Table of Content
- In which areas is Data Science Applied?
- Common Misconceptions Surrounding Data Science
- Diverse Aspects of Data
- The CRISP-DM Methodology
- Moving the Algorithms to the Data
- Data Preparation and Integration
- Creating the Analytics Base Table
- Supervised versus Unsupervised Learning
- Exploring Forecasting Models
- Data Science Bias
- Model Evaluation: Emphasizing Generalization OverMemorization
This eBook is based on All About Data Science that has been collected from different sources and people. For more information about this ebook. Kindly write to deviprasad77058@gmail.com. I will happy to help you.
Copyright 2023 by Devi Prasad
This eBook is a guide and serves as a first guide. This book has been written on the advice of many experts and sources who have good command over Data Science. They are listed at the end of this book.
All images used in this book are taken from the LAB which is created by experts. All rights reserved, including the right to reproduce this book or portions thereof in any form whatsoever. For any query reach out to the author through email.
In which areas is Data Science Applied?
Data science plays a pivotal role in influencing decisions across various facets of contemporary societies. This segment delves into three instances that exemplify the influence of data science: consumer enterprises employing it for sales and marketing, governments utilizing it to enhance health, criminal justice, and urban planning, and professional sports franchises integrating it into player recruitment.
Utilization of Data Science in Sales and Marketing Walmart harnesses extensive datasets about customer preferences through point-of-sale systems, tracking customer behavior on its website, and monitoring social media commentary. For over a decade, Walmart has utilized data science to optimize stock levels in stores, exemplified by the restocking of strawberry Pop-Tarts in Hurricane Francis's path in 2004 based on sales data before Hurricane Charley. More recently, Walmart has employed data science to boost retail revenues, introducing new products based on social media trends, making product recommendations using credit card activity analysis, and enhancing customers' online experience. Walmart attributes a 10 to 15 percent increase in online sales to data science optimizations (DeZyre 2015).
Online, the equivalent of upselling and cross-selling is the "recommender system." If you've watched a movie on Netflix or made a purchase on Amazon, you've experienced these platforms using collected data to suggest what to watch or buy next. Recommender systems can guide users toward popular items or niche products tailored to their preferences. Chris Anderson's book "The Long Tail" (2008) argues that as production and distribution become more cost-effective, markets shift from focusing on a few hit items to a broader array of niche products. The design decision between promoting hit or niche products is crucial for recommender systems and influences the data science algorithms they employ.
Governments Harnessing Data Science In recent years, governments have recognized the benefits of embracing data science. In 2015, the US government appointed Dr. D. J. Patil as the inaugural chief data scientist. Major data science initiatives led by the US government have primarily focused on health, such as the Cancer Moonshot and Precision Medicine Initiatives. The Precision Medicine Initiative combines human genome sequencing and data science to customize drugs for individual patients. The All of Us program, part of the initiative, gathers environmental, lifestyle, and biological data from over a million volunteers to create extensive datasets for precision medicine. Data science is also transforming urban organization by monitoring and managing environmental, energy, and transportation systems, informing long-term urban planning (Kitchin 2014a). Further exploration of health and smart cities is covered in chapter 7, discussing the increasing importance of data science in our lives in the coming decades.
The US government's Police Data Initiative focuses on employing data science to help police departments understand their communities' needs, predict crime hot spots, and assess recidivism. However, some applications of data science in criminal justice have faced criticism from civil liberty groups. Chapter 6 delves into the privacy and ethics concerns raised by data science, highlighting the varying opinions people hold regarding personal privacy and data science in different domains. The chapter also explores the use of personal data and data science in determining insurance premiums for life, health, car, home, and travel.
Data Science in Professional Sports The film "Moneyball" (Bennett Miller, 2011), featuring Brad Pitt, showcases the increasing integration of data science in modern sports. Based on the book by Michael Lewis (2004), it narrates how the Oakland A's baseball team used data science to enhance player recruitment. The team identified that on-base percentage and slugging percentage were more informative indicators of offensive success than traditional baseball statistics. This insight allowed the Oakland A's to recruit undervalued players and outperform their budget. The success of the Oakland A's has spurred a revolution in baseball, with many other teams incorporating similar data-driven strategies into their recruitment processes.
The moneyball story is a vivid example of how data science can provide a competitive advantage. From a
Impressum
Verlag: BookRix GmbH & Co. KG
Texte: Devi Prasad
Bildmaterialien: Devi Prasad
Cover: Shahu Singh
Lektorat: Mahesh Patil
Korrektorat: Diwakar Jain
Übersetzung: Mukesh Ravi
Satz: Devi Prasad
Tag der Veröffentlichung: 30.11.2023
ISBN: 978-3-7554-6248-4
Alle Rechte vorbehalten