Building Predictive and Prescriptive AI Data Models

This course is best for technical scientists, engineers, or technical data analysts who want to become proficient in Python-based machine learning for predictive and prescriptive data modeling. The goal of the course is to provide learners with the tools they need to get started with supervised and unsupervised learning and to teach them practical ways to build their own machine-learning solutions. 

Key skills covered in this course: 

• Data Science
• Machine Learning in Python (Scikit-learn, Keras, Fast.ai in longer course) 

Upon successful completion of the course, learner outcomes include: 

• Summarize the data requirements and assumptions  for various machine learning models 
• Define metrics that evaluate the model’s performance against the use case
• Explain the needs and use cases for the type of ML most relevant to the company (Classification, Regression, or Unsupervised Learning) 
• Prepare data for training and analysis using Python
• Train and test a machine-learning model in Python
• Discuss how a model may be monitored for performance and fine-tuning over time

Potential learners:

• Analysts
• AI Engineers
• Data Engineers
• Software Engineers

Learners should meet the following prerequisites:

• Experience working with data in a scripting language such as Python or R*  
• Knowledge of probability and statistics, algebra, linear algebra (preferred), and calculus (preferred)

*If participants have experience working with data in a different language, they can complete a Python tutorial before the start of the course