{"enrichment":{"faq":[{"a":"ml-strategy generates trading signals by applying sklearn classifiers\u2014RandomForest, GradientBoosting, and Ridge\u2014to 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.","q":"How does ml-strategy generate trading signals using machine learning models?"},{"a":"ml-strategy implements walk-forward training to avoid future data leakage\u2014a 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.","q":"What is walk-forward validation and why does ml-strategy use it?"},{"a":"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.","q":"Which features does ml-strategy engineer for price direction prediction?"},{"a":"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.","q":"How do RandomForest, GradientBoosting, and Ridge models compare in ml-strategy?"},{"a":"ml-strategy validates and handles OHLCV data quality issues within its ML pipeline and prevents overfitting through walk-forward validation\u2014retraining on expanding historical windows rather than static train-test splits. This rolling approach ensures models adapt to market regime changes without memorizing future patterns.","q":"How does ml-strategy handle OHLCV data quality and prevent overfitting?"},{"a":"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.","q":"Is ml-strategy open source and what license does it use?"}],"shadow_tags":["ensemble-learning","backtesting-framework","feature-extraction","time-series-prediction","risk-mitigation","algorithmic-trading","data-leakage-prevention","hyperparameter-tuning","signal-generation"],"summary_rewrite":"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."},"files":[{"bytes":11471,"path":"agent/src/skills/ml-strategy/SKILL.md","sha256":"5138bc8d762af44dabec751dfbada316b5b7cdbc29d751aad9fea793be617626","url":"https://skillfed.io/files/HKUDS/Vibe-Trading/ml-strategy/561d44c2/SKILL.md"}],"id":"HKUDS/Vibe-Trading/ml-strategy","links":{"html":"https://skillfed.io/HKUDS/Vibe-Trading/ml-strategy","md":"https://skillfed.io/HKUDS/Vibe-Trading/ml-strategy.md","repo":"https://github.com/HKUDS/Vibe-Trading"},"meta":{"agents_supported":[],"first_seen":"2026-07-28","forks":4557,"language":"Python","last_updated":"2026-07-27","license":"MIT","name":"ml-strategy","publisher":"HKUDS","stars":28096},"relations":{"similar":[{"id":"agiprolabs/claude-trading-skills/feature-engineering"},{"id":"agiprolabs/claude-trading-skills/walk-forward-validation"},{"id":"0xrikt/crypto-skills/crypto-backtest"},{"id":"secondsky/claude-skills/ml-pipeline-automation"},{"id":"agiprolabs/claude-trading-skills/signal-classification"},{"id":"datadrivenconstruction/DDC_Skills_for_AI_Agents_in_Construction/cost-prediction"},{"id":"agiprolabs/claude-trading-skills/vectorbt"},{"id":"PuckAPI/claude-sports-analytics/model-building"},{"id":"marketcalls/vectorbt-backtesting-skills/vectorbt-expert"},{"id":"agiprolabs/claude-trading-skills/ohlcv-processing"}]},"slug":{"owner":"HKUDS","repo":"Vibe-Trading","skill":"ml-strategy"},"version":"561d44c2"}