Layer IV · Research

Research that survives its own scrutiny.

Most retail research fails quietly: a look-ahead bias nobody caught, thirty trades mistaken for evidence, a curve fitted to one regime. The research layer is built to argue with you. An idea is restated as rules precise enough for software, run in your own Python on your own machine, and reported with its assumptions beside its results.

Talk to Blackshore Agency

What it holds

Ideas restated as testable rules, run in Python on your machine, every assumption on the record.

01Data in, aligned

Fetch one symbol or many and align them on a common index, cached on disk so an iteration loop is not also a download loop. The bundled source is Yahoo Finance history, and we say so plainly. Anything else, a vendor, an exchange or your own database, is connected through the connectivity layer.

02Signals checked before they are trusted

The usual indicators, RSI, moving averages, ATR, MACD and Bollinger bands, with signal preparation that handles the shifting and alignment where look-ahead bias creeps in. Diagnostics run over your signals before the backtest does, so the obvious mistakes surface first.

03Backtests, grids and honest verdicts

Run a single backtest or a parameter grid and watch results arrive as they complete. The research agent will not call a strategy tradeable on thin evidence: numbers that did not come from a real run are labelled illustrative, and fewer than about thirty trades proves nothing.

04Results you can set side by side

Charts, trade tables, statistics and written reports render on the Canvas beside the conversation that produced them, and stay there to be compared with the next run: in sample against out, this parameter set against that one. Any of it prints to PDF.

Research agent · Backtests & sweeps · Out-of-sample checks · Canvas reports

Due diligence

Questions asked first.

Which market data is included?

Yahoo Finance history, cached locally. No institutional feed is bundled, and none is implied. The source you actually want is connected like any other API, with your credentials on your machine.

Can I use my own Python libraries?

Yes. Research runs in the Python 3 already on your machine. QuantIDE has never shipped an interpreter of its own, so your environment, packages and versions are the ones that run.

Does a good backtest mean the strategy works?

No, and nothing here will tell you otherwise. A backtest is evidence about the past under stated assumptions. The layer is designed to make those assumptions visible and the weak results obvious, not to make a strategy look tradeable.

Your infrastructure. Your keys. Our engineers on call.