NEU Logo
Đại học Kinh tế Quốc dânChương trình đào tạo
English
Tiếng Việt
NEU Logo
QR Code

Đại học Kinh tế Quốc dân

207 Giải Phóng,Bạch mai, Hà Nội, Việt Nam

(84)24.36.280.280

(84)24.38.695.992

facebook.com/ktqdNEU

QR Code
Bản quyền thuộc về: Đại học Kinh tế Quốc dân
Trang chủ
Hướng dẫn sử dụng
TOKT1149 — Ứng dụng khoa học dữ liệu trong Marketing | Chương trình đào tạo NEU

TOKT1149 — Ứng dụng khoa học dữ liệu trong Marketing

Credits
3
Showing intake
K66-2024
Requested intake
K67

Course description

This course equips students with knowledge of and tools for data mining applied to marketing. Students learn how to use data to price products, estimate customer lifetime value, and build models to predict customer churn, identify potential customers, and segment customers. In addition, students are introduced to machine learning and deep learning techniques to build market basket analysis systems, product recommendation systems, and systems for analyzing customer sentiment toward products and services. Thus, this course provides comprehensive guidance on solving major problems in the field of marketing using data analytics tools. This, in turn, helps students gain a deeper understanding of customer behavior while building more effective targeted and personalized marketing strategies.

Main contents

- Knowing how to compute and visualize key KPIs in marketing

Product pricing

Customer lifetime value, Monte Carlo simulation, decision-making in marketing

Using clustering methods to segment customers

Market basket analysis using association rules

Recommending the products that customers are most likely to buy

Customer sentiment analysis

Course requirements

Requirements for eligibility to sit the end-of-course examination

The attendance score must be 5 or above (in accordance with the University's general regulations)

Method of grading attendance: see Appendix 2, rubric 1.

Regulations on class attendance

Students are responsible for attending all class sessions.

In the event of absence due to force majeure, students must proactively acquire the knowledge through the materials provided by the lecturer and other required readings.

Regulations on classroom conduct

The course is conducted on the principle of mutual respect between learners and instructors;

Take complete notes and participate in answering questions;

Read the required materials in advance;

Complete homework assignments;

Do not make noise or disturb others, and do not eat during class;

Laptops, tablets, and mobile phones may only be used for taking lecture notes and performing computations for study purposes; they must absolutely not be used for any other purpose.

Regulations on submitting major assignments

Learners who fail to submit required individual/group assignments will receive a score of 0 (zero).

After the prescribed deadline, each day of late submission will result in a one-point deduction.

Lecturers

  • Dr. Nguyen Thi Quynh Giang
  • Vu Thi Bich Ngọc

Teaching plan

Week 1

Lecture 1. Introductory session 1.1. The concept of data science and marketing 1.2. Basic problems in applying data analytics in the field of marketing 1.3. The key KPIs used to evaluate the quality of a marketing campaign
References
[1] Chapter 1, 2 of book 2 [2] The entirety of book 3
Activities
Lecturer - Introduces the syllabus, textbook, reference materials, software, and slides - Lectures on theory according to the slide content - Introduces examples in the slides - Provides guidance on reading the textbook and reference materials - Describes the data to be used for computing the KPIs Students - Review the syllabus in advance - Listen to the lecture, absorb the lecturer's knowledge, and ask questions when necessary - Review the knowledge from the prerequisite course Home assignments - Read the materials in advance and complete the exercises and examples in the slides and book
Assessment
Rubric 1

Week 2

Seminar 1 - Summary of knowledge about KPIs - Discussion of the examples, questions, and exercises of seminar 1 - Group practice guidance on how to compute and build a dashboard
References
[1] Chapter 1, 2 of book 2 [2] Lecture 1 slides
Activities
Lecturer - Divides students into groups and guides each group in identifying the KPIs appropriate to the requirements of the assignment. - Guides the calculation of each KPI. - Demonstrates a dashboard; guides students on the layout of a dashboard. Students - Read the materials in advance - Follow the practice steps - Perform the work on the computer - Work in groups to practice computing and designing the dashboard layout - Complete the dashboard at home. - Exchange and discuss Home assignments - Redo the practice exercises - Complete the exercises and requirements not answered in the seminar class

