# chickenbestlover/RNN-Time-series-Anomaly-Detection

RNN based Time-series Anomaly detector model implemented in Pytorch.

Repository: https://github.com/chickenbestlover/RNN-Time-series-Anomaly-Detection
Canonical: https://ross.abutalabs.com/products/rnn-time-series-anomaly-detection
Language: Python
License: Apache-2.0
License Family: permissive
Topics: rnn, neural-network, anomaly-detection, time-series, prediction, forecast
Last push: 2021-08-02T08:11:46+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 3086, "days_push": 1857, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1305, forks 310 (observed 2026-08-28T04:04:18.712444+00:00)

## What it is
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
- artifact type: library
- maturity: maintenance
- function: machine-learning, deep-learning, nlp
- domain: machine-learning, time-series, data-science
- platform: python
- tags: rnn, anomaly-detection, time-series, pytorch, forecasting, linux, gpu

## Member repositories
- chickenbestlover/RNN-Time-series-Anomaly-Detection (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:18.712444+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T04:51:01.610855+00:00, confidence not recorded.
  - readme: https://github.com/chickenbestlover/RNN-Time-series-Anomaly-Detection (fetched 2026-08-28T04:04:18.712444+00:00, sha 348444b0c52e)
- Data as of 2026-08-30T08:39:29.467469+00:00.