Stock Keeping Units Research Articles

Exposure to mycotoxins from the consumption of corn-based breakfast cereals in the United Arab Emirates

Corn-based breakfast cereals, known as cornflakes, have become a common breakfast choice worldwide, recognized for their convenience and versatility. However, mycotoxins can contaminate these products, adversely affecting human health. This study assessed the occurrence of major mycotoxins (AFB1, OTA, DON, ZEA, and FUM) in cornflake stock-keeping units (SKUs) marketed in the United Arab Emirates (UAE). It also evaluated the effect of different independent variables (country of origin, temperature on the production day, storage time, presence of chocolate, bran, and nut ingredients) and estimated the exposure levels of the UAE population to these mycotoxins and the associated risk factors. Seventy-six distinct cornflake SKUs were identified through a market screening and tested for mycotoxins using the Enzyme-Linked Immunosorbent Assay (ELISA) technique. AFB1, OTA, ZEA, FUM, and DON were detected in 23.7, 48.7, 27.6, 9.2 and 88.2% of the samples, respectively. The mean concentrations among positive samples were 2.0, 1.0, 10.14, 584.9, and 90.6 μg/kg, respectively. Except for AFB1, the average mycotoxin levels in samples were below the established limits by the European Union (EU). Among positive samples, none exceeded the US FDA limits for all mycotoxins, and only one exceeded the CODEX limit for FUM. On the other hand, four (5.3%), one (1.3%), one (1.3%), and one (1.3%) SKU exceeded EU limits for AFB1, OTA, FUM, and ZEA, respectively. The country of origin (developing vs. developed countries) exhibited a significant effect on AFB1 presence (p < 0.0001). Furthermore, higher temperature on the production day was associated with significantly higher AFB1 occurrence (p = 0.009). Moreover, the presence of chocolate ingredient had a borderline significant effect on AFB1 (p = 0.05) and a significant effect on OTA (p = 0.002), with higher percentages observed in SKUs containing chocolate. However, no significant effects were found for storage time or the presence of bran and nut ingredients in the cornflakes. On the other hand, the HQ values were below 1 for all mycotoxins, indicating low risk. MoE values exceeded 10,000 among regular cornflake consumers, except for FUM, suggesting minimal risk. Liver cancer risk was 0.0032 cases per 100,000 people per year. Weekly OTA exposure was 0.133 ng/kg BW, below PTWI (Provisional Tolerable Weekly Intake).

A Novel Autoencoder-Integrated Clustering Methodology for Inventory Classification: A Real Case Study for White Goods Industry

This article presents an inventory classification method that provides more accurate results in the white goods factory, which will contribute to sustainability, sustainability economics, and supply chain management targets. A novel inventory classification application is presented with real-world data. Two different datasets are used, and these datasets are compared to each other. These larger dataset is Stock Keeping Unit (SKU)-based (6.032 SKUs), and the smaller one is product-group-based (270 product groups). In the first phase, Artificial Intelligence (AI) clustering methods that have not been used in the field of inventory classification, to our knowledge, are applied to these datasets; the results are obtained and compared using K-Means, Gaussian mixture, agglomerative clustering, and spectral clustering methods. In the second stage, an autoencoder is separately hybridized with the AI clustering methods to develop a novel approach to inventory classification. Fuzzy C-Means (FCM) is used in the third step to classify inventories. At the end of the study, these nine different methodologies (“K-Means, Gaussian mixture, agglomerative clustering, spectral clustering” with and without the autoencoder and Fuzzy C-Means) are compared using two different datasets. It is shown that the proposed new hybrid method gives much better results than classical AI methods.

