
Machine Learning for Time Series with Python, 2nd Edition
Machine Learning for Time Series with Python, 2nd Edition is a practical guide to forecasting workflows, model evaluation, and production monitoring. It ranges from classical methods to deep learning and foundation models, so it suits readers with Python basics who want broad coverage rather than a narrowly focused forecasting manual.
At a glance
- Covers classical forecasting such as ETS, ARIMA, and Theta alongside gradient boosting and neural-network approaches.
- Describes forecast evaluation with SMAPE, MASE, RMSSE, rolling windows, and walk-forward validation.
- Includes feature engineering, practical demand and financial forecasting examples, and pipeline tools such as sktime, darts, mlforecast, and skforecast.
- Extends beyond forecasting to uncertainty quantification, anomaly and drift handling, and production monitoring.
Pros and cons
Pros
- Connects foundational forecasting methods with modern machine learning and deep learning approaches.
- Includes practical topics spanning evaluation, feature engineering, model monitoring, and scaling.
- The listed scope includes applications such as demand forecasting, financial forecasting, spatiotemporal modeling, and survival analysis.
Cons
- The broad scope spans many specialized methods, so readers seeking only a focused introduction to one forecasting technique may find it extensive.
Technical specifications
9 specifications| Publisher | Packt Publishing |
|---|---|
| Edition | 2nd |
| Publication date | October 26, 2026 |
| Language | English |
| Print length | 486 pages |
| ISBN-13 | 978-1837631339 |
| ISBN-10 | 1837631336 |
| Weight listed | 1.82 pounds |
|---|---|
| Dimensions | 7.5 x 1.1 x 9.25 inches |
What to know before buying
Listing details to confirm
The listing describes a second edition and gives a publication date of October 26, 2026. Basic Python knowledge is stated as a prerequisite, while statistics familiarity is described as helpful.
Who is it for?
A good fit for
- Data analysts and data scientists building forecasting workflows in Python.
- Python developers who want to apply classical, machine-learning, and deep-learning methods to time-series data.
- Readers interested in model evaluation, uncertainty, monitoring, or specialized time-series applications.
Less suited to
- Readers without basic Python knowledge, which the listing identifies as a must.
- Readers looking only for a short, narrowly focused guide to a single forecasting method.
Customer reviews on Amazon
- 5 stars
71% 71% - 4 stars
29% 29% - 3 stars
0% 0% - 2 stars
0% 0% - 1 star
0% 0%
The supplied rating aggregate is positive, with the reported ratings falling in the four- and five-star categories. The sample is small and includes no written feedback here, so it cannot establish which aspects readers liked or whether the book's broad coverage meets a particular reader's needs.
Frequently asked questions
What background does the book assume?
The listing says basic Python knowledge is a must and familiarity with statistics will help readers get more from the book.
Which forecasting methods are covered?
The described scope includes ETS, ARIMA, Theta, gradient boosting, recurrent networks, Transformer-based and convolutional models, and foundation models.
Does it address deployment and monitoring?
Yes. The listing includes production workflows such as feature stores, model tracking, monitoring, deployment, and scaling strategies.
Does the book cover topics beyond forecasting?
Yes. The described topics include classification, anomaly and drift handling, spatiotemporal modeling, irregular time series, survival analysis, and causal inference.
Alternative options

Modern Time Series Forecasting with Python: Explore industry-ready time series forecasting using modern machine learning and deep learning
$55.76

Machine Learning for Time-Series with Python: Forecast, predict, and detect anomalies with state-of-the-art machine learning methods
$39.56

An Illustrated Guide to AI Agents: Concepts and Code for Building Agents with LLMs, Tools, and Memory
$53.99

Graph Data Modeling in Python: A practical guide to curating, analyzing, and modeling data with graphs
$46.99

Building AI Agents with LLMs, RAG, and Knowledge Graphs: A practical guide to autonomous and modern AI agents
$39.89

Time Series Analysis with Python Cookbook: Practical recipes for the complete time series workflow, from modern data engineering to advanced forecasting and anomaly detection
$47.49

Python Developer Bootcamp
$67.69

Multi-Agent AI Engineering: Design, build, and operate AI systems that think and act as coordinated teams
$49.63

The Practical Network Engineer's Guide: Master routing, network diagnostics, and troubleshooting
$37.99

Python for Algorithmic Trading Cookbook: Recipes for designing, building, and deploying algorithmic trading strategies with Python
$42.49

Hands-On AI Development with Python: Build and Deploy Real-World AI, Machine Learning, Deep Learning, and NLP Applications
$34.99

Claude Visual Bible: A step-by-step, screenshot-by-screenshot guide to writing, researching, analyzing, and automating with Claude
$28.25























