Archived. IrrationalSignals is no longer a commercial product. This site is an engineering & product case study.
Build Case Study

An ML trading-signals product,
built end-to-end — then wound down.

An intraday statistical-signals service for US equities: data pipeline, model, API, billing, and brand. Here's the system, the decisions, and the call to wind it down.

What it was

Statistical models scanned hundreds of US equities every market hour and surfaced the ones with a measurable short-horizon edge. Each signal shipped with a direction, a win rate, and an entry/exit reference — delivered through a tiered, API-first SaaS with a Python SDK. The interesting part wasn't the signals; it was taking the whole thing — pipeline to billing — from zero to shipped, and being honest about where it worked and where it didn't.

What this build demonstrates

Data & ML

An honest model

A staged feature pipeline and a LightGBM ranker behind an AUC deploy gate — where every signal declared how trustworthy its own win rate was.

Product

Shipped, not prototyped

Tiering mapped to real cost and conviction, API keys, rate limits, billing, instrumentation wired to answer the question that mattered.

Judgement

Knowing when to stop

The engineering held; the edge and the business case didn't hold up. It was decommissioned deliberately rather than left to drift.

MRVL BUY
78%
Historical win rate — per_symbol
Entry
$87.45
Exit target
$88.52
Sector
Tech / Semis
Expected return
+1.23%

Illustrative example of the API's signal payload — not a live or current signal. The case study explains how the win rate and expected return were actually derived.

The full story

How the pipeline worked, how the win rate was computed, the product and pricing decisions, the honest limitations, and why the service was wound down.

Read the case study →

IrrationalSignals is archived and no longer operates as a live service. Nothing here is investment advice. Signals were statistical observations, not recommendations.