The collection, interpretation, and analysis of data have always been a central pillar of business decision-making. Historically, this has followed a two-step process: statisticians gather data, organize it, run analytics, and prepare reports. At some future point, a decision-maker will examine these reports, interpret the results, and make decisions. However, with the advent of powerful and inexpensive computing platforms, data collection and analysis has moved into the continuous decision-making cycle itself, with decisions being constantly updated as new data is instantly analyzed and acted upon. Consequently, decision-makers can no longer isolate themselves from the grungy side of data, and they need to know where the data originated, how it was transformed, what nature, and the strengths and limitations of the analytical techniques used. Today, to be effective, decision-makers need an intuitive understanding of the statistics, the math, and the programming that underlie this “live” analytical and decision-making process.
This course aims to give you an understanding of the analytical side of the decision-making cycle, focusing on programming as the element that “glues” the collection, transformation, visualization, and analysis of data. We will see how to get data from common sources (APIs, web scraping), examine the rudiments of data visualization (charts, maps), and get an intuitive understanding of the types of analytical tools in use today (machine learning, deep learning, analysis of networks, analyzing natural language texts).
With its extensive collection of libraries, Python is fast becoming the platform of choice for data analytics, so Python will be our language for this course. The course is very hands-on, and you should expect a lot of programming work, all of it fairly intense. A basic understanding of how to write programs in Python is, therefore, a must for this class. But, the primary takeaway from the course is not the programming but rather an understanding of the mechanics, the vocabulary, and the techniques in data analytics. Even if you find programming a frustrating and head-banging exercise, you can get a lot out of the class (if you’re willing to suffer a bit!).
STUDENTS WILL NEED TO EITHER HAVE PASSED (PYTHON FOR MBAS) OR THE ADVANCED PYTHON QUALIFICATION EXAM (https://www8.gsb.columbia.edu/courses/python#advanced_qual) BEFORE THE FIRST DAY OF CLASS
Division: Decision, Risk and Operations
Curriculum Pathway: Data Analytics and AI
Completion Requirement
Spring 2025
B8139 - 001
Day(s)
Date(s)
Start/End Time
Room
-
Wednesday 01/27/2025 - 05/02/2025 2:20PM - 5:35PM Geffen 520