Algorithm aversion during disruptions: The case of safety stock

Algorithm aversion occurs when organizations or individuals reject optimal analytical decision support in favour of informal, subjective decisions. This phenomenon has been observed in many practical decision-making scenarios and is generally believed to negatively impact decision quality. However, its existence and effect in volatile supply chain environments has not been empirically tested in the literature. Safety stock buffering demand volatility is an important decision in supply chain management, making it an ideal lens to observe algorithm aversion. In this paper, we empirically investigate algorithm aversion behaviour in the context of safety stock settings. We collect data from a case retail company across a range of stockkeeping units (SKUs), encompassing both pre-disruption and post-disruption time stages with varying levels of volatility. We introduce a simulation model to determine whether algorithm aversion exists for safety stock decisions and to assess how algorithm adoption and adaptation affects performance. Our findings indicate that algorithm aversion occurs during supply chain disruptions, with algorithmic decisions significantly outperforming human judgment. Based on interview results and theories of information systems, we propose a theory to explain and generalize the above findings. This theory attributes algorithm aversion behaviour to reduced sense of fitness among algorithm users and lack of slack resources for both users and developers. It also offers insights into how the adoption and adaptation of algorithms influence decision performance during disruptive events.

How Retailers Change Ordering Strategies When Suppliers Go Direct

This study empirically investigates whether and to what extent suppliers’ decisions to start selling directly to end consumers provoke reactions in the ordering strategy of downstream channel partners, such as independent multibrand retailers. Using a multimethod approach that combines transactional data, survey data, and a scenario-based experiment, the authors demonstrate that retailers tend to exit these relationships after a direct channel introduction, as exhibited by their strategic decisions to order fewer distinct stockkeeping units (SKUs), accompanied by higher wholesale prices per unit. On average, retailers decrease the number of distinct SKUs ordered by 15 (or 18.75%) and pay a higher average wholesale price by €.79 (or 20.84%). Yet the responses also differ across retailers, reflecting moderating impacts of retailer power, expertise, and relationship quality. Retailer power emerges as a robust moderating factor, with more powerful retailers indicating a lower propensity to exit the relationship. Expertise and relationship quality have more nuanced influences on retailers’ ordering strategies. The multimethod approach serves to reveal the underlying mechanisms of these moderating effects, such that both rational (coercive power and switching costs) and emotional (conflict and confidence) considerations are in play.

Pesky Stock Keeping Unit (SKU) demand forecasting model for American Auto Parts Retailer

Pesky Stock Keeping Unit (SKU) demand forecasting model for American Auto Parts Retailer

One-Shot Learning from Prototype Stock Keeping Unit Images

This paper highlights the importance of one-shot learning from prototype Stock Keeping Unit (SKU) images for efficient product recognition in retail and inventory management. Traditional methods require large supervised datasets to train deep neural networks, which can be costly and impractical. One-shot learning techniques mitigate this issue by enabling classification from a single prototype image per product class, thus reducing data annotation efforts. We introduce the Variational Prototyping Encoder (VPE), a novel deep neural network for one-shot classification. Utilizing a support set of prototype SKU images, VPE learns to classify query images by capturing image similarity and prototypical concepts. Unlike metric learning-based approaches, VPE pre-learns image translation from real-world object images to prototype images as a meta-task, facilitating efficient one-shot classification with minimal supervision. Our research demonstrates that VPE effectively reduces the need for extensive datasets by utilizing a single image per class while accurately classifying query images into their respective categories, thus providing a practical solution for product classification tasks.

Smart customer service in unmanned retail store enhanced by large language model

In unmanned retail store, providing smart customer service requires two stages: understanding customer needs, and guiding the customer to the product. In this paper, we propose an end-to-end (Customer-to-Shelf) software service framework for unmanned retail. The framework integrates visual recognition technology to detect retail objects, large language models to analyze customer shopping needs and make proper recommendations. First, deep neural network based image recognition models are studied for implementing effective stock keeping units (SKUs) object recognition on the shelf. Second, a novel method is proposed to fine-tune large language models (LLMs) with limited training dataset. Metaheuristic approaches are used to optimize the mask locations in a low dimensional parameter space, resulting a more efficient parameter updating method for limited downstream data. Third, by facilitating an automatic analysis of customer preferences powered by large language models, we present a smart recommender system based on domain-specific knowledge, which completes the Customer-to-Shelf software service framework. Experimental results show that our proposed fine-tuning method, is more efficient than other state-of-the-art training methods for limited downstream domain dataset. Using fine-tuned large models, we can successfully create a seamless shopping experience for customers by understanding personalized needs and providing shopping advice in the unmanned retail store.

