chickenbestlover/RNN-Time-series-Anomaly-Detection

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

1305 stars · 310 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

A PyTorch implementation of an RNN-based time-series anomaly detector using a two-stage strategy of multi-step prediction followed by anomaly score calculation. It includes datasets such as NYC taxi, ECG, and gesture data for evaluation.

Use cases

• detect anomalies in time-series data
• forecast future values of a time series with an RNN
• reproduce time-series anomaly detection research
• run anomaly detection on NYC taxi or ECG datasets
• train a PyTorch model for streaming data outlier detection

When to choose

• you need a research-grade RNN anomaly detection baseline in PyTorch
• you work with univariate time-series like sensor streams or ECG signals
• you want a two-stage predict-then-score anomaly detection pipeline

When to avoid

• you need production support on Windows (errors reported)
• you need actively maintained code or recent PyTorch compatibility
• you need multivariate or transformer-based anomaly detection

Facets

library · maturity maintenance

machine-learning deep-learning nlp machine-learning time-series data-science python rnn anomaly-detection time-series pytorch forecasting linux gpu

Member repositories

For agents

markdown · JSON · MCP: product_card(name="chickenbestlover/RNN-Time-series-Anomaly-Detection")