SledgeKey Learn

Backtesting Academy

Every term you encounter in a SledgeKey backtest, explained. Configuration parameters, performance metrics, risk measures, and the methodology that keeps results honest.

Configuration

Rebalance Frequency

How often the portfolio rescreens and resets weights. Quarterly, monthly, or annual, each with different cost and signal trade-offs.

Transaction Cost

The slippage and fees deducted on every trade. The single most underestimated drag on backtested returns.

Weighting Metric

How positions are sized — equal weight, market cap, revenue, or other fundamentals. Determines whether the strategy is concentrated or balanced.

The maximum number of positions in the portfolio. Controls diversification and the dilution of your top picks.

Max Position Size

A cap on how much of the portfolio any single stock can occupy. Prevents concentration risk in cap-weighted portfolios.

Backtest Window

The historical period the strategy is tested over. Length, regime coverage, and where you start all matter.

Initial Capital

The starting balance of the simulated portfolio. Doesn't change percentage returns, but matters for absolute dollar metrics.

Benchmark Selection

The reference index that performance is compared against. SPY is the default, and choosing wisely matters more than people think.

Hedge Protection

An optional protective put overlay that triggers below a threshold. Costs premium in exchange for downside truncation.

Performance Metrics

The cumulative percentage gain or loss over the backtest period. The headline number, but rarely the most useful one.

Annual Return (CAGR)

The constant annual rate that compounds to the same total return. The fairest single-number measure across windows of different lengths.

Excess return per unit of total volatility. The standard measure of risk-adjusted return.

Annualized standard deviation of returns. The denominator of Sharpe and a proxy for risk.

The largest peak-to-trough decline. The pain metric, what it would have felt like to ride this strategy.

The percentage of months with positive returns. A measure of consistency, not magnitude.

Best & Worst Month

The single-month extremes. Helpful for sizing your stomach against the strategy.

Calendar Year Returns

Performance broken out year by year. Reveals whether returns came from one lucky window or showed up consistently.

Risk Metrics

Sharpe's better-behaved cousin — divides excess return only by downside volatility, since upside surprises aren't risk.

Annual return divided by max drawdown. Measures return per unit of pain rather than per unit of volatility.

Value at Risk (VaR 95%)

The 5th percentile of monthly returns. The threshold worse than 95% of months, useful for tail planning.

Conditional VaR (CVaR 95%)

The average return inside that worst 5% of months. Captures how bad it gets when it gets bad.

Whether the return distribution leans left or right. Negative skew means rare large losses, positive means rare large gains.

How fat the tails of the return distribution are. High kurtosis means more extreme months than a normal distribution would predict.

Drawdown Episodes

The top five peak-to-trough declines with their dates, depths, and recovery durations. The full pain catalog.

Rolling 12-Month Sharpe

Sharpe ratio computed over a moving 12-month window. Reveals whether risk-adjusted performance was stable or episodic.

Rolling 12-Month Returns

Trailing-year return at every point in time. Shows the strategy's hit rate against a 1-year holding period.

Methodology

What Is Backtesting?

Simulating a strategy on historical data to estimate how it would have performed. The promise, the pitfalls, and the framing.

Survivorship Bias

When a backtest only includes companies that still exist today. Inflates returns by quietly excluding the failures.

Look-Ahead Bias

Using data the strategy could not have known at the time. Subtle, common, and devastating to result credibility.

Point-in-Time Data

Using the financial data exactly as it was reported on each historical date — restated values not allowed.

Out-of-Sample Testing

Validating a strategy on data that wasn't used to design it. The single best defense against overfitting.

Designing a strategy that worked in the past because it was tuned to the past. The cardinal sin of backtesting.

Rebalancing Methodology

How a portfolio resets at each period — the discipline that separates a real strategy from a buy-and-forget portfolio.

The return of holding short-term Treasuries. The opportunity cost embedded in every Sharpe and Sortino calculation.

Hedging

Protective Puts

Buying put options to truncate downside. The mechanic, the cost, and why SledgeKey applies them at the portfolio level rather than per stock.

Black-Scholes-Merton

The pricing model SledgeKey uses to value protective puts. How the inputs map to the cost you pay each rebalance.

Treasury Rates as Risk-Free

Why short-term Treasuries are the proxy for the risk-free rate, and how SledgeKey uses live treasury data in its option pricing.

Implied Volatility from Returns

How volatility is estimated for option pricing in a backtest, when there's no live options market to read it from.