Three reads before you trust an optimizer.
01
The noisiest input gets the most power. Return forecasts carry error bars of plus minus 6 points. The optimizer treats them as facts and leans the whole book on the difference between 12 and 11. That is not optimization. It is error, amplified.
02
Out of sample is the only sample that pays. 14 models tested against plain equal weight. None won consistently. The math needs roughly 250 years of clean data to earn its keep on 25 assets. Nobody has 250 years.
03
Equal weight is not naive. It is humble. It makes zero return forecasts, so it makes zero forecast errors. The work is done by the discipline of rebalancing back to equal. Selling what ran. Buying what lagged. On a calendar, not a feeling.
An optimizer answers to two decimal places a question nobody can answer to ten. Equal weight skips the question. That is the edge.