AIOps_docs.md

github重要的：

• AIOps白皮书：https://www.rizhiyi.com/assets/docs/AIOps.pdf
• AIOps手册：https://github.com/chenryn/aiops-handbook
• awesome-AIOps: https://github.com/linjinjin123/awesome-AIOps
• Anomaly Detection Learning Resources https://github.com/yzhao062/anomaly-detection-resources
• awesome-TS-anomaly-detection https://github.com/rob-med/awesome-TS-anomaly-detection

知乎/博客：

• 深度好文：腾讯运维的 AI 实践
• 腾讯云智能运维(AIOps)项目实践
• 时间序列异常检测——学习笔记
• 机器学习之：异常检测
• 基于时间序列的异常检测算法小结
• 时间序列异常检测算法
• 异常检测的N种方法，阿里工程师都盘出来了
• 时间序列异常检测算法S-H-ESD
• 基于时间序列的单指标异常检测_雅虎流量数据

ppt类：

• 异常检测在苏宁的实践
• ClickHouse在新浪的最佳实践
• AS深圳2018 《织云Metis时间序列异常检测全方位解析》

代码类：

• keras-anomaly-detection
• Keras的LSTM多变量时间序列预测
• 基于机器学习算法的时间序列价格异常检测（附代码）

benchmark datasets:

• Numenta's NAB

NAB is a novel benchmark for evaluating algorithms for anomaly detection in streaming, real-time applications. It is comprised of over 50 labeled real-world and artificial timeseries data files plus a novel scoring mechanism designed for real-time applications.

• Yahoo's Webscope S5

The dataset consists of real and synthetic time-series with tagged anomaly points. The dataset tests the detection accuracy of various anomaly-types including outliers and change-points.