Impact of certification information on consumer behaviour in hybrid retail platforms: empirical evidence from JD.com

PurposeThis study aims to examine the impact of logistics and merchant certification information on consumer behaviour in hybrid retail platforms. Furthermore, it explores the moderating role of online shopping experience on the certification effect.Design/methodology/approachThe authors utilize transaction-level data from over 2.5 million consumers involving 30,000 stock keeping units (SKUs) on JD.com in March 2018. They analyse the impact of different types of certification information on consumer behaviour using ordinary linear regression and linear probability models.FindingsThe findings reveal that, compared with information without certification, (1) single logistics certification information can enhance consumers' search depth and purchase intention; (2) dual logistics and merchant certification information also has a positive impact on consumer behaviour; and (3) single certification information is more effective for inexperienced consumers, while dual certification is more effective for experienced consumers.Originality/valueTheoretically, this study contributes to the literature on certification information in hybrid retail platforms and broadens information communication methods for online shopping. Our discovery is meaningful for managers in locating customers and allocating resources. In addition, we encourage online retailers to utilize certification information to engage consumer.

Microbial assessment of commercial pet foods marketed in the United Arab Emirates

Examining the microbiological characteristics of pet food is imperative to safeguard the health and well-being of companion animals, pet owners, and the surrounding environment. Domestic animals, known for carrying harmful microorganisms, pose a significant health risk, especially in close proximity to people and children. Notably, no studies have previously investigated pet food quality in the Gulf Cooperation Council countries, in particular, the United Arab Emirates (UAE). This study examined the microbiological quality of all stock keeping units (SKUs) of pet foods marketed in UAE (n = 118). Parameters assessed include Total Aerobic Microbial Count (TAMC), Enterobacteriaceae, Total Yeast and Mold Count (TYMC), Salmonella, Listeria monocytogenes, and Clostridium species. Among the 118 samples, 33 (28%) exceeded the acceptable TAMC limit of 106 CFU/g, highlighting significant variations based on manufacturers and ingredients. Eight samples (7%) surpassed the maximum Enterobacteriaceae limit of 3 × 102 CFU/g. TYMC levels exhibited variation, with 33 (28%) exceeding the limit of 104 CFU/g. L. monocytogenes was identified in 44 (37%) of the samples, while Salmonella was not detected. Clostridium contamination was observed in 28 (24%) of the samples. Statistical analyses revealed associations between pet food characteristics and microbial quality, underscoring the imperative for international standards to ensure the safety of pet food. These findings carry significant implications for pet owners, regulatory bodies, and the pet food industry, emphasizing the need for ongoing efforts to enhance the overall quality and safety of pet food products.

Velocity-based rack storage location assignment for the unidirectional robotic mobile fulfillment system

Nowadays, the robotic mobile fulfillment system (RMFS) has been increasingly used by online retailers. Compared with traditional picker-to-parts warehouses, the racks of RMFS do not have to return to the same location after picking, thus we can dynamically change their locations, which brings great potential to efficiently fulfill orders. Aiming at minimizing the sum of rack travel distances, the key question is how to reassign a rack to an unoccupied storage location after picking items from the rack. However, the issue involves two challenges for unidirectional RMFS, one is that huge differences may exist between the classical Manhattan distance estimation and the actual distance for the unidirectional aisles in RMFS, and the other one is that we need to account for the frequency of rack moving for multi-item orders. We thus first propose closed-form formulas to optimally estimate the cycle travel distance for each rack. Then, by overcoming the repeated counting issue for multi-item orders, we propose a novel SKU (Stock Keeping Units)-correlation-based algorithm to choose high-velocity racks, which can better fulfill multi-item orders. Finally, embedding the cycle travel distance and SKU-correlation-based velocity, we propose a Velocity-based Rack Storage Location Assignment method (VRSLA) to solve the rack storage location assignment problem by assigning high-velocity racks to the nearest storage locations. Collaborating with a large online retailer in China, we demonstrate the performance of VRSLA by using both small-scale and large-scale datasets. The computational results show that VRSLA not only can achieve near-best solutions compared with an integer programming model solved by Gurobi, but also outperforms four state-of-the-art assignment methods in literature (random, velocity-based class, shortest path, and sale-based) by reducing the rack travel distance up to 43.32%. We also found that the stronger the correlation between SKUs on the racks or the larger the size of the RMFS, the shorter the rack travel distance by the proposed VRSLA method.

