Data Science for Retail Management

Course Director: Xuehui Gao

Purpose

This course covers Python foundations, sentiment analysis, and topic modeling, and Artificial Intelligence (AI) analytics applied to real-world scenarios to gain marketing insights for strategic retail management.

Content

1. Python Foundations:

• Fundamental programming (data types, functions, and libraries) relevant to retail data analysis
• Data manipulation with libraries like Pandas and NumPy for managing large-scale retail datasets
• Data visualization with Matplotlib for presenting retail performance metrics and customer insights

2. Sentiment Analysis:

• Text preprocessing (tokenization, stemming, lemmatization) to clean and structure retail related textual data
• Natural Language Processing (NLP) techniques for polarity detection (positive, negative, neutral) and emotion classification in retail

3. Topic Modeling:

• Text clustering and uncovering hidden topics in large retail datasets to identify product preferences and emerging trends

**Format and Structure **

The course consists of lectures, seminars, group work, tutoring and assignments with and without the use of statistical software: Python.

This course also incorporates case studies with real companies, allowing students to see firsthand how data is applied in actual business scenarios.

Course administrators: Karl.Strelis@hhs.se, alexandra.svahn.alberts@hhs.se

After successfully completing this course, students should be able to:

• Work with popular libraries such as Pandas, NumPy, and Matplotlib.
• Practice Python coding for modeling, statistical analysis, and generating marketing insights.
• Build sentiment analysis models and conduct topic modeling.
• Interpret model results to solve real-world problems in retail.
• Gain a solid understanding of machine learning and AI concepts, preparing for future studies in data analytics.

To take the subject, it is recommended to have taken Introduction to Retailing Marketing, Marketing Research, Data Analytics: Statistics for Retail Management and Customer Experience Management.

Students are required to know the basic statistical concepts, such as probability, independence, Bayes' theorem, random variables, probability distributions, measures of central tendency and dispersion, the central limit theorem, random sampling, estimation, inference, hypothesis testing, regression, mediation, moderation, bootstrapping, classification, clustering, and prediction.

Bengfort, B., Bilbro, R., & Ojeda, T. (2018). Applied text analysis with Python: Enabling language-aware data products with machine learning. O'Reilly Media, Inc. ISBN 9781491963043 (textbook and online resources).

Berger, J. (2016). Contagious: Why things catch on. Simon and Schuster. ISBN 9781451686586(textbook and online resources).

Grus, J. (2019). Data science from scratch: first principles with python, 2nd Edition. O'Reilly Media,, Inc. ISBN 9781492041139 (textbook and online resources).

All intended learning outcomes will be assessed through individual work (70%) and a written exam (30%).

Find the course schedule in TimeEdit

Have you been granted educational support because of a documented disability? If so, please contact the course director as soon as possible so that adequate accommodations can be made.

Contact specialneeds@hhs.se if you have questions about being granted educational support or need a copy of your educational support certificate.

For more information, visit the Specific Educational Needs page on the Student Hub (login required).