Assortment optimization presents a complex challenge for retailers, as it depends on numerous decision factors. Changes in assortment can result in demand redistribution with multi-layered consequences. This complexity is even more pronounced for omnichannel retailers, which have to manage assortments across multiple sales channels. Choice modeling has emerged as an effective method in assortment optimization, capturing customer shopping behavior and shifts in demand as assortments change. In this paper, we utilize the multichannel attraction model-a discrete choice model specifically designed for omnichannel environments-and generalize it for the case of a retailer managing both an online store and a network of physical stores. We integrate assortment decisions with optimal inventory decisions, assuming stochastic demand. Our model shows that overlooking the demand variability can result in suboptimal assortment decisions due to the demand pooling effect. We derive complexity results for the assortment optimization problem, which we formulate as a mixed-integer second-order cone program. We then develop two heuristic algorithms based on different relaxations of the formulated optimization problem. Furthermore, we conduct an extensive numerical analysis to provide managerial insights. We find that an increasing coefficient of variation of demand has a dual effect on optimal assortment sizes, initially causing a decrease in online assortment size due to rising costs, followed by an increase in online assortment size because of the demand pooling effect. Finally, we evaluate the potential benefits of omnichannel assortment optimization compared to assortment optimization in siloed channels.

In markets where customers tend to purchase baskets of products rather than single products, assortment optimization is a major challenge for retailers. Removing a product from a retailer's assortment can result in a severe drop in aggregate demand if this product is a complement to other products. Therefore, accounting for the complementarity effect is essential when making assortment decisions. In this paper, we develop a modeling framework designed to address this problem. We model customers' choices using a Markov random field – in particular, the Ising model – which captures pairwise demand dependencies as well as the individual attractiveness of each product. Using the Ising model allows us to leverage existing methodologies for various purposes including parameter estimation and efficient simulation of customer choices. We formulate the assortment optimization problem under this model and show that it is APX-hard. We also provide multiple theoretical insights into the structure of the optimal assortments based on the graphical representation of the Ising model, and propose several heuristic algorithms that can be used to obtain high-quality solutions to the assortment optimization problem. Our numerical analysis demonstrates that the developed simulated annealing procedure leads to an expected profit gain of 15

The supply chain risk management literature differentiates between disruption risk that arises from supply disruptions to normal activities and recurrent risk that arises from problems in coordinating supply and demand in the absence of disruptions. Over the past decades, significant research has been carried out to better understand supply chain resilience, that is, the ability of a supply chain to mitigate disruptions. Supply chain efficiency, that is, the ability to mitigate recurrent risks in the absence of disruptions has been studied even longer. But only recently have the topics of efficiency and resilience been coupled in the supply chain literature. In this literature review, we focus on the intersection of supply chain resilience and supply chain efficiency. We provide a thematic overview of literature streams according to the structure of the underlying supply chains. We identify various gaps in the current literature including areas in multi-echelon and multi-product supply chain research. Furthermore, we consider dual-purpose and dedicated levers for building resilience. Dual-purpose levers are resources that are able to promote efficiency in a supply chain while enhancing resilience in expectation. By contrast, dedicated resilience levers are resources that are able to guarantee the resilience of a supply chain in the face of particular disruptions without benefiting the supply chain in the absence of disruptions. We call for more research to better understand the value of dual-purpose and dedicated resilience levers to overall supply chain performance.