When time drives search effort: the effect of assortment variety on visual attention to SKU pricing

PurposeUnderstanding the effect of assortment composition on attentional levels is an essential topic for academic researchers and practitioners. This work has important implications when analyzing the influence of shopping frame time and search effort on the relationship between the reaction to assortment composition and visual attention to stock-keeping units (SKUs) pricing.Design/methodology/approachTwo experimental studies through gauze behavior analysis technology (using eye-tracking equipment) analyze the variable's large assortment, visual attention to SKU pricing, search effort and shopping frame time.FindingsThe results suggest that, although it increases the search effort, a large assortment decreases the visual attention to SKU pricing. Further, our results indicate a moderating effect associated with mitigating the negative effect by medium-low levels of search effort and a moderating impact of time in this relation.Practical implicationsMarketing professionals can carefully optimize the in-store experience by managing the assortment and variety and by influencing consumers' visual attention to SKU pricing along the journey as part of the experience. Assortment and SKU pricing strategies need to be aligned with consumer journey design.Originality/valueOur findings contribute to assortment theory and management by detailing the relationship between consumers' reactions to assortment perception and visual attention to SKU pricing in time flow. We reinforce the importance of considering assortment strategies from the consumer perspective and giving reliable information about in-store behavior.

A Data-driven Approach for Planning Stock Keeping Unit (SKU) in a Steel Supply Chain

In response to the growing complexities in supply chain management, there is an imperative need for a data-driven methodology aimed at optimizing inventory allocation strategies. The purpose of this research is to enhance the efficiency of allocation and operational scheduling, particularly concerning the stock keeping units (SKUs). To achieve this, one year's operational data from a specific organization's SKUs is taken and machine learning tools are employed on the data collected. These tools are instrumental in identifying clusters of SKUs that exhibit similar behaviour. Consequently, this research offers recommendations for rational inventory allocation strategies that are finely attuned to the unique characteristics of each SKU cluster. Results obtained reveals substantial disparities between the recommended strategies for the organization's SKUs and those typically found in the literature such as same strategy cannot be used for all different types for products. This underscores the critical importance of adopting a tailored approach to supply chain management. Furthermore, the research demonstrates the remarkable efficiency of unsupervised machine learning algorithms in determining the optimal number of segments within the SKUs. The current research differentiates from others in a way that in most of the research, the holistic data-driven approach is underutilized, right from the selection of the clustering algorithm to the validation of segments.

Fixing Inventory Inaccuracies at Scale

Problem definition: Inaccurate records of inventory occur frequently and, by some measures, cost retailers approximately 4% in annual sales. Detecting inventory inaccuracies manually is cost-prohibitive, and existing algorithmic solutions rely almost exclusively on learning from longitudinal data, which is insufficient in the dynamic environment induced by modern retail operations. Instead, we propose a solution based on cross-sectional data over stores and stock-keeping units (SKUs), viewing inventory inaccuracies as a problem of identifying anomalies in a (low-rank) Poisson matrix. State-of-the-art approaches to anomaly detection in low-rank matrices apparently fall short. Specifically, from a theoretical perspective, recovery guarantees for these approaches require that nonanomalous entries be observed with vanishingly small noise (which is not the case in our problem and, indeed, in many applications). Methodology/results: So motivated, we propose a conceptually simple entrywise approach to anomaly detection in low-rank Poisson matrices. Our approach accommodates a general class of probabilistic anomaly models. We show that the cost incurred by our algorithm approaches that of an optimal algorithm at a min-max optimal rate. Using synthetic data and real data from a consumer goods retailer, we show that our approach provides up to a 10× cost reduction over incumbent approaches to anomaly detection. Along the way, we build on recent work that seeks entrywise error guarantees for matrix completion, establishing such guarantees for subexponential matrices, a result of independent interest. Managerial implications: By utilizing cross-sectional data at scale, our novel approach provides a practical solution to the issue of inventory inaccuracies in retail operations. Our method is cost-effective and can help managers detect inventory inaccuracies quickly, leading to increased sales and improved customer satisfaction. In addition, the entrywise error guarantees that we establish are of interest to academics working on matrix-completion problems. History: This paper was selected for Fast Track in M&amp;SOM from the 2022 MSOM Supply Chain Management SIG Conference. Funding: Financial support from the National Science Foundation Division of Civil, Mechanical, and Manufacturing Innovation [Grant CMMI 1727239] is gratefully acknowledged. Supplemental Material: The online appendix is available at https://doi.org/10.1287/msom.2023.0146 .

