Causal Model of Fresh Write-Offs: Identifying Drivers and Estimating the Effect of Forecasting and Order Optimization at the SKU-Store Level

Citation: Olga Maksimchuk, "Causal Model of Fresh Write-Offs: Identifying Drivers and Estimating the Effect of Forecasting and Order Optimization at the SKU-Store Level", Universal Library of Business and Economics, Volume 01, Issue 02.

Copyright: This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

Abstract

The article examines the specifics of managing food losses in the Fresh retail segment, a topic whose salience intensified in 24 amid persistent margin pressure, climate-related risks, and rising requirements for supply-chain sustainability. The research objective is to develop and empirically validate a causal model of write-offs operating at a granular level of an individual stock-keeping unit (SKU) and a specific store. In contrast to widely used correlational schemes, the proposed approach relies on Double Machine Learning (DML), enabling separation of the managerial intervention effect from external confounders, including meteorological factors and fluctuations in consumer demand. The analysis isolates dominant determinants of write-offs; the most consequential include inventory age, the intensity of marketing activity, and the quality of local forecasting procedures. Empirical verification is performed on data from a large retail chain; the introduction of causal optimization algorithms demonstrates a stable 15% reduction in write-off volume while simultaneously improving on-shelf availability. The results support the proposition that embedding causal inference into replenishment loops constitutes a critical condition for enhancing operational performance and environmental sustainability of modern supply chains under high market uncertainty.

Keywords: Food Waste, Fresh Retail, Causal Inference, Double Machine Learning, Order Optimization, Demand Forecasting, SKU-Store, Inventory Management, Sustainable Development, Logistics Efficiency.

https://doi.org/10.70315/uloap.ulbec.2024.0102017