680. Optimizing Promotional Product Distribution in Retail with Machine Learning: A Decision Support Approach
Invited abstract in session TC-38: Forecasting, prediction and optimization 3, stream Data Science meets Optimization.
Tuesday, 12:30-14:00Room: Michael Sadler LG19
Authors (first author is the speaker)
| 1. | Eslem Guler Kose
|
| Innovative Data Analytics, Migros Ticaret AŞ | |
| 2. | Fatih Mehmet YILMAZ
|
| R&D Data Analytics, Migros Ticaret | |
| 3. | Ebru Özcan
|
| Data Science, Migros A.Ş. | |
| 4. | Ridvan Taylan
|
| Retail Analytics, Project & System Management, Migros |
Abstract
Efficient product distribution is crucial in retail, impacting customer satisfaction and business profitability. Traditional methods often rely on assumptions and manual opinions, leading to error-prone processes, resulting in stockouts or overstock issues, which negatively affect customers and businesses. This study addresses these challenges by leveraging advanced machine learning algorithms.
The primary objective of the research is to increase sales of promotional products by reducing stockouts and overstocks, preventing unexpected holding costs, and optimizing distribution. By analyzing multidimensional datasets, such as previous promotion data, risk profiles, transactional data, and product similarities, this research aims to develop a system that accurately predicts the future distribution of each product to allocated stores and provides decision-support recommendations.
Various machine-learning algorithms were employed during the estimation process. Among them, the XGBoost algorithm, which uses bagging to train multiple decision trees and then combines the results, was chosen as the primary model due to its high accuracy. Implementing this strategy has already streamlined distribution efforts by a factor of ten, ultimately maximizing the effectiveness of delivering promotional products to relevant stores. By discovering these patterns, we aim to direct products towards the most efficient distribution channels, enhancing operational efficiency and increasing turnover.
Keywords
- Analytics and Data Science
- Decision Support Systems
- Supply Chain Management
Status: accepted
Back to the list of papers