Time Series Analysis on AWS: Learn how to build forecasting models and detect anomalies in your time series data

Cover
Title page
Copyright and Credits
Dedications
Contributors
Table of Contents
Preface
Section 1: Analyzing Time Series and Delivering Highly Accurate Forecasts with Amazon Forecast
Chapter 1: An Overview of Time Series Analysis
	Technical requirements
	What is a time-series dataset?
	Recognizing the different families of time series
		Univariate time-series data
		Continuous multivariate data
		Event-based multivariate data
		Multiple time-series data
	Adding context to time-series data
		Labels
		Related time series
		Metadata
	Learning about common time-series challenges
		Technical challenges
		Data quality
		Visualization challenges
		Behavioral challenges
		Missing insights and context
	Selecting an analysis approach
		Using raw time-series data
		Summarizing time series into tabular datasets
		Using imaging techniques
		Symbolic transformations
	Typical time-series use cases
		Virtual sensors
		Activity detection
		Predictive quality
		Setpoint optimization
	Summary
Chapter 2: An Overview of Amazon Forecast
	Technical requirements
	What kinds of problems can we solve with forecasting?
		Framing your forecasting problem
	What is Amazon Forecast?
	How does Amazon Forecast work?
		Amazon Forecast workflow overview
		Pricing
	Choosing the right applications
		Latency requirements
		Dataset requirements
		Use-case requirements
	Summary
Chapter 3: Creating a Project and Ingesting Your Data
	Technical requirements
	Understanding the components of a dataset group
		Target time series
		Related time series
		Item metadata
	Preparing a dataset for forecasting purposes
		Preparing the raw dataset (optional)
		Uploading your data to Amazon S3 for storage
		Authorizing Amazon Forecast to access your S3 bucket (optional)
	Creating an Amazon Forecast dataset group
	Ingesting data in Amazon Forecast
		Ingesting your target time series dataset
		Ingesting related time series
		Ingesting metadata
		What's happening behind the scenes?
	Summary
Chapter 4: Training a Predictor with AutoML
	Technical requirements
	Using your datasets to train a predictor
	How Amazon Forecast leverages automated machine learning
	Understanding the predictor evaluation dashboard
		Predictor overview
		Predictor metrics
	Exporting and visualizing your predictor backtest results
		What is backtesting?
		Exporting backtest results
		Backtest predictions overview
		Backtest accuracy overview
	Summary
Chapter 5: Customizing Your Predictor Training
	Technical requirements
	Choosing an algorithm and configuring the training parameters
		ETS
		ARIMA
		NPTS
		Prophet
		DeepAR+
		CNN-QR
		When should you select an algorithm?
	Leveraging HPO
		What is HPO?
		Training a CNN-QR predictor with HPO
		Introducing tunable hyperparameters with HPO
	Reinforcing your backtesting strategy
	Including holiday and weather data
		Enabling the Holidays feature
		Enabling the Weather index
	Implementing featurization techniques
		Configuring featurization parameters
		Introducing featurization parameter values
	Customizing quantiles to suit your business needs
		Configuring your forecast types
		Choosing forecast types
	Summary
Chapter 6: Generating New Forecasts
	Technical requirements
	Generating a forecast
		Creating your first forecast
		Generating new subsequent forecasts
	Using lookup to get your items forecast
	Exporting and visualizing your forecasts
		Exporting the predictions
		Visualizing your forecast's results
		Performing error analysis
	Generating explainability for your forecasts
		Generating forecast explainability
		Visualizing forecast explainability
	Summary
Chapter 7: Improving and Scaling Your Forecast Strategy
	Technical requirements
	Deep diving into forecasting model metrics
		Weighted absolute percentage error (WAPE)
		Mean absolute percentage error (MAPE)
		Mean absolute scaled error (MASE)
		Root mean square error (RMSE)
		Weighted quantile loss (wQL)
	Understanding your model accuracy
	Model monitoring and drift detection
	Serverless architecture orchestration
		Solutions overview
		Solutions deployment
		Configuring the solution
		Using the solution
		Cleanup
	Summary
Section 2: Detecting Abnormal Behavior in Multivariate Time Series with Amazon Lookout for Equipment
Chapter 8: An Overview of Amazon Lookout for Equipment
	Technical requirements
	What is Amazon Lookout for Equipment?
