Identify business cases for using data science and Big Data
Understand how to apply various powerful data science methods to business problems
Understand the requirements and pitfalls of working with each data science method
| Prerequisites | none |
| Instruction | 3 hours, 15 min |
| Practice | 2 to 4 hours |
Syllabus: Data Science Methods
This course is designed for managers and executives who want to understand how and when powerful data science methods can be applied to drive business forward. In just over 3 hours of instruction time, you will learn the intuition, practical use cases, and pitfalls about the most commonly used data science methods. Improve communication with your data science team and drive your data strategy forward.
By the end of this course, students will be able to:
- Identify business cases for using data science and Big Data
- Understand how to apply various powerful data science methods to business problems
- Understand the requirements and pitfalls of working with each data science method
Assessment:
- Concept reviews: these are comprised of short five question quizzes that cover the most important concepts and ideas in each lesson. They encourage holistic understanding and are multi-faceted question types (i.e. drag and drop, fill-in-the-blanks, matching, etc).
Materials provided:
- Accompanying PDFs to use as reference materials
- Printable guidelines that managers can fill out to assess how to apply data science methods in their business
Course Outline
How to segment your data (38 min)
What is data science?
Finding patterns in your data
Grouping your data
Targeting your customers
How to find important features (39 min)
Making product recommendations
Identifying important attributes
Measuring likelihood of events
Checking your models
How to measure networks (30 min)
Networks as a framework
Measuring networks
Measuring trust
Measuring connectedness
How to understand your customers (28 min)
Measuring associations
Turning the qualitative into quantitative
Measuring sentiment
How to predict demand (28 min)
Predicting customer demand
Using correlation
Using many variables to explain outcomes
How to work with unusual data (32 min)
Understanding non-linear relationships
Quantifying seasonality
Detecting outliers
Putting it all together
Total instructional time: 3 hrs, 15 min
Richard Heimann
Richard Heimann is the Chief Data Scientist at Cybraics, Inc. He is part of the adjunct Faculty at University of Maryland, Baltimore County and an Instructor of Human Terrain Analysis at George Mason University. Rich serves on the Selection Committee for the AAAS Big Data & Analytics Fellowships Program. He has deep expertise running data science teams and is the co-author of “Social Media Mining with R.”