{"enrichment":{"faq":[{"a":"feature-engineering transforms raw market data into stationary, predictive features for crypto trading models. Start by computing technical indicators (RSI, MACD, Bollinger Bands) from OHLCV data, then layer volume and on-chain metrics like whale flows. Ensure all features are stationary\u2014differencing or log-returns eliminate trends that cause lookahead bias. Normalize across your training window to prevent data leakage. Feature quality matters more than model complexity in trading ML.","q":"How do I build features for crypto trading models?"},{"a":"feature-engineering emphasizes selecting stationary, non-redundant features that capture price dynamics without lookahead bias. Prioritize technical indicators (momentum, acceleration), volume divergence signals, and microstructure features from DEX trading. On-chain features like token whale flows add predictive power. Use correlation filtering to remove redundancy, then rank by importance. Rolling statistics computed over fixed lookback windows prevent future data leakage into training.","q":"What are the best features for trading ML models?"},{"a":"feature-engineering prevents lookahead bias by computing all features within a fixed historical window\u2014never using future data. Use rolling statistics with explicit lookback periods; avoid forward-filling or centering operations on price data. Normalize features per training batch, not globally. For label creation in binary classification trading, ensure labels are defined only from data available at prediction time. Stationarity checks confirm no hidden future dependence.","q":"How do I avoid lookahead bias in feature engineering?"},{"a":"feature-engineering covers on-chain features including whale flow tracking, transaction volume patterns, and holder concentration metrics for token trading. These microstructure signals reveal market intent before price moves. Combine with technical indicators and volume divergence to build robust feature sets. Ensure on-chain data is stationary (use differencing or log-returns) and synchronized with OHLCV timestamps to avoid temporal misalignment.","q":"What on-chain features help with token price prediction?"},{"a":"feature-engineering normalizes features per training batch to prevent data leakage\u2014compute mean and std from training data only, then apply to validation/test sets. Use rolling statistics with fixed lookback windows rather than global aggregates. For price and volume features, log-returns or differencing ensure stationarity before normalization. This approach preserves temporal structure while eliminating scale artifacts that confuse ML models.","q":"How do I normalize features for trading model training?"},{"a":"feature-engineering selects features by first ensuring stationarity through differencing, log-returns, or detrending. Then apply correlation filtering to remove redundant features that duplicate information. Rank survivors by importance using model-agnostic methods. Focus on technical indicators, volume signals, and on-chain metrics that capture distinct market regimes. Non-redundant feature sets train faster and generalize better than bloated feature matrices.","q":"How do I select stationary, non-redundant features?"}],"shadow_tags":["signal-construction","market-microstructure","blockchain-analytics","predictive-modeling","data-transformation","time-series-stationarity","feature-selection","backtesting-preparation","regime-adaptation"],"summary_rewrite":"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."},"files":[{"bytes":10728,"path":"skills/feature-engineering/SKILL.md","sha256":"09dcfb6896273e46f0b3de40e554449c017e900d9fa19d8bb845c8cee42012ec","url":"https://skillfed.io/files/agiprolabs/claude-trading-skills/feature-engineering/d11d5f92/SKILL.md"}],"id":"agiprolabs/claude-trading-skills/feature-engineering","links":{"html":"https://skillfed.io/agiprolabs/claude-trading-skills/feature-engineering","md":"https://skillfed.io/agiprolabs/claude-trading-skills/feature-engineering.md","repo":"https://github.com/agiprolabs/claude-trading-skills"},"meta":{"agents_supported":[],"first_seen":"2026-07-28","forks":52,"language":"Python","last_updated":"2026-06-24","license":"MIT","name":"feature-engineering","publisher":"agiprolabs","stars":248},"relations":{"similar":[{"id":"agiprolabs/claude-trading-skills/mean-reversion"},{"id":"agiprolabs/claude-trading-skills/cointegration-analysis"},{"id":"agiprolabs/claude-trading-skills/regime-detection"},{"id":"HKUDS/Vibe-Trading/quant-statistics"},{"id":"HKUDS/Vibe-Trading/correlation-analysis"},{"id":"organvm/a-i--skills/time-series-analyst"},{"id":"agiprolabs/claude-trading-skills/pandas-ta"},{"id":"aj-geddes/useful-ai-prompts/time-series-analysis"},{"id":"HKUDS/Vibe-Trading/ml-strategy"},{"id":"agiprolabs/claude-trading-skills/walk-forward-validation"}]},"slug":{"owner":"agiprolabs","repo":"claude-trading-skills","skill":"feature-engineering"},"version":"d11d5f92"}