skills.rest
philipcoller-777
philipcoller-777COMMUNITY
Explore all skills by this author →
GitHub

ml-strategy

Predict OHLCV return direction with walk-forward trained machine learning models.

Updated May 15, 2026
Search Tags:#finance#ml#predictive-models#walk-forward#signal-generation#ohclv
One-click install
npx skills add https://github.com/philipcoller-777/Vibe-Trading-TV2 --skill ml-strategy-philipcoller-777
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: ml-strategy
Source: https://github.com/philipcoller-777/Vibe-Trading-TV2/tree/main/agent/src/skills/ml-strategy
Command: npx skills add https://github.com/philipcoller-777/Vibe-Trading-TV2 --skill ml-strategy-philipcoller-777

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Machine-learning driven forecasting of OHLCV price movements to generate trading signals, reducing the need for manual model tuning and enabling data-driven decisions.

Core Features & Use Cases

  • Walk-forward training to avoid look-ahead bias and leakage in time-series data.
  • Feature engineering that builds momentum, volatility, RSI, and intraday factors from OHLCV data.
  • Flexible model selection among RandomForest, GradientBoosting, and Ridge to fit different data regimes.
  • End-to-end signal generation producing continuous [-1, 1] signals and discrete decisions.

Quick Start

Train the model on your OHLCV dataset and generate daily trading signals.

Frequently Asked Questions about ml-strategy

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I predict OHLCV return direction using machine learning without look-ahead bias?▼

You can predict OHLCV return direction using walk-forward training, which sequentially fits models on past data and evaluates them on subsequent periods to prevent look-ahead bias and data leakage.

What features do I need to generate machine learning trading signals from OHLCV data?▼

Generating machine learning trading signals from OHLCV data requires feature engineering to build momentum, volatility, RSI, and intraday factors, which are then used to train predictive models.

Which machine learning models are best for multi-symbol time-series forecasting?▼

For multi-symbol time-series forecasting, you can select among RandomForest, GradientBoosting, and Ridge models, allowing you to fit different data regimes and generate robust predictions.

Can I output continuous and discrete trading signals from predictive models?▼

Yes, predictive models can output both continuous trading signals scaled safely between [-1, 1] and discrete decisions through end-to-end signal generation from the trained time-series data.

Does walk-forward training require manual model tuning for different market regimes?▼

Walk-forward training reduces the need for manual model tuning by automatically fitting selected models across sequential time periods, enabling data-driven decisions that adapt to different market regimes.

Related Skills

Explore More Data & Analytics Skills→
wudyewudye

ml-strategy

Generate machine-learning trading signals from OHLCV time series with walk-forward training.

Community
Advanced
robonet-techrobonet-tech
1

improve-trading-strategies

Refine, optimize, and enhance trading strategies with Allora signals.

Official
Advanced
YFOOOOYFOOOO
1

technical-indicators

Compute MA, MACD, RSI, and BOLL indicators from OHLCV DataFrames with pandas and ta-lib.

Community
Advanced
brainbytes-devbrainbytes-dev
10

time-series-analysis

Model financial time series with ARIMA, GARCH, and cointegration tests.

Community
Advanced