Skip to main content

Are you tired of reactive maintenance? Do you want to learn how to predict equipment failures before they happen? Detect abnormal patterns in your time series? Join our hands-on workshop on predictive maintenance and anomaly detection using Darts – the open source library for time series forecasting and anomaly detection (Python). In this workshop, you will learn how to use time series data to predict equipment failures and detect anomalies. First, we cover the basics of time series forecasting, from data preprocessing & feature engineering to model selection. Then, we move to two real-world use cases from the healthcare and industrial sectors. By the end, you will have a good understanding of how to perform both time series forecasting and anomaly detection for predictive maintenance and other applications. This workshop is suitable for data scientists, machine learning engineers, and anyone interested in time series analysis. Basic knowledge of Python is recommended.


  • Demonstrate the opportunities offered by anomaly detection in various industries
  • Expand knowledge of the latest modeling techniques in time series forecasting and anomaly detection.


09:00 – 10:00 Introduction to Darts
Time series forecasting and anomaly detection (data structure, forecasting model training / prediction / evaluation, anomaly detection)
10:00 – 10:30 Simple anomaly detection
example on healthcare data (ECG)
10:30 – 11:00 Break
11:00 – 12:20 Advanced example of predictive maintenance
12:20 – 12:30 Summary, take-away message