Open Access

ARTICLE

Long Short Term Memory Networks Based Anomaly Detection for KPIs

Haiqi Zhu¹, Fanzhi Meng^2,*, Seungmin Rho³, Mohan Li^4,*, Jianyu Wang¹, Shaohui Liu¹, Feng Jiang¹

1 School of Computer Science and Technology, Harbin Institute of Technology, Harbin, 150000, China.
2 Institute of Computer Application, China Academy of Engineer Physics, Mianyang, 621900, China.
3 Department of Software, Sejong University, Seoul, Korea.
4 Cyberspace Institute of Advanced Technology, Guangzhou University, Guangzhou, 510006, China.

*Corresponding Authors: Fanzhi Meng. Email: '" />; Mohan Li. Email: '" />

Computers, Materials & Continua 2019, 61(2), 829-847. https://doi.org/10.32604/cmc.2019.06115

Abstract

In real-world many internet-based service companies need to closely monitor large amounts of data in order to ensure stable operation of their business. However, anomaly detection for these data with various patterns and data quality has been a great challenge, especially without labels. In this paper, we adopt an anomaly detection algorithm based on Long Short-Term Memory (LSTM) Network in terms of reconstructing KPIs and predicting KPIs. They use the reconstruction error and prediction error respectively as the criteria for judging anomalies, and we test our method with real data from a company in the insurance industry and achieved good performance.

---

Keywords

---

Citations