Data Science Design Patterns

  • ISBN 13:


  • ISBN 10:


  • Edition: 1st
  • Format: Hardcover
  • Copyright: 08/03/2020
  • Publisher: Addison-Wesley Professional

Note: Not guaranteed to come with supplemental materials (access cards, study guides, lab manuals, CDs, etc.)

Extend Your Rental at Any Time

Need to keep your rental past your due date? At any time before your due date you can extend or purchase your rental through your account.

Rental Options

List Price $54.99 Save

Free Shipping Free Shipping On Every Order
Usually Ships in 2-3 Business Days


Data Science Design Patterns brings together several dozen proven patterns for building successful decision-support and decision-automation systems in the enterprise. Like Martin Fowler's classic Patterns of Enterprise Application Architecture, it helps you rapidly hone in on proven solutions to common problems, leveraging the hard-won expertise of those who have come before you.


Todd Morley helps you draw upon and integrate diverse domains including statistics, machine learning, information retrieval, compression, optimization, and other areas of software development and business consulting. His patterns address many common challenges, including categorization, prediction, optimization, testing, and human factors. They link directly to key goals for data science and analytics: increasing revenue, decreasing costs, reducing risk, choosing strategies, and making key decisions.


Each pattern offers a high-level design for an application module or layer that either directly solves an enterprise-scale data science problem, or offers a higher-level approach to solving it. Throughout, Morley presents wide-ranging examples, links to real-world case studies, and extensive bibliographic references for deepening your understanding.


This guide's patterns will substantially shorten the learning curve faced by software developers, architects, and IT professionals who have limited mathematical background, and are tasked with solving large-scale data science business problems. They will be equally valuable to experienced data scientists interested in applying best practices to become even more effective.

Write a Review