# How Far Should We Look Back to Achieve Effective Real-Time Time-Series Anomaly Detection?

arXiv: https://arxiv.org/abs/2102.06560 · HTML: https://mlsanity.com/paper/2102.06560/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 14 references that are in the map.
- First posted on arXiv 12 Feb 2021.

## Builds on (most cited first, 10 of 10)

- [Unsupervised Anomaly Detection via Variational Auto-Encoder for Seasonal KPIs in Web Applications](https://mlsanity.com/paper/1802.03903/) (2018)
- [Time-Series Anomaly Detection Service at Microsoft](https://mlsanity.com/paper/1906.03821/) (2019)
- [Evaluating Real-time Anomaly Detection Algorithms - the Numenta Anomaly Benchmark](https://mlsanity.com/paper/1510.03336/) (2015)
- [Collective Anomaly Detection based on Long Short Term Memory Recurrent Neural Network](https://mlsanity.com/paper/1703.09752/) (2017)
- [Automatic Anomaly Detection in the Cloud Via Statistical Learning](https://mlsanity.com/paper/1704.07706/) (2017)
- [RePAD: Real-time Proactive Anomaly Detection for Time Series](https://mlsanity.com/paper/2001.08922/) (2020)
- [ReRe: A Lightweight Real-time Ready-to-Go Anomaly Detection Approach for Time Series](https://mlsanity.com/paper/2004.02319/) (2020)
- [Intrusion Detection using Continuous Time Bayesian Networks](https://mlsanity.com/paper/1401.3851/) (2014)
- [Hybrid Job-driven Scheduling for Virtual MapReduce Clusters](https://mlsanity.com/paper/1808.08040/) (2018)
- [Performance evaluation of job schedulers on Hadoop YARN](https://mlsanity.com/paper/1808.08289/) (2018)

## Built on by (most cited first, 8 of 8)

- [SALAD: Self-Adaptive Lightweight Anomaly Detection for Real-time Recurrent Time Series](https://mlsanity.com/paper/2104.09968/) (2021)
- [RePAD2: Real-Time, Lightweight, and Adaptive Anomaly Detection for Open-Ended Time Series](https://mlsanity.com/paper/2303.00409/) (2023)
- [RoLA: A Real-Time Online Lightweight Anomaly Detection System for Multivariate Time Series](https://mlsanity.com/paper/2305.16509/) (2023)
- [NP-Free: A Real-Time Normalization-free and Parameter-tuning-free Representation Approach for Open-ended Time Series](https://mlsanity.com/paper/2304.06168/) (2023)
- [Impact of Deep Learning Libraries on Online Adaptive Lightweight Time Series Anomaly Detection](https://mlsanity.com/paper/2305.00595/) (2023)
- [Impact of Recurrent Neural Networks and Deep Learning Frameworks on Real-time Lightweight Time Series Anomaly Detection](https://mlsanity.com/paper/2407.18439/) (2024)
- [Adapt Data to Model: Adaptive Transformation Optimization for Domain-shared Time Series Foundation Models](https://mlsanity.com/paper/2603.00629/) (2026)
- [Evaluation of k-means time series clustering based on z-normalization and NP-Free](https://mlsanity.com/paper/2401.15773/) (2024)

## Abstract (arXiv)

Anomaly detection is the process of identifying unexpected events or ab-normalities in data, and it has been applied in many different areas such as system monitoring, fraud detection, healthcare, intrusion detection, etc. Providing real-time, lightweight, and proactive anomaly detection for time series with neither human intervention nor domain knowledge could be highly valuable since it reduces human effort and enables appropriate countermeasures to be undertaken before a disastrous event occurs. To our knowledge, RePAD (Real-time Proactive Anomaly Detection algorithm) is a generic approach with all above-mentioned features. To achieve real-time and lightweight detection, RePAD utilizes Long Short-Term Memory (LSTM) to detect whether or not each upcoming data point is anomalous based on short-term historical data points. However, it is unclear that how different amounts of historical data points affect the performance of RePAD. Therefore, in this paper, we investigate the impact of different amounts of historical data on RePAD by introducing a set of performance metrics that cover novel detection accuracy measures, time efficiency, readiness, and resource consumption, etc. Empirical experiments based on real-world time series datasets are conducted to evaluate RePAD in different scenarios, and the experimental results are presented and discussed.