often co-move in crisis — exactly when you needed the diversification most.
·7m - Research·Methodology
From Backtest to Live: The Institutional Deployment Checklist
A working backtest is the start of deployment, not the end. The institutional checklist that separates strategies that survive their first live month from strategies that don't.
·9m - Research·Metrics
Sharpe Ratio: A Complete Guide for Algorithmic Traders
Sharpe is the default metric in systematic trading and the most often abused. The complete practitioner's guide to the math, the gotchas, and what Sharpe does and doesn't tell you.
·9m - Research·Methodology
What Is Walk-Forward Optimization (and Why It Beats Single-Period Backtesting)
Walk-forward optimization is the institutional standard for strategy validation. Here's the mechanics, the parameter choices, and why a single-period backtest is structurally incapable of catching overfitting.
·9m - Research·Position Sizing
Kelly Criterion in Practice: Half-Kelly, Fractional Kelly, and the Case Against Full Kelly
Full Kelly is mathematically optimal in expectation and operationally insane. Here's why fractional Kelly dominates institutional practice — and how to set the fraction.
·7m - Research·Execution
Slippage Modeling: The Difference Between Paper and Live P&L
Slippage is the largest single gap between backtest performance and live performance for most retail systematic strategies. Three escalating levels of realism — and why the conservative side is almost always the right call.
·7m - Research·Methodology
Why Most Retail Backtests Overfit — And the Institutional Fix
Most retail backtests beat the live performance by 2–5×. The reason is selection bias, and it is structural — not a discipline issue. Here's what institutional research does differently.
·9m - Research·Methodology
Statistical Significance in Trading: How Many Trades You Actually Need
Most retail backtests claim edge they cannot prove. Here's the math on minimum sample sizes for credible strategy validation — and why "looks profitable" usually doesn't pass the bar.
·8m - Research·Risk
Regime Detection: When to Turn a Strategy Off
Most strategies have a regime where they earn their backtest Sharpe and another where they hemorrhage. Real-time regime detection is the discipline that decides when to turn the strategy off.
·8m - Research·Risk
Drawdown vs Volatility: Which Actually Predicts Strategy Survival
Volatility is what statisticians measure; drawdown is what investors live through. The two metrics tell different stories — and the case for drawdown as a primary survival metric is stronger than the textbook implies.
·8m - Research·Position Sizing
The R-Multiple Framework: Position Sizing for Systematic Traders
The R-multiple framework expresses every trade in units of risk, not dollars. It is the cleanest position-sizing primitive for systematic strategies — and the one most often misused by retail.
·7m - Research·Allocation
Risk Parity vs Equal-Weight: Choosing a Strategy Allocator
Risk parity allocates equal volatility contribution; equal-weight allocates equal capital. They produce different portfolios with different failure modes — and the choice matters more than most allocators realize.
·7m