We like to imagine that small-cap investing is a battle of pure intellect. If you do the work, and are smart enough to piece it all together, success is all but guaranteed.
But this whole investing caper is a probabilistic affair, even for the most capable of investors. Being good isn’t about getting it right all the time, it’s about being right often enough such that the gains you make more than account for the losses.
I think the Kelly Criterion offers us a useful framework here. At least as a mental model that can help guide your thinking.
Like so much of probability theory, it was originally developed to determine optimal wager sizes in games of chance. Basically, the formula suggests that the amount of capital you risk should be directly proportional to your perceived odds and the potential payout.
Essentially, the better the odds, and the higher the gain relative to the loss, the bigger the bet. Its strength is in urging you to swing big on a fat pitch, keep it sensible when it’s not, and above all, keep you in the game.
Of course, despite its (fairly earned) reputation, the stock market is not a casino. The true odds are never known and certainly can’t be precisely calculated. But the underlying thrust of the idea can still be helpful.
To see how this works in practice, consider how a standard Kelly calculation operates under the hood. The core maths balances two primary inputs: your probability of winning versus losing, and your potential reward relative to your downside risk.
Suppose you spend weeks researching a niche industrial small-cap company. Based on your deep dive, you attempt to map out the potential outcomes and quantify three key numbers: your potential upside, your potential downside, and the odds that your thesis is actually correct.
You estimate that if your thesis plays out over the next three years, the stock doubles for a 100% gain. If you are wrong, you estimate the downside risk is a 50% loss. Finally, based on the strength of your research, you estimate there is a 60% chance that your thesis is correct, leaving a 40% chance that things go sideways.
To see what the model recommends, you plug those estimates into the Kelly formula, which I’ll show as:
Portfolio weighting = P − (1 − P) / B
Where P is your probability of success, and B is your win-loss ratio, calculated as your potential gain divided by your potential loss.
For our example, B is 1.0 / 0.5 = 2, which gives us an optimal weighting of 0.6 − (0.4 / 2) = 0.4, or 40%.
Before you spit your morning coffee all over your phone, let me quickly acknowledge that such a massive weighting is probably ill-advised. The maths might be solid, but your estimate of the key variables is anything but. If, for example, it turns out you really only had a 20% chance of being right, our mate Kelly would’ve actually suggested a negative position size! In other words, the trade had a negative expected value and you shouldn’t bet a cent on it, let alone 40%.
So for this to have any real-world value, you need to have done enough work to at least have a reasonable chance of estimating the key inputs. And even then, you need to add a big fat margin of safety.
That’s why proponents usually suggest a “Half-Kelly”, which is just the same formula, but halved (the name kind of gives it away). And let’s face it, for a high-conviction thesis where you estimate the odds are heavily in your favour, 20% is still a meaningful commitment. If you’re right, it’ll really move the needle for your overall portfolio. But crucially, it leaves 80% of your portfolio safe from any catastrophic miscalculation in your original estimates.
You can even take it a step further and just impose an upper bound by capping starting positions at 5% to 10% of your portfolio regardless of what the maths might suggest.
Again, the mistake to avoid here is one of false precision. This is just something that forces you to ask two honest questions before placing a trade. First, is your estimated upside large enough relative to your downside, and are the odds of being right high enough, to justify taking a position at all?
It’s a neat way to marry the ambition of finding multi-bagger small caps with the humility required to stay in the game for decades.
Strawman is Australia’s premier online investment club.
Members share research & recommendations on ASX-listed stocks by managing Virtual Portfolios and building Company Reports. By ranking content according to performance and community endorsement, Strawman provides accountable and peer-reviewed investment insights.
Disclaimer– Strawman is not a broker and you cannot purchase shares through the platform. All trades on Strawman use play money and are intended only as a tool to gain experience and have fun. No content on Strawman should be considered an inducement to buy or sell real world financial securities, and you should seek professional advice before making any investment decisions.
© 2026 Strawman Pty Ltd. All rights reserved.
