DEV Community

Quantooox
Quantooox

Posted on

Why our paper portfolios race a random portfolio

Our live paper portfolios trade once a week on the scores published before the market opens. Alongside the index, each one is compared with a random long-short portfolio: same number of stocks, same rebalancing, same costs, but the stocks are picked at random.

Why not just compare with the index?

A long-short portfolio owns the top-ranked stocks and bets against the bottom-ranked ones, so it is roughly market-neutral. Comparing it with the S&P 500 mixes two things: whether the ranking helped, and what the market did. In a falling market almost any market-neutral book "beats the index".

What the random portfolio isolates

Same construction, no information. If the scored portfolio and the random one end up in similar places, the scores added nothing beyond the mechanics of holding many stocks long and short. Over a few weeks they often trade places, which is exactly the point: short periods are noise.

How long until it means something?

With weekly rebalancing and typical stock volatility, separating a real ranking from luck takes years, not weeks. Our research already tells us what to expect: the score showed no reliable ranking ability in testing. The live portfolios exist to show that honestly, in public, every day.

All portfolios are hypothetical: no real money, not a claim of performance. The diary on the blog explains each day's moves in plain words.


From Quantooo Lab, the makers of quantooo.com, a free, open and educational quant lab: every formula, every test and every failure is public. See it here: https://quantooo.com/portfolios

Educational, not investment advice.

Top comments (0)