Making assortment decisions is becoming an increasingly difficult task for many retailers worldwide as they implement omnichannel initiatives. Discrete choice modeling lies at the core of this challenge, yet existing models do not sufficiently account for the complex shopping behavior of customers in an om-nichannel environment. In this paper, we introduce a discrete choice model called the multichannel at-traction model (MAM). A key feature of the MAM is that it specifically accounts for both the product substitution behavior of customers within each channel and the switching behavior between channels. We formulate the corresponding assortment optimization problem as a mixed integer linear program and provide a computationally efficient heuristic method that can be readily used for obtaining high-quality solutions in large-scale omnichannel environments. We also present three different methods to estimate the MAM parameters based on aggregate sales transaction data. Finally, we describe general effects of the implementation of widely-used omnichannel initiatives on the MAM parameters, and carry out nu-merical experiments to explore the structure of optimal assortments, thereby gaining new insights into omnichannel assortment optimization. Our work provides the analytical framework for future studies to assess the impact of different omnichannel initiatives. (c) 2022 The Author(s). Published by Elsevier B.V. This is an open access article under the CC BY license ( http://creativecommons.org/licenses/by/4.0/ )

Demand forecasting is becoming increasingly important as firms launch new products with short life cycles more frequently. This paper provides a framework based on state-of-the-art techniques that enables firms to use quantitative methods to forecast sales of newly launched, short-lived products that are similar to previous products when there is limited availability of historical sales data for the new product. In addition to exploiting historical data using time-series clustering, we perform data augmentation to generate sufficient sales data and consider two quantitative cluster assignment methods. We apply one traditional statistical (ARIMAX) and three machine learning methods based on deep neural networks (DNNs) – long short-term memory, gated recurrent units, and convolutional neural networks. Using two large data sets, we investigate the forecasting methods' comparative performance and, for the larger data set, show that clustering generally results in substantially lower forecast errors. Our key empirical finding is that simple ARIMAX considerably outperforms the more advanced DNNs, with mean absolute errors up to 21%–24% lower. However, when adding Gaussian white noise in our robustness analysis, we find that ARIMAX's performance deteriorates dramatically, whereas the considered DNNs display robust performance. Our results provide insights for practitioners on when to use advanced deep learning methods and when to use traditional methods.

Ranking algorithms play a crucial role in information technologies and numerical analysis due to their efficiency in high dimensions and wide range of possible applications, including internet ranking, scientometrics, and systemic risk in finance (SinkRank and DebtRank). The traditional approach to internet ranking goes back to the seminal work of Sergey Brin and Larry Page, who developed the initial method PageRank (PR) in order to rank websites for search engine results based on linear algebra rules. But how robust is this method in times of rapid internet growth? Recent works have studied robust reformulations of the PageRank model for the case when links in the network structure may vary; that is, some links may appear or disappear, influencing the transportation matrix defined by the network structure. In this article, the authors make a further step forward, allowing the network to vary not only in links but also in the number of nodes. The authors focus on growing network structures and develop methods for ranking of networks uncertain both in size and in structure.

Years of globalization, outsourcing and cost cutting have increased supply chain vulnerability calling for more effective risk mitigation strategies. In our research, we analyze supply chain disruptions in a production setting. Using a bilevel optimization framework, we minimize the total production cost for a manufacturer interested in finding optimal disruption mitigation strategies. The problem constitutes a convex network flow program under a chance constraint bounding the manufacturer’s regrets in disrupted scenarios. Thus, in contrast to standard bilevel optimization schemes with two decision-makers, a leader and a follower, our model searches for the optimal production plan of a manufacturer in view of a reduction in the sequence of his own scenario-specific regrets. Defined as the difference in costs of a reactive plan , which considers the disruption as unknown until it occurs, and a benchmark anticipative plan , which predicts the disruption in the beginning of the planning horizon, the regrets allow measurement of the impact of scenario-specific production strategies on the manufacturer’s total cost. For an efficient solution of the problem, we employ generalized Benders decomposition and develop customized feasibility cuts. In the managerial section, we discuss the implications for the risk-adjusted production and observe that the regrets of long disruptions are reduced in our mitigation strategy at the cost of shorter disruptions, whose regrets typically stay far below the risk threshold. This allows a decrease of the production cost under rare but high-impact disruption scenarios.

