An experiment in what an agentic-AI research framework can do — published in full so you can check its work, not a tip service to follow. Generic research and education, not advice, not a personal recommendation, not FCA-authorised. Hypothetical book, not real money. Capital at risk.
Portfolio Lab · Research Lab
Portfolio Lab — transparent, low-cost portfolios with real out-of-sample performance, net of all costs. View the portfolios →

← All concepts

Signals are overlays, not bets

Most of the signals people get excited about — insiders buying, a buyback announced, short interest spiking — are real but short-lived. They nudge returns for a few weeks, then fade. That makes them genuinely useful, but useful in a specific way: they're good at telling you when to act and how hard, and bad at being the reason to own something for a year. We treat them accordingly.

What it is

We split the things we know about a company into two kinds. Durable strands — business quality, valuation, capital allocation, management credibility — are the reasons to own it at all; they're what the multi-month hold actually rests on. Conviction and timing signals — insider clusters, a buyback kicking in, a sentiment extreme — are overlays: they sharpen the entry and inform the size, but they don't carry the position by themselves.

Why it matters

The evidence keeps saying the same thing. Take our own insider-cluster study: measured properly, clusters of insiders buying earn a real ~1-month abnormal return and a modest 3-month one — then nothing. As a standalone "buy and hold for a year" rule it does little. As an overlay on a name we already wanted to own for durable reasons, it's exactly what it should be: a well-timed, higher-conviction entry. Treating a 1-month signal as a 12-month thesis is how people lose money with a statistic that was actually true.

How we use it

The honest caveat

"Overlay" is not a licence to use weak signals freely. An overlay still has to have earned its place with evidence — it's just being asked to do a smaller, honest job. A pile of fading signals is not a thesis; it's a reason to look more carefully at the durable strands underneath.

A plain-English explainer of how we think — part of our evidence-driven framework. Not investment advice.