ml-strategy
ML-Strategy generates trading signals by applying sklearn classifiers (RandomForest, GradientBoosting, Ridge) to engineered OHLCV features with walk-forward validation to prevent data leakage. The skill extracts momentum, volatility, and technical indicators, trains models incrementally, and outputs clean directional signals in the [-1.0, 1.0] range.
ML-Strategy generates trading signals by training sklearn models on engineered OHLCV features with walk-forward validation.
AI-generated summary based on this skill's SKILL.md
Decision gist · record as of 2026-07-27
ML-Strategy generates trading signals by training sklearn models on engineered OHLCV features with walk-forward validation. ML-Strategy generates trading signals by applying sklearn classifiers (RandomForest, GradientBoosting, Ridge) to engineered OHLCV features with walk-forward validation to prevent data leakage. The skill extracts momentum, volatility, and technical indicators, trains models incrementally, and outputs clean directional signals in the [-1.0, 1.0] range.
Use it when
- ml-strategy implements walk-forward training to avoid future data leakage—a critical flaw in backtesting where models train on data they.
- ml-strategy builds custom feature engineering for price direction prediction using momentum indicators, volatility measures.
Verify before relying
Read SKILL.md below before installing (1 file). Open directory: indexed for reading, not audited.
Install
HKUDS/Vibe-Trading/ml-strategy · repository language: Python
Open directory. Skills are indexed for reading, not audited. Review a skill's body before installing it.
Frequently asked questions
AI-generated answers based on this skill's SKILL.md and metadata
How does ml-strategy generate trading signals using machine learning models?
ml-strategy generates trading signals by applying sklearn classifiers—RandomForest, GradientBoosting, and Ridge—to engineered OHLCV features. The skill extracts momentum, volatility, and technical indicators from price data, trains models on historical windows, and outputs directional signals in the [-1.0, 1.0] range for buy/sell decisions.
What is walk-forward validation and why does ml-strategy use it?
ml-strategy implements walk-forward training to avoid future data leakage—a critical flaw in backtesting where models train on data they later predict. The skill retrains models incrementally on rolling windows, ensuring each prediction uses only historical information available at that point in time.
Which features does ml-strategy engineer for price direction prediction?
ml-strategy builds custom feature engineering for price direction prediction using momentum indicators, volatility measures, and technical signals like RSI and Bollinger Bands extracted from OHLCV data. These engineered features feed into the classifier pipeline to improve signal quality.
How do RandomForest, GradientBoosting, and Ridge models compare in ml-strategy?
ml-strategy lets you compare three ensemble and regression approaches: RandomForest captures non-linear patterns through multiple decision trees, GradientBoosting iteratively improves predictions by correcting errors, and Ridge regression provides a simpler linear baseline. Each model trades complexity for interpretability differently.
How does ml-strategy handle OHLCV data quality and prevent overfitting?
ml-strategy validates and handles OHLCV data quality issues within its ML pipeline and prevents overfitting through walk-forward validation—retraining on expanding historical windows rather than static train-test splits. This rolling approach ensures models adapt to market regime changes without memorizing future patterns.
Is ml-strategy open source and what license does it use?
Yes, ml-strategy is released under the MIT license, making it free to use, modify, and distribute in both open-source and commercial projects with minimal restrictions.
SKILL.md
Rendered from the published skill. Quoted content, verbatim.
Machine-Learning Predictive Strategy
Purpose
Use sklearn machine-learning models (RandomForest / GradientBoosting / Ridge) to predict the direction of future returns and generate trading signals. Walk-forward training is used to avoid future data leakage, and feature engineering extracts useful factors from OHLCV data.
Signal Logic
- Validate input: check OHLCV columns, minimum row count, NaN ratio — skip symbols that fail
- Feature engineering: build multi-dimensional factors from raw OHLCV data (momentum, volatility, RSI, moving-average ratios, volume ratio, and more). All features are sanitized (inf removed, division-by-zero guarded)
- Label construction: future N-day return > 0 is the positive class (
1), < 0 is the negative class (0) - Walk-forward training: use an expanding or sliding window, train on historical data only, and roll forward day by day for prediction
- Signal generation: map
predict_proba[:, 1]to `[-1.0,
(truncated - see the full file via the links below)
File tree — 1 file
agent/src/skills/ml-strategy/SKILL.md
Let your AI agent find skills like this
Example. Real query, live index.
You found this page by searching. An agent finds it by wishing: SkillFed indexes 56,283 agent skills by what they can do, searchable in plain language.
wish › “Generate trading signals using machine learning models on OHLCV data”
Give your agent the search over MCP, or paste the wish link into any chat. No install? Search from any chat →
Related skills
Transform raw market data into stationary, predictive features for crypto trading models. This skill covers price, volume, technical, microstructure, and on-chain feature construction with emphasis on avoiding lookahead bias and ensuring stationarity. Feature quality matters more than model complexity in trading ML.
Crypto Backtest transforms natural language trading ideas into validated strategies with professional backtesting and detailed reports. It combines multiple indicators—RSI, moving averages, Bollinger Bands, and more—to build robust entry and exit conditions for spot trading only. Users describe their strategy, confirm the generated plan, and receive comprehensive backtest results.
Build production ML pipelines that handle data ingestion, model training, and deployment with Airflow DAGs, Kubeflow containers, and MLflow experiment tracking. This skill covers orchestration patterns, scheduling retraining jobs, managing model versions, and troubleshooting common workflow failures.
Build volatility forecasts using GARCH(1,1) and GJR(1,1) models with walk-forward fitting, then apply them to scale positions inversely to risk. The toolkit includes tested recipes for univariate fits, DCC correlation overlays, and position-sizing logic on BTC, ETH, SOL, and AVAX futures data. Results are cost-dependent: GJR vol-scaling works at institutional rates (2bps) but erodes at retail spreads (7bps); DCC de-weighting adds minimal economic value.
Vectorbt Expert handles strategy backtesting across Indian equities, US stocks, and crypto markets using the vectorbt framework. It generates entry/exit signals via OpenAlgo's 100+ technical indicators, sizes positions intelligently, and produces detailed performance reports with benchmark comparisons.
ML Model Training guides you through building and optimizing machine learning models across three major frameworks. Learn data preparation, feature engineering, algorithm selection, and hyperparameter tuning with practical examples for classification, regression, and clustering.
More skills Scikit Learn Machine Learning (NOASSERTION)