Data-Driven Inventory Control and Integrated Employee Involvement for Special Buys at ALDI SÜD Germany

Alex Tschan (), Lars Hetzel (), Ralf Eisinger (), Carolin Eggen (), Claudia Heuser () and Victoria Fritz ()
Additional contact information
Alex Tschan: ALDI SÜD Germany, Murr, 71711 Baden-Württemberg, Germany
Lars Hetzel: ALDI SÜD Germany, Murr, 71711 Baden-Württemberg, Germany
Ralf Eisinger: ALDI SÜD Germany, Murr, 71711 Baden-Württemberg, Germany
Carolin Eggen: ALDI SÜD Germany, Murr, 71711 Baden-Württemberg, Germany
Claudia Heuser: ALDI SÜD Germany, Mülheim, 45476 Nordrhein-Westfalen, Germany
Victoria Fritz: ALDI SÜD Germany, Murr, 71711 Baden-Württemberg, Germany

Interfaces, 2025, vol. 55, issue 1, 22-35

Abstract: As a subsidiary of the ALDI SOUTH Group, ALDI SÜD Germany launched the data-driven special buys project in response to pandemic-related supply chain disruptions, market shifts, and growing competition. This initiative combines advanced analytics and operations research with employee engagement to optimize product life cycles of special buys products. The solution components include (1) multiperiod mixed-integer optimization (MIP) models for product order decisions to warehouses; (2) XGBoost classification for store product allocation (SAM); (3) a proprietary algorithm (ANA) for just-in-time reallocations between stores; (4) a multiperiod dynamic programming model (DAVE) developed in 2021 for nationwide inventory clearance; (5) an advanced version for inventory clearance, the DAVE stochastic dynamic programming model (DAVE SDP), introduced in 2023; (6) a multivariate regression model for budget allocations for markdowns on small product leftover quantities for incorporating store employee involvement; and (7) a smartphone application (Market-Whispering) to engage 50,000 employees in product selection. This paper focuses on the MIP, which optimizes the decision on stock order quantities to warehouses. We examine this in conjunction with ANA and DAVE because of their significant influence on operational efficiency. For DAVE, we examine two variants: the reference model DAVE and DAVE SDP. The project faced coordination challenges and required a strategic shift from decentralized to centralized approaches. Proprietary software for the special buys product range improved operational efficiency, positively impacting the daily operations of 40,000 store employees, and led to annual savings of several million euros in Germany.

Keywords: order quantity; inventory allocation; markdown pricing; stock-keeping costs; machine learning; employee involvement; Edelman award (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
http://dx.doi.org/10.1287/inte.2024.0182 (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:inm:orinte:v:55:y:2025:i:1:p:22-35

Access Statistics for this article

More articles in Interfaces from INFORMS Contact information at EDIRC.
Bibliographic data for series maintained by Chris Asher ().