Tagged “risk-management”
-
One Equity Curve Is One Sample
A backtest gives you a single path, not a distribution. How to bootstrap trades and blocks to see the range of outcomes the same strategy could produce.
-
Running More Than One Strategy at Once
Two strategies that each work can be worse together. How correlation, overlapping exposure, and capital allocation decide whether combining helps.
-
What to Compare a Strategy Against
A performance figure alone means nothing. How to choose a benchmark, build null models, and match them to a strategy so the comparison is fair.
-
Backtesting a Strategy That Can't Fill at Once
When one decision becomes many child orders, a single-fill backtest overstates it. How to model a slicing schedule and find a strategy's capacity.
-
Is Algorithmic Trading Profitable?
The honest answer is that it is profitable for some participants and not most retail ones. What the question leaves out, and what the real costs are.
-
Regime Change and Why Strategies Decay
Strategies stop working for four distinguishable reasons. How to tell decay from a normal drawdown, and why the distinction has to be defined in advance.
-
Multiple Testing: Why Your Best Result Is Probably Noise
The maximum of many noisy estimates is biased upward. Why the count of strategies you tested changes what the winner means, and how to account for it.
-
Modelling Transaction Costs in a Backtest
Costs are the difference between a backtest and a fantasy. How to model fees, spread, slippage, and holding costs, and why turnover decides everything.
-
What Sits Between a Backtest and a Live Bot
The components a backtest never needs: a real-time feed, persistent state, position reconciliation, idempotent ordering, monitoring, and a kill switch.
-
What Paper Trading Catches, and What It Misses
Paper trading validates plumbing, not edge. The failure classes it reliably exposes, the ones it structurally cannot, and how long to run it.
-
Position Sizing and Risk Management Basics
Survival comes before edge. How position sizing, drawdown math, and volatility targeting decide whether an account lives long enough to matter.
-
How Maximum Drawdown Is Calculated
Maximum drawdown is the deepest peak-to-trough fall in an equity curve. The four-line calculation, the variants worth reporting, and what the number hides.
-
Sortino vs. Sharpe: Two Ways to Divide by Risk
Sortino replaces Sharpe's standard deviation with downside deviation. What changes, what doesn't, and when the distinction is worth the extra complexity.
-
What the Sharpe Ratio Actually Measures
The Sharpe ratio is excess return divided by its own standard deviation. How to compute it, how annualization works, and the assumptions it quietly makes.