Data Science MBA

Table of Contents

1. Frontmatter

2. Chapter 1. Introduction and Definitions

   Alex Coad

   Abstract

   This chapter introduces the fundamental concepts of digitization and digitalization and presents data exploring the current state of digital transformation across various firms and countries. It discusses the three Vs of big data—Volume, Velocity, and Variety—and introduces the hierarchical relationship between the concepts of Big Data, Data Science, Machine Learning, and Artificial Intelligence. The chapter also draws lessons from historical technological advancements like electrification to provide a context for understanding the impact of digital transformation.

3. Chapter 2. Digital Transformation of Organizations

   Alex Coad

   Abstract

   This chapter examines different models of digital transformation, including the digital transformation playbook by Rogers, Schmarzo’s BDBMMI, and the model by Iansiti and Lakhani. It compares these models and discusses their implications for organizational change, highlighting the importance of strategic thinking in digital transformation and the need for organizations to adapt to new digital realities.

4. Chapter 3. Big Data Technologies and Architecture

   Alex Coad

   Abstract

   This chapter provides a historical perspective on organizational structures and discusses the importance of a single data lake in modern data architecture. It explores the role of cloud computing, APIs, microservices, and the benefits of small, agile teams in digital transformation. The chapter also includes an example of using R to fetch data from an API, illustrating practical applications of these technologies.

5. Chapter 4. Data Science in Organizations

   Alex Coad

   Abstract

   This chapter differentiates between Data Science and Applied Statistics, outlining the skills required for data scientists and the leadership skills needed for managers in the digital age. The chapter emphasizes the importance of organizational culture in fostering a data-driven environment and the role of leaders in driving digital initiatives. The chapter underscores the necessity for managers to understand data science to effectively lead digital transformation efforts.

6. Chapter 5. Statistical Associations Using Regression

   Alex Coad

   Abstract

   This chapter covers statistical associations using regression analysis, including univariate distributions, correlations, OLS regression, logistic regression, and Lasso regression. It provides examples in R to illustrate these concepts, helping readers understand how to apply regression techniques to analyze data. The chapter also discusses alternative regression models and their applications.

7. Chapter 6. Ethics of Data Science and AI

   Alex Coad

   Abstract

   This chapter discusses ethical aspects of data science and AI. On the one hand, digitalization has benefits, due to the potential for data to elucidate decision-making processes. On the other hand, there are serious ethical challenges posed by AI. The chapter covers topics such as AI bias, black box algorithms, privacy concerns, and the importance of ethical frameworks in AI development. The chapter also includes an example in R to demonstrate logistic regression on loan data, highlighting ethical issues in predictive modeling.

8. Chapter 7. Working with Data

   Alex Coad

   Abstract

   This chapter focuses on the practical aspects of working with data, including data quality, common problems encountered when working with data, and data pre-processing techniques. It provides an example in R using principal components analysis (PCA) on firm performance data. The chapter emphasizes the importance of data cleaning and preparation in the data science workflow.

9. Chapter 8. The User Experience (UX)

   Alex Coad

   Abstract

   This chapter explores the importance of user experience in digital transformation, discussing how digital technologies can enhance customer insights and drive innovation. It highlights the value of presenting relevant, actionable data through dashboards and the role of UX in improving business outcomes. The chapter underscores the need for organizations to focus on customer needs and leverage digital tools to enhance user experiences.

10. Chapter 9. Data Visualization

    Alex Coad

    Abstract

    This chapter covers the principles of data visualization, emphasizing the importance of graphs in communicating data insights. It discusses basic principles such as simplicity, clarity, and avoiding repetition, as well as pre-attentive processing and visual design principles such as the rule of thirds and the Z-pattern of scanning. The chapter also critiques common types of graphs such as pie charts and 3D plots, and introduces binned scatterplots. It concludes with guidelines on communicating graphs effectively and designing dashboards.

11. Chapter 10. CART and Prediction

    Alex Coad

    Abstract

    This chapter introduces Classification and Regression Trees (CART) as powerful tools for prediction. It presents the CART algorithm, the greedy nature of the algorithm, and how it can be used for both classification and regression tasks. The chapter also discusses Random Forests as an extension of CART, that leads to increased predictive accuracy by aggregating multiple decision trees. Examples in R illustrate the application of CART and Random Forests to real estate data, demonstrating their practical use in predictive modeling.

12. Chapter 11. Text as Data

    Alex Coad

    Abstract

    This chapter discusses the use of text as data, introducing the bag of words model and its applications in text analysis. It covers topics such as tokenization, stopwords, stemming, and the Document Term Matrix (DTM). The chapter also explores term frequency and tf-idf, text regression, sentiment analysis, and topic modeling, providing examples in R to illustrate these techniques. It highlights the potential of text data in providing valuable insights for business applications.

13. Chapter 12. Causal Inference

    Alex Coad

    Abstract

    This chapter emphasizes the importance of causal inference in data science, distinguishing between correlation and causation. It introduces Directed Acyclic Graphs (DAGs) as a tool for visualizing causal relationships and discusses techniques for causal inference, including Randomized Controlled Trials (RCTs), natural experiments, Regression Discontinuity Design (RDD), and Instrumental Variables (IV). The chapter underscores the need for causal understanding to make informed decisions, and highlights the limitations of observational data in establishing causality.

14. Chapter 13. Concluding Remarks

    Alex Coad

    Abstract

    This very short chapter concludes by summarizing the key points discussed throughout the book, and emphasizing the importance of digital transformation and data science in modern organizations. It highlights the need for continuous learning and adaptation in the rapidly evolving field of data science and digital transformation. The chapter encourages readers to stay updated with emerging developments and to apply the concepts and techniques learned to drive organizational success in the digital age.

15. Backmatter