Quantitative Research

A diversified portfolio, backtested

The trade journal stakes a fixed $200 on every signal, one at a time — most of a $100,000 bankroll sits in cash. This section tests the actual fix: instead of a token stake, the bankroll is split evenly across every buy signal open on a given day (about two, on average) and redeployed the same way the next day. No leverage, no compounding of the running balance — each day risks a fixed share of the original bankroll, exactly like the fixed-stake journal, just spread across more names at once.

Diversified portfolio SPY buy-and-hold QQQ buy-and-hold
Diversification, not a bigger edge, is what was missing. Nothing about the underlying trade changed — same signals, same window, same frictions. Fully deploying the bankroll across every simultaneous signal, instead of parking most of it in cash behind a token stake, is what turns a statistically real but economically thin per-trade edge into a return that competes with a buy-and-hold benchmark over the same period. This does not erase the caveats above — real transaction costs, capacity limits in illiquid names, and no sector or size controls still apply at this scale — but it shows the earlier "too small to matter" conclusion was about position sizing, not about the signal itself.
The entry price of the D window is not always reachable. Window D assumes you buy at the close of the filing day. But only 33% of purchase filings are accepted by EDGAR during market hours (9:30–16:00 ET): for the remaining 67% that close had already printed before the filing was public, so nobody could have bought there. Measured against real intraday execution prices (1-minute bars at the second of acceptance, exiting on a matching series from the same provider), the reachable entry costs about 0.08 percentage points per trade — around 6% of the portfolio result with no quality filter, and up to a quarter of it with one. The effect survives real execution prices in every configuration tested. An earlier version of this note put that cost near half the edge and said the effect did not survive without a filter; that came from measuring entry and exit on two different price sources with different dividend-adjustment conventions, and it does not hold once both legs come from the same one.