Learning resources

  • Marketing Analytics — Wayne L. Winston, Data-Driven Techniques with Microsoft Excel, 2019
  • . Hands-on data science for marketing: improve your marketing strategies with machine learning using Python and R. Packt Publishing — Hwang, Yoon Hyup, 2019
  • Course lecture notes, compiled by the teaching team
  • . Data-Driven Marketing (The 15 Metrics Everyone in Marketing should Know). John Wiley & Sons — Jeffery, Mark, Inc. https://doi.org//10.1002/9781119198666, 2012
  • . Introduction to Data Mining — Tan, P., Steinbach, M., & Kumar, V., (First Edition). In Addison-Wesley Longman Publishing Co, 2005
  • Excel, R language
Assessment
- Attendance check - Rubric 4

Week 3

Lecture 2. Predictive analytics in marketing 2.1. Building a logistic regression model and a decision tree model to predict which customers will make a purchase. 2.2 Introduction to the metrics for evaluating the quality of a classifier
References
[1] Chapter 3 of book 2 [2] Lecture 2 slides
Activities
Lecturer - Lectures on theory according to the slide content - Provides guidance on reading the textbook and reference materials - Requires students to review in advance the examples, questions, and exercises for seminar 2 Students - Read the materials in advance - Listen to the lecture, absorb the lecturer's knowledge, and ask questions when necessary Home assignments - Read the materials in advance and complete the exercises and examples in the slides and book
Assessment
- Rubric 1

Week 4

Seminar 2 - Practice building logistic regression and decision tree algorithms.
References
[1] Chapter 3, chapter 8 of book 2
Activities
Lecturer - Guides practice using the R software Students - Read the materials in advance - Follow the practice steps - Perform the work on the computer - Exchange and discuss Home assignments - Redo the practice exercises - Complete the exercises and requirements not answered in the seminar class
Assessment
- Attendance check - Rubric 2

Week 5

Lecture 3. Customer segmentation Using the k-means algorithm to cluster customers
References
[1] Chapter 10 of book 2
Activities
Lecturer - Lectures on theory according to the slide content - Provides guidance on reading the textbook and reference materials - Requires students to review in advance the examples, questions, and exercises for seminar 3 Students - Read the materials in advance - Listen to the lecture, absorb the lecturer's knowledge, and ask questions when necessary Home assignments - Read the materials in advance and complete the exercises and examples in the slides and book

Week 6

Seminar 3 - Practice building the k-means algorithm - Analyze and draw insights from the resulting clusters
References
[1] Chapter 10 of book 2
Activities
Lecturer - Guides practice using the R software Students - Read the materials in advance - Follow the practice steps - Perform the work on the computer - Exchange and discuss Home assignments - Redo the practice exercises - Complete the exercises and requirements not answered in the seminar class
Assessment
- Rubric 1, 2

Week 7

Lecture 4. Product pricing 3.1. Estimating the demand curve and using Solver to find the profit-optimal price 3.2. Product bundle pricing 3.3. Nonlinear pricing 3.4. Revenue management
References
[1] Chapters 4-8 of book 1 [2] Lecture 3 slides
Activities
Lecturer - Lectures on theory according to the content of session 3 slides - Introduces examples in the slides - Provides guidance on reading the textbook and reference materials - Requires students to review in advance the examples, questions, and exercises for seminar 4 Students - Read the materials in advance - Listen to the lecture, absorb the lecturer's knowledge, and ask questions when necessary Home assignments - Read the materials in advance and complete the exercises and examples in the slides and book

Week 8

Seminar 4 - Building models and practicing pricing for various scenarios through a set of exercises.
References
[1] Chapters 4-8 of book 1 [2] Seminar 4 slides
Activities
Lecturer - Guides the formulation of the problem from the specific requirements of the assignment. - Builds the objective function and constraints for the optimization problem. - Performs the work in Excel using the Solver tool Students - Read the materials in advance - Follow the practice steps - Perform the work on the computer - Participate in correcting the exercises - Exchange and discuss Home assignments - Redo the practice exercises - Complete the exercises and requirements not answered in the seminar class
Assessment
- Rubric 1, 2

