How much to risk

The same trading signals can produce a smooth compounding curve or a blown-up account depending only on how positions are sized. These pages explain the position-sizing methods a backtest must model honestly — fixed, fractional, Kelly, volatility- and risk-based — and how each changes the equity curve, the drawdown and the probability of ruin. Sizing is where a validated edge is either preserved or destroyed.

Position Sizing: Position sizing is the rule that converts a trading signal into a quantity to trade, and it is as decisive as the signal itself for a backtest's results. Methods range from fixed size and fixed-fractional risk to the Kelly criterion, volatility-based and risk-based sizing, governed by capital allocation and a per-trade risk budget. Because sizing compounds, it determines a strategy's growth rate, its worst drawdown and its risk of ruin — so a backtest that ignores realistic sizing is not a fair test.

Fixed Position Sizing

Sizing

Fixed position sizing is trading the same constant quantity on every trade regardless of account size, so a backtest measures the raw quality of the …

→

Fixed-Fractional Position Sizing

Sizing

Fixed-fractional position sizing risks a constant fraction of current account equity on every trade, so the rupee bet grows as the account grows and …

→

The Kelly Criterion

Sizing

The Kelly criterion is the position-sizing fraction that maximises the long-run geometric growth rate of capital, given by f* = W − (1 − W) ÷ b for a…

→

Volatility-Based Position Sizing

Sizing

Volatility-based position sizing scales each position inversely to the instrument's volatility, using a measure such as ATR or return standard deviat…

→

Risk-Based Position Sizing

Sizing

Risk-based position sizing sets the quantity so that hitting the predefined stop loses a fixed, chosen amount of money, computed as quantity = (risk%…

→

Portfolio Allocation

Allocation

Portfolio allocation is the decision of how to divide capital and risk across multiple strategies or instruments, where correlation between the compo…

→

Capital Allocation

Allocation

Capital allocation is the decision of how much total capital to actively deploy against a strategy versus hold in reserve, setting the ceiling within…

→

Risk Per Trade

Risk

Risk per trade is the fixed amount of capital, usually expressed as a small percentage such as 1 percent, that a trader budgets to lose on any single…

→

Frequently asked questions

Why does position sizing matter in a backtest?

Because returns compound, the sizing rule determines a strategy's growth rate, its deepest drawdown and its risk of ruin — not just the win rate or average trade. Two backtests of the same signals can look completely different under different sizing, so sizing must be modelled explicitly and realistically.

What is fixed-fractional position sizing?

Fixed-fractional sizing risks a constant fraction of current capital on each trade — for example 1% of the account. Position size therefore grows after wins and shrinks after losses, which compounds gains and cushions losing streaks, and is the most common sizing model in honest backtests.

Should I use the full Kelly fraction from my backtest?

Rarely. The Kelly criterion gives the growth-optimal fraction assuming the win rate and payoff are known exactly, which a backtest only estimates. Full Kelly is extremely volatile and unforgiving of estimation error, so practitioners typically use half-Kelly or less and treat the backtest's Kelly figure as an upper bound.