This question matters more than most traders realise, because the answer cuts against decades of quant orthodoxy. Kelly Criterion is elegant mathematics — it promises geometrically optimal growth given known probabilities and payoffs. The problem? Small-cap ASX stocks laugh at "known probabilities." Their return distributions have tails so fat they'd need their own postcode.

The direct answer is this: when your input estimates are noisy — and on ASX small-caps they always are — Kelly's precision becomes a liability. Garbage in, geometric ruin out. Equal-weight sizing is dumber in theory but more robust in practice, because it makes almost no assumptions about the future. It's the difference between a finely tuned sports car and a Land Cruiser. One is faster on smooth roads; the other gets you home when the road disappears.

CONCEPTEqual-weight sizing thrives precisely because it stops pretending you know more than you do about small-cap return distributions.
WARNINGFull Kelly on fat-tailed assets can wipe out a portfolio far faster than any single bad trade — miscalibrated edge estimates are catastrophic.
KEY IDEAEstimation error in Kelly inputs scales non-linearly — small mistakes in win-rate estimates produce enormous swings in recommended position size.

Here's the mechanics. Kelly requires you to estimate your edge — the probability of winning and the win/loss ratio. On liquid large-caps with thick datasets, that's hard enough. On ASX small-caps — where a single quarterly cashflow report, a CEO resignation, or a speculative drilling result can gap a stock 40% overnight — your edge estimate has the statistical confidence of a pub prediction. Fat tails mean extreme events happen far more often than a normal distribution predicts, and Kelly simply wasn't designed for that environment.

Simulated Max Drawdown: Equal-Weight vs Full Kelly 80% 60% 40% 20% 0% ~20% Equal-Weight ~68% Full Kelly Max Drawdown Illustrative simulation — fat-tailed universe

What actually happens in practice is that Full Kelly over-concentrates into positions where your estimated edge is highest — exactly the positions where estimation error is also highest on illiquid small-caps. Fractional Kelly (betting half or quarter Kelly) helps, but even then you're trusting noisy inputs. Equal-weight sidesteps the whole problem by distributing capital evenly, letting the law of large numbers do the heavy lifting. For deeper reading on the mathematics, Investopedia's Kelly Criterion explainer covers the formula in detail, while the statistical theory behind fat tails is well documented on Wikipedia's fat-tailed distribution page. The broader framework for why robust sizing often beats optimal sizing under uncertainty is captured in research on position sizing theory.

The practical takeaway: if your universe is ASX small-caps, start with equal-weight, run it for a statistically meaningful sample, then only consider Kelly variants once you have genuine confidence in your edge estimates. Complexity earns its seat at the table — it doesn't just show up and demand one.

This content is for educational purposes only and does not constitute financial product advice. Past performance is not indicative of future results. Profit Logic Ltd (ACN 688 669 936) accepts no responsibility for errors or omissions in this content or anywhere on this website. Always seek advice from a licensed financial adviser before making investment decisions.