Additive manufacturing (AM), originally used for prototyping, is increasingly adopted for custom final part production across different industries. However, printing speed and production volume are two barriers for the adoption of AM for product customization at large scale. Nevertheless, manufacturers could aim to combine the benefits of AM for product customization with traditional mass customization (MC) technologies over the product life cycle (PLC). This approach is showcased in our paper as a manufacturing opportunity and is addressed via a non convex-concave optimization model that considers a monopolist manufacturer producing horizontally differentiated products at scale. To satisfy individual customer preferences under capacity considerations, the firm jointly decides on the inventory, production quantity, product variety, optimal technology-switching times (between AM and MC) and pricing strategy. Our approach can be implemented by decision-makers to leverage customer-centricity and benefit from this novel hybrid manufacturing practice. By deriving a closed-form solution for the production quantity based on an adaptive inventory policy, the resulting optimization problem is solved using the Sample Average Approximation framework grounded by analytical results. Our results demonstrate that the new usage of AM with MC can benefit a manufacturer for customer-centric driven strategies. Significant profit improvements can be achieved with an AM–MC–AM technology-switching scenario under certain capacity conditions and with an increasing-decreasing pricing strategy. Our results also indicate that the benefits of pricing flexibility are highest when capacity is unlimited or when the firm does not hold inventory. Under capacity constraints, a simple decreasing pricing policy combined with inventory performs very well.

Service‐level requirements play a crucial role in eliminating stock‐outs in a production pipeline. However, delivering a specific service level can become an unattainable goal given the various uncertainties influencing both the production pipeline and customer demand and causing the manufacturer to adapt the initial strategy in response to disruptions. Such deviations from optimality frequently result in unexpected (and potentially very high) costs and are complex to manage. On the one hand, the manufacturer can use a robust or distributionally robust approach to prepare for the worst‐case disruption, ensuring that the realized cost will be lower than the estimated cost with high probability. On the other hand, this solution may lead to overly conservative production schedules. In this article, we take a different approach and develop a bilevel stochastic optimization model with chance constraints, which allows us to make the production more predictable in the event of disruptions by driving costs and optimal schedules closer to the benchmark for each scenario considered. We introduce doubly probabilistic service‐level requirements to account for two interdependent layers of uncertainty, that is, production disruptions and distributional uncertainties in customer demand. This allows us to make high‐quality production decisions with only a limited understanding of the demand pattern. Approximating the problem for a numerical solution, we guarantee tight optimality gaps for high service levels and propose an efficient solution scheme, combining robust scenario reduction with a customized Benders decomposition procedure. In the managerial section, we use the Omega× Swatch MoonSwatches example to demonstrate that a desirable doubly probabilistic service level can be attained for disruptions with a drop in demand. In the case of disruptions followed by a peak in demand, one can tighten the optimality gaps if the service level is reduced.

We analyze the environmental benefits of operational flexibility that emerge in the form of less product waste during the sourcing process by reducing overproduction. We consider three different options for operational flexibility: (1) lead-time reduction, (2) quantity-flexibility contracts, and (3) multiple sourcing. We use a multiplicative demand process to model the evolutionary dynamics of demand uncertainty. We then quantify the impact of key modeling parameters for each operational-flexibility strategy on the waste ratio, which is measured as the ratio of excess inventory when a certain operational-flexibility strategy is employed to the amount when an offshore supplier is utilized without any operational flexibility. We find that the lead-time reduction strategy has the maximum capability to reduce waste in the sourcing process of buyers, followed by the quantity-flexibility and multiple-sourcing strategies, respectively. Thus, our results indicate that operational-flexibility strategies that rely on the localization of production are key to reducing waste and improving environmental sustainability at source.

