Course

Course Summary
Credit Type:
Course
ACE ID:
STAT-0043
Organization's ID:
567
Organization:
Length:
4 weeks (60 hours)
Dates Offered:
Credit Recommendation & Competencies
Level Credits (SH) Subject
Graduate 3 data science
Description

Objective:

The course objective is to provide guidance and practical tools to build better models and avoid these problems. The course offers a framework to follow in implementing data science projects, and an audit process to follow in reviewing them. Case studies along with R and Python code are provided.

Learning Outcomes:

  • identify the types of unintended harm that can arise from AI models
  • explain why interpretability is key to avoiding harm
  • distinguish between intrinsically interpretable models and black box models
  • explain the tradeoff between performance and interpretability
  • establish and implement a Responsible Data Science framework for your projects
  • apply interpretability methods to black box models
  • measure the performance of models with metrics to assess bias and unfairness
  • conduct an audit of a data science project from an ethical standpoint

General Topics:

  • Introduction - review of predictive modeling
  • Why interpretability is an ethical issue
  • The responsible data science (RDS)
  • Process metrics for assessing bias
Instruction & Assessment

Instructional Strategies:

  • Computer Based Training
  • Discussion
  • Practical Exercises

Methods of Assessment:

  • Quizzes
  • Project

Minimum Passing Score:

80%
Supplemental Materials