International retail buying groups and consumer prices

The aim of the research described in this paper is to investigate the effect of international retail buying groups on consumer prices. The study focuses on EDEKA, the leading grocery retailer in Germany, and its membership in AgeCore, the largest European international retail buying group. The empirical analysis is based on an extensive EDEKA scanner dataset, including over 6 million observations of monthly consumer prices for 138,000 stock-keeping units (SKUs) across 20 food categories, over a six-year period. The analysis shows that EDEKA’s membership in AgeCore led to reduced prices for its customers. These findings are consistent with recent studies on the influence of retail buying groups on consumer prices and contribute to an increasing body of evidence that international retail buying groups reduce consumer prices. The paper shows that international buying groups are a force for the good, as they contribute to reduce consumer prices while simultaneously offering a cost-efficient mechanism for retailers to create scale to obtain competitive buying conditions.

Assessing the intention to adopt computational intelligence in interactive marketing

Interactive marketing (IM) can be used by e-commerce businesses to provide interactive and personalised experiences to e-customers by building sustainable relationships and delivering value. Computational intelligence (CI) is the ability of a machine to learn specific tasks via data or experimental observation for understanding and analysing customer behavioural patterns. Thus, this study explores how e-customers may intend to adopt CI in e-commerce within the boundaries of IM. Using online surveys, the primary data were collected from 315 e-customers of e-commerce businesses. Subsequently, the quantitative approach was used to analyse the data. The finding reveals that using a variety of techniques such as fuzzy logic, learning theory, evolutionary computation, genetic algorithms, and deep learning, CI predicts e-customer behaviour in a changing environment. Such a prediction results in desirable impacts, including more successful IM campaigns and retention actions. Further, CI uses a computational thinking approach, including the specification of the problem, algorithmic expression, solution implementation, and solution evaluation, for the identification and classification of stock-keeping units. This allows e-customers to compare the attributes of similar products.

Warehouse management optimization using a sorting-based slotting approach

Purpose: Slotting is one of the main operations in warehouse management. It is based on the efficient allocation of slots for stock-keeping units (SKUs). Order picking and slotting represent a high percentage of total logistics costs; therefore, improving these activities leads to significant savings in the overall performance. This paper aims to develop an allocation model integrating SKUs physical variables, warehousing design, and operation (dimensions, layout, material handling equipment), and heterogeneous product demand.Design/methodology/approach: The modeling methodology considers two phases. First, an integer linear programming model for warehousing spaces assignment for SKUs considering priority and required orders is developed. Then, the total operation times using different strategies are calculated.Findings: The effectiveness of the model was verified through simulation using historical data. The results showed that the best performance in the total time of the slotting operation is achieved by using the ABC as a criterion for the classification of the SKUs and by sequentially assigning the row, level, column, and the section.Practical implications: This approach can be adapted to different industrial sectors and serves as a basis for more robust models regarding the number of constraints or the incorporation of additional warehouse operating parameters.Originality/value: The most important contribution of this work is the development of a flexible and adaptable methodology to changes in the operation to improve the efficiency of storage management through slotting. Future work includes other objective functions of sustainable operations and uncertainty treatment techniques.

