Anomaly detection in multivariate time series is an important problem across various fields such as healthcare, financial services, manufacturing or physics detector monitoring.
Accurately identifying the moments when unexpected errors or defects occur is essential for these applications. This can be challenging as the types of anomalies are unknown beforehand. Additionally, the multi-dimensional nature of time series data adds to the problem’s complexity, as the correlations between different dimensions must be considered.
This presentation will introduce the problem of time series anomaly detection and present how to tackle these problems with machine learning for applications in data quality monitoring in particle physics.
