Introduction
It’s the age of machine learning. Companies are seizing upon the power of this technology to combat risk, boost sales, cut costs, block fraud, streamline manufacturing, conquer spam, toughen crime fighting, and win elections.
This course will prepare you to participate in the deployment of machine learning – whether you’ll do so in the role of enterprise leader or quant. In order to serve both types, this course goes further than typical machine learning courses, which cover only the technical foundations and core quantitative techniques. This course includes illuminating software demos of machine learning in action using SAS products. However, the curriculum is vendor-neutral and universally-applicable. The contents and learning objectives apply, regardless of which machine learning software tools you end up choosing to work with.
What You’ll Learn
- Apply ML: Identify opportunities where machine learning can improve marketing, sales, financial credit scoring, insurance, fraud detection, and more
- Plan ML: Determine the way machine learning will be operationally integrated and deployed, and the staffing and data requirements to get there
- Greenlight ML: Forecast the effectiveness of a machine learning project and then internally sell it, gaining buy-in from your colleagues
- Lead ML: Manage a machine learning project, from the generation of predictive models to their launch
What you will learn from this course
Module 1 – Business Application of Machine Learning
➤ The ingredients of a machine learning application
➤ Risky business: predictive analytics enacts risk
management
➤ Response modeling to target marketing
➤ Gains curves for response modeling
➤ Churn modeling to target customer retention
➤ Case study: targeting ads
➤ Case study: product recommendations
➤ Credit scoring
➤ Five ways insurance companies use machine learning
➤ Fraud detection
➤ Case study: insurance fraud detection
➤ Machine learning for government and healthcare
Module 2 – Scoping, Greenlighting, and Managing Machine Learning Initiatives
➤ The six steps for running a ML project
➤ Running and iterating on the process steps
➤ How long a machine learning project takes
➤ Refining the prediction goal
➤ Where to start — picking your first ML project
➤ Strategic objectives and key performance indicators
➤ Personnel – staffing your machine learning team
➤ Sourcing the staff for a machine learning project
➤ Greenlighting: Internally selling a machine learning initiative
➤ More tips for getting the green light
➤ The most important video about ML ever, period
Module 3 – Data Prep: Preparing the Training Data
➤ Defining the dependent variable
➤ Refining the predictive goal statement in detail
➤ Identifying the sub-problem
➤ How much data do you need, and how balanced?
➤ A flash from the past: independent variables
➤ Behavioral versus demographic data
➤ Derived variables
➤ Five colorful examples of behavioral data for workforce analytics
➤ The predictive value of social media data
➤ More social data: population trends and interpreting sentiment
➤ Merging in other sources of data
➤ Data cleansing: what kind of noise is okay?
➤ Data disaster: “High school dropouts are better hires”
Module 4 – The High Cost of False Promises, False Positives, and Misapplied Models
➤ More accuracy fallacies: predicting psychosis,
Criminality, & bestsellers
➤ The cost of false positives and false negatives
➤ Assigning costs: so important, yet so difficult
➤Machine learning for social good
➤ Predicting pregnancy — and other sensitive machine inductions
➤ Predatory micro-targeting
➤ Predictive policing in law enforcement and national security1
➤ Course wrap-up