MGT 100: Customer Analytics Summer 2024R

Java Python Syllabus

MGT 100: Customer Analytics

Summer 2024

Welcome

We welcome everyone to this course. We want all students to feel valued, respected, and safe.

We also want you to succeed. We will work hard to help make that happen; we have good intentions toward you! However, this is not an easy class for most people, as we cover challenging material quickly. You will need to participate actively. This means engaging with readings, analytic tools, your instructors, and your peers. Rest assured that virtually all students pass this course and, we hope, learn a lot along the way.

This course was designed from scratch by UCSD faculty for quantitative UCSD students. It serves as a core course in the joint Econ/Rady Business Economics major and as an alternate core course in the Business and Marketing minors. We actively work to maintain, update, and improve the course every time we teach it. We have received overwhelmingly positive comments about the value of the course, the style. in which we’ve taught it, and the skills students gained as a result of studying this material. We endeavor to provide you the same challenging yet enjoyable experience.

Instructors

Prof. Dan Yavorsky

• email: dyavorsky@ucsd.edu

• links: bio | website | linkedin

• office hours: immediately before/after Friday class and over zoom by appointment

TA Sreyashi Bhattacharya

• email: srbhattacharya@ucsd.edu

• links: linkedin

• office hours: Mondays 8-9pm via Zoom (Meeting ID 998 8965 0320).

Logistics

Class is 11:00a – 1:50pm on Wednesdays and Fridays. Lectures will be recorded and posted on Canvas.

• Wednesdays are virtual over Zoom (Meeting ID 929 6533 3888)

• Fridays are in person in Room 1S114 of Otterson Hall at UCSD Rady

All materials for this course are free and available on (or linked from) Canvas. Materials include books, articles, videos, blogs, and visualizations, as well as slides, R code scripts, and datasets.

We will use Piazza as the primary method of Q&A: link

Course Introduction

Customer Analytics is the use of customer data — often combined with domain knowledge, relevant theory, and statistical modeling — to inform. and improve business decision-making. Our primary goal is to develop student understanding of data-driven business decision making. We also aim to enable students to perform. and interpret analytic techniques whose results inform. those decisions.

In pursuit of those goals, our course design principles are experiential learning and assessment of applications. Half our time will be spent discussing key concepts in customer analytics. The other half will be spent coding to implement those ideas. Our mentors instilled in us the idea that “you don’t understand it until you code it,” and we, in turn, aim to propogate this belief with the next generation of scholars. Implementation will all be done in the programming language R.

Class meetings will have a regular format. Each class session we will include a lecture followed by an analytic (i.e., coding or programming) demonstration. During the demonstration, we will step through an R code script. to implement techniques from that session’s lecture.

Outside of the classroom, students will complete required readings and homework assignments consisting of a set of analytic tasks similar to what was demonstrated in class. Students will submit mini-quizzes to evaluate their effort towards the reading and analytic tasks. There is no midterm; there will be a final exam.

This is designed as a survey course: we cover a broad range of topics in limited depth, although we maintain a deeper through-line that investigates demand modeling and usage. The survey nature of the course is more typical of graduate business courses than the undergraduate economics courses many students will have taken previously.

We seek to simulate a professional experience. We therefore expect consistent, regular attendance and participation. We require no memorization, encourage collaboration, and will aim to provide sufficient time and resources to complete deliverables.

We understand that student financial resources are often limited. We rely exclusively on materials that are either free or already paid by your tuition. We then provide pointers to additional or advanced material for students interested in deeper learning.

Most students will need to commit approximately 5–10 hours per session (i.e., 10–20 hours per week in the summer) outside of class to have a successful experience. We will modify these terms an MGT 100: Customer Analytics Summer 2024R d expectations as needed. Student feedback is welcome at any point.

Topics

We address the following topics. Please see the associated Canvas module for each topic to find related materials and more information.

1. Introduction to Course & R

2. Customer Data & Data Visualization

3. Market Segmentation

4. Dimension Reduction and Market Mapping

5. Demand Estimation

6. Heterogeneity

7. Price Optimization

8. Branding

9. Market Size and Customer Lifetime Value

10. Final Exam

Assignments and Grading

Homeworks and Quizzes (60%): Each week except the first, there will be a quiz. The quiz questions will (1) cover topics and ideas from that week’s assigned readings, (2) require you to submit results from implementing (on data with code) analytic techniques, and (3) ask you to interpret the analytic results or consider the resulting insights about the product, market, or customers. As part of the quizzes, you will submit your R scripts, which will be reviewed to ensure active engagement with the material, to award partial credit, and to ensure honest, individual effort (i.e., to check for plagerism).

Final Exam (40%): There will be a final exam. It will assess comprehension of the readings, require under-standing the material presented in the lectures, and draw heavily from the assigned homework. Additional details about the final exam will be announced toward the end of the course.

Grade Calculations: The median grade will be curved to a B+. Each student’s lowest quiz score will be dropped if more than 80% of SET evaluations are completed. Individual grades may be adjusted upwards or downwards for consistent behavior. as described below.

Course Policies

Attendance: We strongly recommend regular attendance and participation, but we will not formally assess them. It is imperative to keep pace with the course and not fall behind. You should proactively anticipate and manage issues you might experience in balancing your efforts across other courses or obligations.

Late Enrollment: Students who add the course after the first session are responsible for immediately catching up on all class content and deliverables.

Collaboration: All assignments except the final exam may be worked on in collaboration with other students. Collaboration is optional and groups should be small. Each student is individually responsible for creating and submitting their own answers and code.

Contacting Instructors: Please use Piazza as the primary method contact the professor and/or TA(s). Post questions about course content and homeworks publicly so that both the instructors and other students can provide answers. For matters that pertain to you individually (illness, questions about grading, etc.) please email the instructor and cc the TA(s) (or vice-versa); do not email us separately.

Class Participation: Some letter grades may be adjusted based on class contributions. An example of a positive contribution would be helping to consistently move the class discussion forward. Examples of negative contributions include disengagement with the course, distracting others, or nonconformance to course or classroom norms.

When Struggling: We understand that student learning styles differ and no single approach is best for everyone. We also know that anyone can go through a difficult time. Please tell us if you have trouble learning in this environment. We may be able to make suggestions, connect you with resources, or find appropriate accommodations. We will work with you as best we can.

Use of AI Technology: We explicitly allow use of AI technology (e.g. ChatGPT). We caution that you are responsible for content and accuracy of your submitted work. It is plagiarism and a violation of UCSD Policy on the Integrity of Scholarship to copy work created by someone else (or their technology) and pass it off as your own. Relevant additional information is available in the FAQ of (academicintegrity.ucsd.edu).

Late Submissions: Late deliverables will be accepted for partial credit unless grave circumstances with some form. of documentation are provided prior to the deliverable due date.

Re-grade Requests: Any request for regrading must be made in writing within two weeks of a deliverable being assessed but before final course grades are submitted to the Registrar. The professor and/or TA(s) will entirely regrade any such deliverable, meaning that the resulting grade change may be positive or negative