With the development of information technology, every organization must adapt to a data-driven world where decisions are made based on not only fundamental business logic but also real-time and high-dimensional data. The process of making data-informed, or even data-driven, decisions is called data science. Such decision-making process requires that the leaders of organizations understand the technological platform of data acquisition, storage and manipulation. It also requires leadership to be familiar with various data-driven decision-making techniques, their advantages and their disadvantages.
This course provides an introduction to the topic and helps leaders utilize data to better manage their organizations. The first half of the day will provide a framework for data-driven decision making, which includes data acquisition, data storage, data manipulation, inference and optimization. Participants will learn all basic fundamental layers that enable an organization to make data-driven decisions.
The second half of the day will involve two major analysis tools in the data science world: causal inference and machine learning. Participants will learn how to apply those two techniques to different types of problems. Participants will also learn the advantages and disadvantages of each technique, and how to recognize false claims using these techniques and data.
By the end of the course, participants will possess fundamental knowledge of different building blocks of data science.
OPM Competency: Data Science
- Define “data science” and how it applies to government agencies;
- Identify the fundamental building blocks of data science.
- Understand “causal inference” and how it could help an organization make data-driven decisions.
- Understand “machine learning” and how it could help an organization make data-driven decisions.
- Gain basic judgement on whether a causal-inference or machine-learning claim is false.