Book Image

Time Series Analysis on AWS

By : Michaël Hoarau
Book Image

Time Series Analysis on AWS

By: Michaël Hoarau

Overview of this book

Being a business analyst and data scientist, you have to use many algorithms and approaches to prepare, process, and build ML-based applications by leveraging time series data, but you face common problems, such as not knowing which algorithm to choose or how to combine and interpret them. Amazon Web Services (AWS) provides numerous services to help you build applications fueled by artificial intelligence (AI) capabilities. This book helps you get to grips with three AWS AI/ML-managed services to enable you to deliver your desired business outcomes. The book begins with Amazon Forecast, where you’ll discover how to use time series forecasting, leveraging sophisticated statistical and machine learning algorithms to deliver business outcomes accurately. You’ll then learn to use Amazon Lookout for Equipment to build multivariate time series anomaly detection models geared toward industrial equipment and understand how it provides valuable insights to reinforce teams focused on predictive maintenance and predictive quality use cases. In the last chapters, you’ll explore Amazon Lookout for Metrics, and automatically detect and diagnose outliers in your business and operational data. By the end of this AWS book, you’ll have understood how to use the three AWS AI services effectively to perform time series analysis.
Table of Contents (20 chapters)
1
Section 1: Analyzing Time Series and Delivering Highly Accurate Forecasts with Amazon Forecast
9
Section 2: Detecting Abnormal Behavior in Multivariate Time Series with Amazon Lookout for Equipment
15
Section 3: Detecting Anomalies in Business Metrics with Amazon Lookout for Metrics

Improving your model's accuracy

In Chapter 10, Training and Evaluating a Model, you trained an anomaly detection model and visualized the outputs over an evaluation period. Depending on what your business objectives are, here are several areas you may want to improve the obtained results:

  • Too many false positives: After evaluating the events triggered by Amazon Lookout for Equipment against reality, you might see some events as false positives you would like to discard.
  • Too many false negatives: In some cases, you might know about some anomalous events that were not detected in the evaluation period.
  • No or too short forewarning time: Sometimes, anomalies are detected but too late and you want to get a longer forewarning time so that your end users have enough time to take the appropriate mitigation actions.

Reducing the occurrences of these situations will increase the trust your end user puts in the insights provided by the service and increase the added...