AQM 2000-10 - PREDICT BUS ANALYTIC

Academic Period:

Fall 2025

Section:

Title:

PREDICTIVE BUSINESS ANALYTICS

Meeting Patterns:

Tue/Thu | 11:30 - 13:00

Locations:

Horn Computer Center 164 Can be several values or empty

Start Date:

Tuesday, August 26, 2025 Date format can be changed

End Date:

Friday, December 12, 2025 Date format can be changed

Instructor Name:

Howard Troughton

Instructor Email:

htroughton@babson.edu

Academic Unit:

MAST - Mathematics, Analytics, Science and Technology

Academic Level:

Undergraduate

Maximum Credits:

4

Delivery Mode:

In-Person

Allowed Grading Bases:

Graded

Section Status:

Waitlist

Enrollment Count:

36

Section Capacity:

36

Description:

AQM2000 Predictive Business Analytics 4 Foundation Liberal Arts Credits This course is only open to students who started Fall 2021 or after This course introduces students to the foundational ideas of modern data science through a hands-on implementation in modern statistical software. Students will encounter key conceptual ideas like the importance of holdout data, the dangers of overfitting, and the most common performance indicators for various model types through a tour of popular and practical predictive analytics algorithms: linear regression, k-nearest neighbors, logistic regression, classification and regression trees, naive Bayes’, and others. In addition to these supervised learning models, students will investigate unsupervised learning models like association rules and clustering, which are designed to uncover structure in data rather than predict a particular target. Throughout the course, students will practice communicating the results of their analyses to a variety of stakeholders. Prerequisites: AQM1000

HTML Description:

AQM2000 Predictive Business Analytics

4 Foundation Liberal Arts Credits

This course is only open to students who started Fall 2021 or after

This course introduces students to the foundational ideas of modern data science through a hands-on implementation in modern statistical software. Students will encounter key conceptual ideas like the importance of holdout data, the dangers of overfitting, and the most common performance indicators for various model types through a tour of popular and practical predictive analytics algorithms: linear regression, k-nearest neighbors, logistic regression, classification and regression trees, naive Bayes’, and others. In addition to these supervised learning models, students will investigate unsupervised learning models like association rules and clustering, which are designed to uncover structure in data rather than predict a particular target. Throughout the course, students will practice communicating the results of their analyses to a variety of stakeholders.

Prerequisites: AQM1000

Format:

In-Person Can be several values or empty

Session:

Full Session Can be several values or empty

Elective:

Can be several values or empty

Program:

Foundation Liberal Arts (UGrad), , Can be several values or empty