DEDUPED Hot AI repos, turned into use cases Get the Monday 5

How to tune a strategy with hyperopt and FreqAI with Freqtrade

Search strategy parameters with machine learning, or build a self-training model with FreqAI.

Short answer: Run hyperopt on your strategy and list results with hyperopt-list; then Inspect a result with hyperopt-show and see loss functions with list-hyperoptloss; See available models with list-freqaimodels and read the FreqAI docs. All steps.

  • Money
  • Advanced
  • 2 hours
  • From the README
  • Any agent

Who it is forA quant hobbyist who wants to tune parameters or try adaptive machine learning models.

The problemHand tuning parameters is slow and easy to overfit.

The outcomeOptimised parameter sets ranked by a loss function, or a FreqAI model that retrains on the market.

What you need first

  • Python 3.12 or newer, pip, git and TA-Lib, or Docker
  • An accurate system clock synced to NTP
  • About 2GB RAM, 1GB disk and 2 vCPU recommended
  • Exchange API keys only when you move past dry-run

Steps

  1. Run hyperopt on your strategy and list results with hyperopt-list
  2. Inspect a result with hyperopt-show and see loss functions with list-hyperoptloss
  3. See available models with list-freqaimodels and read the FreqAI docs
  4. Check formulas with recursive-analysis and re-run lookahead-analysis before trusting results

Prompt for your agent

With freqtrade/freqtrade, run hyperopt on <strategy> over <period>, show the best three parameter sets, then backtest the best one on a later out of sample period and compare.

Caveat. Optimised parameters often overfit the past, so always validate on unseen data and in dry-run. Not financial advice: paper trade first, and remember you can lose money.

Use this in your AI agent

Ask your agent

Using the Deduped MCP, get the setup steps for freqtrade/freqtrade and "Tune a strategy with hyperopt and FreqAI"

Add Deduped to Claude Code once

claude mcp add --transport http deduped https://dedupedai.com/mcp

Cursor, ChatGPT, others

Share: X LinkedIn Hacker News Email Copy link

Third-party repos we don't own. AI-written use cases can be wrong. Disclaimer