Skip to content
Predictive Analytics – Project Capstone

Predictive Analytics – Project Capstone

A predictive modeling practicum for the predictive analytices course program.

Overview

In this course, students will apply data mining techniques in a real world case study. The case study concerns microtargeting in political campaigns, but the principles apply equally to any marketing campaign involving individual-level messaging. This course is really a “lab” for practically testing your skills in a real world context. You should have some facility with R or Python, and some familiarity with predictive modeling, before taking this course.

Note: This course is also listed as Persuasion Analytics, the study of micro-targeting and uplift modeling. The data in the course are sizeable and complex, and the domain (political targeting) is relatively new and unlikely to be familiar to most students, hence the course is ideal as a real-world case study for analytics students who need to be prepared to apply their analytical skills to new situations. Students who sign up for Persuasion Analytics will use curated, reduced data sets and an Excel add-in; students who are taking Predictive Analytics Project Capstone as part of their certificate program must use the full dataset and either R or Python.

  • Introductory, Intermediate
  • 4 Weeks
  • Expert Instructor
  • Tuiton-Back Guarantee
  • 100% Online
  • TA Support

Learning Outcomes

  • Prepare data for a predictive modeling task
  • Develop predictive models Integrate the results of A-B tests for an uplift model
  • Assess model performance
  • Improve single model performance using ensembles
  • Implement models for a real decison scenario

Who Should Take This Course

The course will also be useful as a guided project for anyone who has learned predictive modeling methods using prepared and curated data, and wants to gain experience implementing them in a real-world context with messy data.

Student in our Programming for Data Science Certificate program will take this course as their capstone project.

Our Instructors

Mr. Ken Strasma

Mr. Ken Strasma

Ken Strasma is a pioneer in the field of predictive analytics in high-stakes Presidential campaigns, serving as the National Targeting Director for President Obama’s historic 2008 campaign and for John Kerry’s 2004 presidential campaign. He produced the predictive analytics models used by the campaigns, and helped popularize the use of that technology.

Strasma is now the co-founder and CEO of HaystaqDNA, a firm that provides predictive analytics and strategic consulting services for corporations, non-profits and membership organizations.

Since 2008, Strasma has consulted on hundreds of political and corporate projects in the United States and internationally. HastaqDNA clients include multiple Fortune 500 companies with a combined market capitalization of more than $600 billion. Haystaq commercial clients span the worlds of entertainment, sports, consumer goods and healthcare. Haystaq has provided predictive analytics in international political campaigns in four continents.

Ken is the author of numerous articles and studies regarding targeting, marketing, demographics and social media analysis.

Course Syllabus

Week 1

Setting the Scene

  • Why political campaigns need to target
  • Phases of a campaign
  • Finding the right targets for the right phase
  • Getting to know the data
  • Understanding and engineering features
  • Transformations

Week 2

Developing Predictive Models

  • Traditional vs. individual level targeting
  • Deciding what to predict
  • The model-building process
  • Assessing models

Week 3

Combining Models

  • Ensembles
  • Controlled and Natural Experiments
  • A-B tests
  • Uplift – Combining A-B tests with Predictive Models

Week 4

Implementation and Actions

  • Deciding who to target and with what message

Class Dates

2024

03/08/2024 to 04/05/2024
Instructors:

Prerequisites

You must be familiar with predictive modeling and have sufficient programming level skills to write predictive model code in R or Python.

Private: Predictive Analytics 1 with Python – Machine Learning Tools

This course introduces the basic paradigm for predictive modeling: classification and prediction.
  • Skill: Introductory, Intermediate
  • Credit Options: CEU
Karolis Urbonas
Susan Kamp
Stephen McAllister
Amir Aminimanizani
Elena Rose
Leonardo Nagata
Richard Jackson

Frequently Asked Questions

  • What is your satisfaction guarantee and how does it work?

  • Can I transfer or withdraw from a course?

  • Who are the instructors at Statistics.com?

Visit our knowledge base and learn more.

Register For This Course

Predictive Analytics – Project Capstone

Additional Information

Homework

The homework in this course consists of short answer questions to test concepts, guided exercises in writing code and guided data analysis problems using software.

This course also has example software codes, supplemental readings available online.

Course Text

Depending on topic being covered, reference materials will be provided as required.

Software

To do the project in the course you will need access to and some familarity with R or Python.

Supplemental Information

Literacy, Accessibility, and Dyslexia

At Statistics.com, we aim to provide a learning environment suitable for everyone. To help you get the most out of your learning experience, we have researched and tested several assistance tools. For students with dyslexia, colorblindness, or reading difficulties, we recommend the following web browser add-ons and extensions:

 

Chrome

 

Firefox

 

Safari

  • Navidys (for colorblindness, dyslexia, and reading difficulties)
  • HelperBird for Safari (for colorblindness, dyslexia, and reading difficulties)

Register For This Course

Predictive Analytics – Project Capstone