	What are the different approaches to tackle anomaly detection?
		What is an anomaly?
		Model-based approaches
		Other anomaly detection methods
		Using univariate methods with a multivariate dataset
	The challenges encountered with multivariate time series data
	How does Amazon Lookout for Equipment work?
		Defining the key concepts
		Amazon Lookout for Equipment workflow overview
		Pricing
	How do you choose the right applications?
		Latency requirements
		Dataset requirements
		Use case requirements
	Summary
Chapter 9: Creating a Dataset and Ingesting Your Data
	Technical requirements
	Preparing a dataset for anomaly detection purposes
		Preparing the dataset
		Uploading your data to Amazon S3 for storage
	Creating an Amazon Lookout for Equipment dataset
	Generating a JSON schema
		Dataset schema structure
		Using CloudShell to generate a schema
	Creating a data ingestion job
	Understanding common ingestion errors and workarounds
		Wrong S3 location
		Component not found
		Missing values for a given time series
	Summary
Chapter 10: Training and Evaluating a Model
	Technical requirements
	Using your dataset to train a model
		Training an anomaly detection model
		How is the historical event file used?
		Deep dive into the off-time detection feature
	Model organization best practices
	Choosing a good data split between training and evaluation
	Evaluating a trained model
		Model evaluation dashboard overview
		Interpreting the model performance dashboard's overview
		Using the events diagnostics dashboard
	Summary
Chapter 11: Scheduling Regular Inferences
	Technical requirements
	Using a trained model
	Configuring a scheduler
		Preparing your Amazon S3 bucket
		Configuring your scheduler
	Preparing a dataset for inference
		Understanding the scheduled inference process
		Preparing the inference data
	Extracting the inference results
	Summary
Chapter 12: Reducing Time to Insights for Anomaly Detections
	Technical requirements
	Improving your model's accuracy
		Reducing the number of signals
		Using the off-time conditions
		Selecting the best signals
	Processing the model diagnostics
		Deploying a CloudWatch-based dashboard
		Using the Lookout for Equipment dashboards
		Post-processing detected events results in building deeper insights
	Monitoring your models
	Orchestrating each step of the process with a serverless architecture
		Assembling and configuring the AWS components
	Summary
Section 3: Detecting Anomalies in Business Metrics with Amazon Lookout for Metrics
Chapter 13: An Overview of Amazon Lookout for Metrics
	Technical requirements
	Recognizing different types of anomalies
	What is Amazon Lookout for Metrics?
	How does Amazon Lookout for Metrics work?
		Key concept definitions
		Amazon Lookout for Metrics workflow overview
		Pricing
	Identifying suitable metrics for monitoring
		Dataset requirements
		Use case requirements
	Choosing between Lookout for Equipment and Lookout for Metrics
	Summary
Chapter 14: Creating and Activating a Detector
	Technical requirements
	Preparing a dataset for anomaly detection purposes
		Collecting the dataset
		Uploading your data to Amazon S3 for storage
		Giving access to your data to Amazon Lookout for Metrics
	Creating a detector
	Adding a dataset and connecting a data source
	Understanding the backtesting mode
	Configuring alerts
	Summary
Chapter 15: Viewing Anomalies and Providing Feedback
	Technical requirements
	Training a continuous detector
		Configuring a detector in continuous mode
		Preparing data to feed a continuous detector
	Reviewing anomalies from a trained detector
		Detector details dashboard
		Anomalies dashboard
	Interacting with a detector
		Delivering readable alerts
		Providing feedback to improve a detector
	Summary
Index
Other Books You May Enjoy