TECH 68 — Machine Learning for Business with Python
Quarter: Fall
Instructor(s): Charlie Flanagan
Date(s): Nov 9—Nov 10
Class Recording Available: No
Class Meeting Day: Saturday and Sunday
Class Meeting Time: 10:00 am—4:00 pm (PT)
Please Note: This course has a different schedule than what was previously published. The course will meet on Saturday, November 9 and Sunday, November 10, 10:00 am - 4:00 pm (PT).
Tuition: $435
Refund Deadline: Nov 2
Unit(s): 1
Enrollment Limit: 60
Status: Open
Quarter: Fall
Day: Saturday and Sunday
Duration: 2 days
Time: 10:00 am—4:00 pm (PT)
Date(s): Nov 9—Nov 10
Unit(s): 1
Tuition: $435
Refund Deadline: Nov 2
Instructor(s): Charlie Flanagan
Enrollment Limit: 60
Recording Available: No
Status: Open
Please Note: This course has a different schedule than what was previously published. The course will meet on Saturday, November 9 and Sunday, November 10, 10:00 am - 4:00 pm (PT).
The availability of open source tools and libraries has made it easier to learn and experiment with AI technologies. These tools, including Python and third-party libraries, are the secret to unlocking the hidden value within the data. In this course, we will explore different business-related problems and solve them using the relevant libraries, including Scikit-Learn, TensorFlow, spaCy, and Altair. We will measure the causal impact of a marketing campaign, predict whether a customer is likely to leave, and determine how much to charge for a new product. Students will learn the entire workflow, from identifying a business problem to gathering the data and implementing the solution in code in a scalable and repeatable way. Students will hear from data science guest speakers tackling these same business problems and leave the course knowing how to formulate business problems in a data science setting and possessing the tools needed to solve them. All students will have the option of working on a capstone project, which can be used as part of a more extensive portfolio.
Python programming experience with Pandas, NumPy, and Matplotlib libraries is recommended, but not required.