New product family demand planning: Addressing SKU‐level spread bias

AbstractNew product supply chain planning is challenging, primarily due to the lack of historical demand data. Rarely, however, do the academic literature or companies differentiate the demand forecasting process for new products from existing ones, despite their increased reliance on judgmental estimates. This research focuses on how judgmental errors lead to an under‐estimation of the difference between the highest‐ and lowest‐demand stock‐keeping units (SKUs), and consequently negatively impact supply chain planning for new product family introductions. A generalized empirical model and accompanying discrete event simulation are developed and applied to data from a major consumer packaged goods (CPG) firm during the launch of a new cosmetics product family. This application allows us to identify a focal type of judgmental error (identified as the SKU‐level spread bias) inherent to new product forecasting and to provide a new theoretical understanding of how this type of bias harms supply chain performance. Via an empirically driven theory‐building approach that iterates between the simulation outcomes and existing literature, SKU‐level spread bias is demonstrated to harm demand forecasts and, thereby, supply chain plans. Our unique theory‐building approach advances theory by identifying planner SKU‐level spread bias as a new source of bias that firms should seek to mitigate when introducing new product families.

Space efficiency and throughput performance in AVS/RS under variant lane depths

An automated vehicle storage and retrieval system (AVS/RS) is a widespread automated warehouse solution that hosts hundreds of stock-keeping units (SKU) and counts thousands of incoming and outgoing unit loads corresponding to a sequence of time-dependent storage and retrieval transactions. AVS/RS ensures high storage density, reduced cycle time, and high productivity. This study introduces and applies an original data-driven comparative and competitive multi-scenario methodology to measure and control the performance of a multi-deep tier-captive AVS/RS. This original methodology measures and controls the impact of lane depth (1), assignment strategy (2), opening strategy (3), and dispatching strategy (4) on the storage capacity, system throughput, and space efficiency in the design and configuration of an AVS/RS. The proposed methodology was applied to a real case study, demonstrating that the combination of the four leverages significantly affects system performance.

Gaining From Losing a Competition in Product Variety

This article studies the impact of a competing firm's substantial expansion in product variety, achieved through modularity and delayed differentiation, on the sales and inventory of the focal firm in the market. Intuitively, the firm's sales are expected to decrease when a competitor increases its product variety, as existing consumers are drawn to the greater range of competing products, resulting in a substitution effect. However, we also emphasize a simultaneous spillover effect, where the dramatic increase in a competitor's product variety can expand the overall market for all firms (including the focal firm) by attracting new consumers to the market. The net impact thus depends on the tradeoff between the substitution effect and spillover effect, forming an empirical question. To explore this tradeoff and quantify the net impact of a competitor's substantial increase in product variety on the focal firm's sales and inventory, we exploit the launch of Coca-Cola's Freestyle dispenser that offers over 120 beverage products via modularity and delayed differentiation. Our analysis focuses on the treatment effects of the launch of Freestyle on changes in the focal firm's sales quantity, sales dispersion, and inventory levels. Contrary to common intuition, we find that the focal firm's total sales remain unchanged following the launch of Freestyle dispensers, but its sales dispersion increases by 2.2%, which in turn leads to a 1.0% increase in inventory levels at distribution centers. The unchanged total sales and increased sales dispersion imply a redistribution of sales among the focal firm's stock keeping units (SKUs). By analyzing data at the SKU level and the business customer level, we uncover the mechanism behind this sales re-allocation: a 1.9% increase in the sales of the focal firm's long-tail products at the expense of its star product sales. Meanwhile, we identify a 0.9% increase in sales to retailers and entertainment locations, while sales to restaurants decline. These empirical results help disentangle the substitution and spillover effects on the focal firm's sales resulting from its competitor's substantially increased product variety. Managerial implications derived from these findings are discussed.

Machine Learning in Warehouse Management: A Survey

Warehouse design and planning involve complex decisions on receiving, storage, order picking and shipping products (i.e., stock-keeping units - SKUs) and can affect the performance of entire supply chains. With the advancement of Industry 4.0 and increased data availability, high-computing power, and ample storage capacity, Machine Learning (ML) has become an appealing technology to address warehouse planning challenges such as Storage Location Assignment Problems (SLAP) and Order Picking Problems (OPP) for intelligent warehousing management. This paper presents a state-of-the-art review of ML applied to Warehouse Management Systems (WMS) through the analysis of recent research application articles. A mapping to classify the scientific literature in this new research area, including ML methods, algorithms, data sources and use cases of ML-aided WMS, as well as further research perspectives and challenges, are introduced. Preliminary results suggest that the possible research areas in ML-WMS are still incipient and need to be further explored.