Data Informed Decision Making

We live in a world dense with data, computational power, and connectivity. This creates an expectation that decision-making be rigorous, rational, and empirically grounded rather than being based purely on intuition or expertise. This course introduces you to this expectation and how to meet it.  We begin with the power and importance of data-informed decision making (DIDM) and how to recognize opportunities to leverage the power of data. We learn how to communicate the stories told by data, how to rigorously assess the accuracy and validity of those stories, and how to identify, collect, and analyze the data needed to generate them.

Options and Alternatives

# Preliminaries

Code? Excel? R? Python?

Textbook(s)? OER?

Data-Informed Decision Making

# CHAPTER 2
# Unit One

Data-Informed Decision Making

Data-informed decision making (DBDM) is the process of making decisions based on the analysis of empirical data rather than intuition or ideology or materially motivated preferences.  In this unit we explore the elements of this definition, describe a generic workflow for doing DBDM, unpack the benefits of DBDM, identify indications, contraindications, and caveats, and explore the many types and variants of DBDM.  The imperative of decision making motivates the following unit: how data inform through the stories they tell.

What makes DM hard?
multiple criteria, incomplete/uncertain information, risk,

MADM,MCDM,MODM

Introduction

Outline

Hook: Hurricane Katrina example highlighting the power of data in decision-making.

DDDM impact on publishing, wine tasting, finance, sports, and healthcare.

shift from intuition/experience-based decision-making to data-driven decision-making.

example of Planet project using satellite imagery/ML to combat deforestation.

potential of DDDM as well limitations.

Concepts

  • Data-driven decision-making
  • Intuition-based decision-making
  • HIPPO (Highest Paid Person's Opinion)
  • Big data analytics
  • Algorithmic trading
  • Machine learning
  • Dataism

Reading Review Questions


How did the example of Hurricane Katrina highlight the power of data in decision-making?
What are some of the industries that have been impacted by data-driven decision-making? Provide examples.
Explain the shift from intuition-based decision-making (HIPPO) to data-driven decision-making.
How is the Planet project using data to combat deforestation? What are the advantages of this approach?
Discuss the potential benefits and limitations of relying on data for decision-making.

# Unit Two

The Story Within Your Data

Every method of DBDM links the taking of a decision with the telling of a story. In this unit we ask what are the kinds of things a dataset can say? We talk about measures of central tendency and dispersion, and patterns such as trends and association. The unit includes exploratory data analysis (EDA), basic data visualization, and how to present and write about the stories that data tell.  Our focus on the story that data tell motivates the next unit where we ask what makes a data story believable.

# Unit Three

Analytical Tools

A data story is only as convincing as the analysis behind it is correct. In this unit we learn several analytical tools and how to characterize the uncertainty in the answers they provide. When we acquire some mastery of data analytical tools we will be prepared for the next unit in which we examine the stuff itself: what is data? where does it come from? how can we make sure it is what it is? 

# Unit Four

Collecting the Right Data

The decision depends on the story depends on the analysis depends on the data. In this unit we learn about different types of data, properties of data, methods of measurement, sources of data, methods of data collection and generation, data cleaning, and feature engineering.  

Bibliography

# CHAPTER 2

Types of Analytics

# CHAPTER 2

Decision Making

# CHAPTER 2

Tableau Superstore Dataset

# CHAPTER 2

Bibliography: What is decision making?

# CHAPTER 2

Bibliography: Telling Stories with Data

# CHAPTER 2

Feature: Interviews with Data Scientists/Analysts

# CHAPTER 2

Feature: Interviews with Data Scientists/Analysts

# CHAPTER 2

Working Notes

# CHAPTER 2