Spoilage reduction in fresh product supply chains is an important challenge and represents great opportunities for cost savings and reduced environmental and social footprints. The purpose of this paper is to identify the drivers of spoilage and to discuss how these insights can be used to reduce spoilage.We use panel data techniques to quantify the drivers of spoilage in the days-fresh category using daily spoilage and supply chain data (457,539 store-SKU level observations) for fresh fruits and vegetables at Switzerland's largest retailer. We quantify to what extent inventory, promotions, delivery type, commitment changes, order variations, order cycle, and quality issues influence spoilage. We discuss the mechanisms through which inventory age and product standards impact spoilage of days-fresh products. Our novel findings underline the necessity for specialized supply chain processes, tracking inventory age and damage, and collaboration with supply chain partners in the management of this fundamental product category.

Additive manufacturing (AM) was initially designed for prototyping and product personalization, where high production quantities were not required. Now, it is also implemented for final part production to achieve cost-effective mass customization (MC). Thanks to its tool-less production and extreme flexibility, AM has the potential to address individual customer preferences with custom final parts. Nevertheless, despite its increased competitiveness, AM is not yet likely to replace traditional MC systems, but it can complement them, improving manufacturing efficiency. To broaden our understanding of how AM can complement traditional manufacturing systems, we develop an exploratory quantitative model. First, we leverage customer-centricity in a novel time-varying locational choice model of heterogeneous customers, coupling the Bass and the Hotelling-Lancaster models. Then, we investigate customer-centric marketing and operations decisions, exploring technology-switching scenarios that interchange AM with MC across the product life cycle (PLC). We formulate and solve an optimization problem by jointly deciding on technology-switching times, pricing, and product variety strategies to maximize a manufacturer's profit and meet individual customers' diverse and evolving needs. We use a validated Sample Average Approximation approach for the numerical solution of our non-convex optimization problem. Testing different pricing strategies, we show that decreasing and flexible trajectories are optimal. We derive analytical properties for the optimal pricing policy and demonstrate that a manufacturer can benefit from interchanging AM and MC across the PLC, in particular by adopting an AM-MC-AM scenario.

We focus on the optimal use of risk mitigation inventory (RMI) and reserve capacity to manage disruption risk in serial multi‐stage supply chains where product transformation occurs at each stage. We find that under reasonable conditions it is better to hold more RMI downstream than upstream even when the upstream holding costs are lower. We also find that it is often optimal to hold more reserve capacity downstream than upstream. While in one‐stage supply chains RMI and reserve capacity always behave as substitutes, it turns out that in multi‐stage serial supply chains the interplay between RMI and reserve capacity is more nuanced. We find that echelon RMI and reserve capacity at each stage are substitutes. In contrast, RMI at a stage complements reserve capacity at the adjacent downstream stage.

Assortment planning deserves much attention from practitioners and academics due to its direct impact on retailers' commercial success. In this paper we focus on the increasingly popular retail practice to use combined product assortments with both "standard" and more fashionable and short-lived "variable" products for building up store traffic of "loyal" and "non-loyal" heterogeneous customers and enlarging the sales due to the potential cross-selling effect. Addressing the assortment planning as a bilevel optimization problem, we focus on decision-dependent uncertainties: the retailer's binary decision about product inclusion influences the distribution of the product's demand. Furthermore, our model accounts for customers' optimal purchase quantities, which depend on budget constraints limiting the basket that a customer is able to purchase. We propose iterative heuristics using optimal quantization of demand and customers budget distributions to define the total assortment and the inventory level per product. These heuristics provide lower bounds on the optimal value. We conduct a comparison to other existing lower bounds and we formulate upper bounds via linear (LP) and semidefinite (SDP) relaxations for the performance evaluation of the heuristics and for an efficient numerical solution in high-dimensional cases. For managerial insights, we compare the proposed approach with three assortment planning strategies: (1) the retailer does not carry variable products; (2) the retailer ignores the cross-selling effect; and (3) the maximum space allocated to each product is fixed. Our results suggest that variable assortment boosts the retailers profits if the cross-selling effect is not neglected in the decision about products quantities. (C) 2020 The Authors. Published by Elsevier B.V.

