---
name: run-a-feature-engineering-research-loop-over
description: "Propose, test and log candidate predictive features on a fixed schedule. A research bot keeps a disciplined experiment loop over historical market data: it drafts candidate predictive features, scores each on an in-sample window with an existing backtest script, records the definition and reasoning, and retires ideas that fail."
license: CC-BY-4.0
compatibility: "Needs access to: PostgreSQL, Terminal, Google Sheets, Notes."
metadata:
  author: "BotBento Editorial"
  version: "2026-11-13"
  source: "https://botbento.com/usecases/run-a-feature-engineering-research-loop-over/"
  kind: workflow
  hermes:
    tags: ["quant-research", "feature-engineering", "backtesting", "experiment-tracking", "machine-learning"]
    category: research
---
# Run a feature-engineering research loop over market data

Propose, test and log candidate predictive features on a fixed schedule

## When to use

A research bot keeps a disciplined experiment loop over historical market data: it drafts candidate predictive features, scores each on an in-sample window with an existing backtest script, records the definition and reasoning, and retires ideas that fail. Each run closes with a short ranked list of surviving candidates and open questions to carry into the next round.

## Steps

1. On a schedule: weekday research run
2. Draft and score candidate features
3. Ranked feature log with open questions

## Instructions

You are a research loop bot working against a fixed historical dataset. On each scheduled run, read the feature log, propose three to five new candidate features built only from columns known at decision time, and express each as a query or script. Run the existing backtest script on an in-sample window for every candidate, then append its score, exact definition and one line of reasoning to the log. Never execute trades or place orders; draft any trade idea for human review. Do not delete or overwrite earlier log entries, and ask before emailing results to anyone.

## Source

Summarized in our own words from [Launch HN: EdotEnv (YC S26) – Quant Trading RL Envs to Teach LLMs Research](https://news.ycombinator.com/item?id=49172936) (Hacker News, checked 2026-11-13). Any results described there are the authors’ own.

From the BotBento use-case directory: https://botbento.com/usecases/run-a-feature-engineering-research-loop-over/. Licence: [CC BY 4.0](https://creativecommons.org/licenses/by/4.0/).
