Generate machine-learning trading signals from OHLCV data with walk-forward training.
npx skills add https://github.com/HKUDS/Vibe-Trading --skill ml-strategy
Please help me install this Agent Skill. Skill: ml-strategy Source: https://github.com/HKUDS/Vibe-Trading/tree/main/agent/src/skills/ml-strategy Command: npx skills add https://github.com/HKUDS/Vibe-Trading --skill ml-strategy
ML strategies on trading data often suffer from data leakage, inf-laden features, and unbounded predictions, so this Skill validates OHLCV inputs, sanitizes every feature, and keeps outputs clipped while relying solely on historical windows for training.
Run the ml-strategy on recent OHLCV data to receive normalized buy and sell signals with walk-forward ML.
High-intent search queries and answers about installing and using this skill.
Generate machine-learning trading signals by feeding daily OHLCV time series into a walk-forward training loop that predicts five-day directional returns and outputs clipped [-1.0, 1.0] confidence values. Models include RandomForest, GradientBoosting, or Ridge.
Walk-forward training prevents data leakage by relying solely on expanding or sliding historical windows to retrain models at configurable intervals. This ensures predictions for future periods only use past data, keeping feature engineering and model fitting strictly chronological.
Yes, you can use sklearn models like RandomForest, GradientBoosting, or Ridge classifiers to predict five-day directional returns. The workflow normalizes model probabilities into a [-1.0, 1.0] confidence range to ensure bounded trading signals.
Inf values often result from division-by-zero in momentum, volatility, or RSI ratio features. Sanitize these features by validating OHLCV columns and scrubbing inf values before modeling to ensure clean inputs for the training pipeline.
Handle unbounded predictions by clipping model outputs to a strict [-1.0, 1.0] confidence range without NaN values. This normalization allows systematic rebalancing engines to directly consume probability-based signals as position sizing weights.
Yes, ml-strategy works with any symbol's OHLCV feed by validating the input columns and applying sanitized feature engineering. You can apply this workflow across your entire universe of daily time series to generate independent trading signals.
DaddyElonMusk69Generate directional trading signals from OHLCV data using walk-forward machine-learning training.
loanntcGenerates trading direction signals from OHLCV time series using scikit-learn models with walk-forward training.
wudyeGenerate machine-learning trading signals from OHLCV time series with walk-forward training.
OpenSuckerApply machine learning models to OHLCV data for market prediction and signal generation.