This research focuses on managing disruption risk in supply chains using inventory and reserve capacity under stochastic demand. While inventory can be considered as a speculative risk mitigation lever, reserve capacity can be used in a reactive fashion when a disruption occurs. We determine optimal inventory levels and reserve capacity production rates for a firm that is exposed to supply chain disruption risk. We fully characterise four main risk mitigation strategies: inventory strategy, reserve capacity strategy, mixed strategy and passive acceptance. We illustrate how the optimal risk mitigation strategy depends on product characteristics (functional versus innovative) and supply chain characteristics (agile versus efficient). This work is inspired from a risk management problem of a leading pharmaceutical company.

Process industries operate in commodity markets with low product variety, little product differentiation, and highly capital-intensive manufacturing. Because prices are volatile and demand is uncertain, manufacturing capabilities become the main strategic competitive lever. The purpose of this paper is to evaluate the interplay between market conditions, capital expenditure, manufacturing flexibility, and production capacity to effectively analyze the consequences of manufacturing investments in both the short and the long terms. In order to achieve this, we developed an econometric model linking market conditions and operational decisions. We tested the model on a sample of 480 firms from the mining sector and 1053 firms from the oil and gas sector. The results show that firms in process industries follow the market with their investments, which impacts their operations in the short term as well as their capacity growth in the long term. Additionally, from our findings, we propose a firm value driver model that managers could consider when deciding on capital expenditures. Finally, our results indicate that the managers of financially healthy companies should resist the stock market's short-term pressure to reduce fixed costs and instead play the long game.

We consider a two-echelon supply chain with an upstream manufacturer and a downstream retailer for a single perishable product. The manufacturer processes raw materials into finished products, which are purchased by the retailer in each replenishment cycle. The raw materials of the manufacturer are highly perishable (i.e. perishing within hours or days), and the finished goods at the retailer face demand uncertainty and obsolescence. We model the manufacturer–retailer relationship as a Stackelberg game where the retailer is the leader and decides the replenishment cycle that minimises its mismatch cost between supply and uncertain demand. The manufacturer is the follower and decides its processing rate to minimise its unit cost for finished goods. Our results show that the raw material and finished goods lifetimes, which are interrelated through the duration of the replenishment cycle, have a significant impact on supply chain costs. Although raw material spoilage cost by itself is low, we show that short raw material lifetimes have a significant impact on the costs of both parties. Additionally, we find that while high manufacturer markups increase retailer costs, they reduce the manufacturer's costs due to large production batches.

We focus on the optimal use of risk mitigation inventory (RMI) and reserve capacity to manage disruption risk in serial multi-stage supply chains where product transformation occurs at each stage. We find that under reasonable conditions it is better to hold more RMI downstream than upstream even when the upstream holding costs are lower. We also find that it is often optimal to hold more reserve capacity downstream than upstream. While in one-stage supply chains RMI and reserve capacity always behave as substitutes, it turns out that in multi-stage serial supply chains the interplay between RMI and reserve capacity is more nuanced. We find that echelon RMI and reserve capacity at each stage are substitutes. In contrast, RMI at a stage complements reserve capacity at the adjacent downstream stage.

Process industry firms have thrived in recent decades, but changes in the markets are currently putting both growth and profitability at risk. In this context, inventory management is increasingly viewed as an essential lever for creating a sustainable competitive advantage. Despite this, many firms struggle to implement best practices because of industry-specific constraints. This research explores how seven fundamental characteristics of process industries drive inventory performance. We empirically investigate four process industries and four peer industries, using financial accounting, credit rating, stock market and trading data and implement a seemingly unrelated regression (SUR) equations model. Our results show that capital intensity, capital costs, transportation costs, delivery time, price volatility, demand uncertainty and gross margin directly affect a company's degree of freedom in terms of inventory management and illustrate that inventory management in process industries follows different dynamics. This study enhances the understanding of inventory drivers and gives practitioners a tool to guide future improvement efforts.