Abstract
Retail product placement has traditionally relied on static shelf layouts and techniques such as market basket analysis, often guided by managerial intuition and category based organization. However, such approaches frequently overlook the complexity of consumer purchasing behavior as reflected in the transactional data, and this study investigates how data driven analysis of purchase relationships can inform more effective product placement strategies in physical retail environments. Unlike the sequential models, this study focuses on co occurrence relationships due to dataset constraints, prioritizing interpretability for retail applications. Using transaction level data from the Instacart dataset, this research applies association rule mining through the Apriori algorithm, implemented in R. The products are structured into transactional formats, and the relationships are identified based on support, confidence, and lift metrics. This approach enables the extraction of statistically significant product associations that reflect real purchasing behavior across multiple transactions. The findings reveal that purchasing behavior is highly structured, with strong and consistent associations between specific product groups. These relationships highlight clear opportunities for cross selling and strategic product adjacency within physical retail spaces. The results demonstrate that leveraging co occurrence patterns can enhance product visibility, improve customer navigation, and increase basket value. This study contributes to the current existing literature by translating data mining techniques into actionable merchandising strategies within physical retail contexts. It provides a practical framework for retailers seeking to move beyond static layouts toward adaptive, data driven product placement. By bridging the gap between analytical modeling and in store implementation, the research supports more efficient and customer centric retail decision making.
Publication Date
5-2026
Document Type
Thesis
Student Type
Graduate
Degree Name
Professional Studies (MS)
Department, Program, or Center
Graduate Programs & Research
Advisor
Ioannis Karamitsos
Recommended Citation
Shamaa, Mohra, "Optimizing Product Placement using Purchase Pattern Analysis" (2026). Thesis. Rochester Institute of Technology. Accessed from
https://repository.rit.edu/theses/12545
Campus
RIT Dubai
