Canonical: https://botbento.com/usecases/run-a-feature-engineering-research-loop-over/
Format: Markdown representation of the public HTML page.

# Run a feature-engineering research loop over market data

[Research](https://botbento.com/usecases/research/) · Advanced

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. Each run closes with a short ranked list of surviving candidates and open questions to carry into the next round.

## Quick answers

**What does it do?** Propose, test and log candidate predictive features on a fixed schedule. Result: Ranked feature log with open questions.

**What does it need?** Tools: PostgreSQL, Google Sheets, Terminal, Notes. Advanced: more tools and setup. The prompt includes an approval step.

**How do I run it?** On a schedule: weekday research run. Copy the prompt below into a bot in BotBento.

## How it works

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

## Prompt to start with

```text
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.
```

## Tools it uses

PostgreSQL, Terminal, Google Sheets, Notes

## Works with

BotBento

## Tags

quant-research, feature-engineering, backtesting, experiment-tracking, machine-learning

## Source

[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

Summarized in our own words. Any results described there are the authors’ own, not measured by BotBento.

Verified 2026-11-13: passed every automated gate and a second-model review (kimi-code/k3.1-pro). Automated, not human review. [How verification works](https://botbento.com/usecases/verification/)

By BotBento Editorial · Added 2026-11-13 · Updated 2026-11-13 · [Suggest a correction](https://botbento.com/contact/)

## Related use cases

- [Track ML training runs and log experiment results](https://botbento.com/usecases/autonomous-machine-learning-experiment-tracking-and-iteratio/) — Monitor training jobs, compare metrics to baselines, and note dead ends
- [Large language model research paper digest](https://botbento.com/usecases/large-language-model-research-paper-digest/) — Summarize technical AI preprints, benchmark architectures, and extract key implementation takeaways
- [Quantitative trading strategy backtester and researcher](https://botbento.com/usecases/quantitative-trading-strategy-backtester-and-researcher/) — Evaluate trading logic through automated backtests, parameter sweeps, and risk summaries