Week 7

Lecture 5. Estimating customer lifetime value 4.1. A simple model for estimating customer lifetime value 4.2. Modeling customer lifetime with Markov chains 4.3. Using Monte Carlo simulation to predict the likelihood of success of a marketing campaign
References
[1] Chapters 19, 20, 21 of book 1 [2] Lecture 5 slides
Activities
Lecturer - Lectures on theory according to the content of the lecture 5 slides - Introduces examples in the slides - Provides guidance on reading the textbook and reference materials - Requires students to review in advance the examples, questions, and exercises for seminar 5 Students - Read the materials in advance - Listen to the lecture, absorb the lecturer's knowledge, and ask questions when necessary Home assignments - Read the materials in advance and complete the exercises and examples in the slides and book

Week 8

Seminar 5 - Building a model to model customer lifetime value for each specific use case - Discussion of the examples, questions, and exercises of seminar 5 - Discussion of the exercises in the textbook
References
[1] The exercise section at the end of chapters 19, 20, 21 of book 1
Activities
Lecturer - Guides the translation of the problem from a specific enterprise situation into a concrete model. - Guides the use of data tables in Excel - Guides the solving of exercises in textbook chapters 19, 20, 21 Students - Read the materials in advance - Follow the practice steps - Perform the work on the computer - Participate in correcting the exercises - Exchange and discuss Home assignments - Redo the practice exercises - Complete the exercises and requirements not answered in the seminar class
Assessment
- Attendance check - Answer the questions in the seminar 5 slides - Answer the lecturer's questions during the seminar

Week 9

Lecture 6. Building a product recommendation system 5.1. Market basket analysis 5.2. Building a content-based recommendation system 5.3. Building a utility-matrix-based system
References
[1] Chapters 24, 29 [2] Lecture 5 slides [3] Lecture 5
Activities
Lecturer - Lectures on theory according to the content of the lecture 6 slides - Introduces examples in the slides - Requires students to review in advance the examples, questions, and exercises for seminar 6 Students - Read the materials in advance - Listen to the lecture, absorb the lecturer's knowledge, and ask questions when necessary Home assignments - Read the materials in advance and complete the exercises and examples in the slides and book

Week 10

Seminar 6 - Guidance on building a product recommendation system using the R software
References
[1] Chapters 5, 6 of book 2
Activities
- Guides the construction of the utility matrix from transaction data - Guides the computation of cosine similarity between users and between items - Writing a function to estimate the missing rating values in the utility matrix - Writing a function that returns the top k recommended products Students - Read the materials in advance - Follow the practice steps - Perform the work on the computer - Exchange and discuss Home assignments - Redo the practice exercises - Complete the exercises and requirements not answered in the seminar class
Assessment
- Attendance check - Answer the lecturer's questions during the seminar. - Test No. 1

Week 11

Lecture 7. Sentiment classification 7.1. Using the Naive Bayes classifier for the sentiment classification problem 7.2 Applying Logistic Regression to the sentiment classification problem
References
[1] Lecture and Slides 7
Activities
Lecturer - Lectures on theory according to the content of the lecture 7 slides - Introduces examples in the slides Students - Read the materials in advance - Listen to the lecture, absorb the lecturer's knowledge, and ask questions when necessary Home assignments - Read the materials in advance and complete the exercises and examples in the slides and book

Week 12

Seminar 7 - Correcting exercises
References
[1] Seminar 7 exercises
Activities
Lecturer - Guides students on how to classify comments as having positive or negative sentiment based on the Naive Bayes algorithm. - Guides the computation of the tf-idf and pwi indices. - Exchange and discuss Home assignments - Redo the practice exercises - Complete the exercises and requirements not answered in the seminar class
Assessment
- Attendance check - Test No. 2 - Rubric 3

Week 15

Seminar 8 - Reviewing the course as a whole - Announcing the results of the component assessments - Guidance on the examination and answering questions
References
[2] Seminar 8 slides
Activities
Lecturer - Synthesizes and systematizes the knowledge covered in the lectures - Systematizes the types of questions in the end-of-term examination - Announces the attendance score (10%) - Announces the component test scores and the summary score (40%) - Corrects some questions from the reference examination questions Students - Be fully present to receive information on component scores - Review the entire course content and the reference questions
Assessment
- Attendance check - After this session, no further inquiries regarding component scores will be addressed
End-of-term examination
References
All content covered
Activities
The examination consists of a written part and a coding part submitted directly to the lecturer.
Assessment
See Appendix 1: examination matrix