- Taschenbuch: 456 Seiten
- Verlag: John Wiley & Sons; Auflage: 1 (23. Mai 2014)
- Sprache: Englisch
- ISBN-10: 1118727967
- ISBN-13: 978-1118727966
- Größe und/oder Gewicht: 18,8 x 2,2 x 23,6 cm
- Durchschnittliche Kundenbewertung: Schreiben Sie die erste Bewertung
- Amazon Bestseller-Rang: Nr. 155.272 in Fremdsprachige Bücher (Siehe Top 100 in Fremdsprachige Bücher)
- Komplettes Inhaltsverzeichnis ansehen
Applied Predictive Analytics: Principles and Techniques for the Professional Data Analyst (Englisch) Taschenbuch – 23. Mai 2014
|Neu ab||Gebraucht ab|
Wird oft zusammen gekauft
Kunden, die diesen Artikel gekauft haben, kauften auch
Es wird kein Kindle Gerät benötigt. Laden Sie eine der kostenlosen Kindle Apps herunter und beginnen Sie, Kindle-Bücher auf Ihrem Smartphone, Tablet und Computer zu lesen.
Geben Sie Ihre Mobiltelefonnummer ein, um die kostenfreie App zu beziehen.
Wenn Sie dieses Produkt verkaufen, möchten Sie über Seller Support Updates vorschlagen?
"This book provides an excellent background to predictive analytics" (BCS, December 2014)
APPLY THE RIGHT ANALYTIC TECHNIQUE
Applied Predictive Analytics: Principles and Techniques for the Professional Data Analyst shows tech-savvy business managers and data analysts how to use predictive analytics to solve practical business problems. It teaches readers the methods, principles, and techniques for conducting predictive analytics projects, from start to finish. Internationally recognized data mining and predictive analytics expert Dean Abbott provides a practical and authoritative guide to best practices for successful predictive modeling, including expert tips and tricks to avoid common pitfalls.
This book explains the theory behind the principles of predictive analytics in plain English; readers don't need an extensive background in math and statistics, which makes it ideal for most tech-savvy business and data analysts. Each of the chapters describes one or more specific techniques and how they relate to the overall process model for predictive analytics. The depth of the description of a technique will match the complexity of the approach, with the intent to describe the techniques in enough depth for a practitioner to understand the effect of the major parameters needed to effectively use the technique and interpret the results.
Each of the techniques is illustrated by examples, either unique to the task or as part of predictive modeling competitions. The companion website will provide all of the data sets used to generate these examples, along with links to open source and commercial software, so that readers can recreate and explore the examples.
With detailed descriptions of techniques that get results, Applied Predictive Analytics shows you how to:
* Choose the proper analytics technique for various scenarios
* Avoid common mistakes and identify the weaknesses of various techniques
* Mitigate outliers and fill in missing data when necessary
* Interpret predictive models often considered "black boxes," including model ensembles
* Learn how to assess model performance so the best model is selected
* Apply the appropriate sampling techniques for building and updating models
Welche anderen Artikel kaufen Kunden, nachdem sie diesen Artikel angesehen haben?
Die hilfreichsten Kundenrezensionen auf Amazon.com (beta) (Kann Kundenrezensionen aus dem "Early Reviewer Rewards"-Programm beinhalten)
This book takes a unique, and badly needed, approach to the subject. It is a “how-to” without being a software book. Too many software instruction books focus so much on features and functions that you lose sight of the big picture. Also, too many data mining books focus solely on algorithms – often one chapter per algorithm. While many of those books are good, and necessary, there are plenty of them already.
This book invests approximately equal coverage to the six phases of the Cross Industry Standard Process for Data Mining (CRISP-DM). The evidence that the author is an expert is easy to find. Rather than merely providing the usual boilerplate on statistical significance, he reminds the reader that data miners interpret the ability of their model to generalize differently and with different tools. Rather than writing a section on regression right out of a introductory statistics book, he shows how he sometimes uses regression for classification, an approach that is technically against the rules. Rather than just a laundry list of algorithms he dedicates an entire chapter to ensembles, describing it not as another algorithm, but as a way of thinking about problems. His descriptions of boosting and bagging are clear and succinct. The essence of the book is in someways captured by the fact that one brief section is entitled “Models Ensembles and Occam’s Razor,” a section that praises ensembles even though they seem to threaten parsimony.
Perhaps, most importantly, he gives lots of advice. A book like this, on a topic like this, can be overwhelming in its factual detail. Knowledge of how the technique works does not imply action in and of itself. You need to know what you should do with this information. Applied Predictive Analytics is a coaching and mentoring session with someone that has been doing it for more than 20 years.