Thesis subject

Enhancing Retail Shopping Experience through Consumer Transaction Analytics (BSc / MSc)

In an age where retail is driven by data, this thesis project delves into the world of SPAR's consumer behaviour and preferences. From uncovering the subtle connections between products to crafting personalized shopping experiences, this research aims to apply advanced data analytics to not just understand, but to revolutionize the retail consumer experience.

Short description

This thesis will focus on leveraging data analytics to improve the retail consumer experience. The goal is to analyse and understand consumer behaviour, preferences, and shopping patterns. By employing advanced data analysis, this thesis seeks to insights that can significantly impact consumer satisfaction and loyalty.

In this thesis, transactional data is made available by SPAR International. SPAR is the world’s largest voluntary food retail chain with over 13,623 stores in 48 countries worldwide with global sales of €41.2 BN. At SPAR, a wealth of transactional data is meticulously collected and stored. This transactional data encompasses a comprehensive record of consumer purchases, spanning across a diverse array of products and stores.

Objectives and tasks

The following research objectives can be pursued:

  1. Shopping/Market Basket Analysis: Investigate consumer shopping baskets and purchase-sequence data to identify product affinities, products frequently bought together, and other purchasing patterns.
  2. Consumer Analytics, Personalization, and Segmentation: Develop personalized solutions based on consumer buying patterns, allowing for targeted product/category recommendations and marketing strategies.
  3. Outlet & Location Analysis: Utilize open-source data, consumer profiles, geographic information, and transactional data to determine optimal locations for opening new stores.
  4. Text Mining: Employ text mining techniques to analyse consumer reviews and other text data to identify trends and patterns in consumer feedback.

Requirements

  • Courses: Programming in Python (INF-22306), Statistics (MAT), Big Data (INF-33806) or Machine Learning (FTE-35306)
  • Required skills/knowledge: · Experience in data analytics and willingness to learn new data-driven tools, general interest in the retail sector and consumer behaviour

    Key words: Data Science, Machine Learning, Retail, Food and Beverages, Consumer Behaviour, Market Basket Analysis, Consumer Segmentation, Consumer Review Mining, Consumer Profiles.

    Contact person(s)

    Sander Breevaart (sander.breevaart@wur.nl)