Newsvendor Research Articles

Supply Chain Performance with a Downside-Risk-Averse Retailer and Strategic Customers

Predicting future promotion information on markdowns, customers can maximize their utilities by deciding when to buy. With this strategic behavior, this paper investigates a downside-risk-averse retailer’s integrated stock and pricing problem using a single case study method. Analyzing effects of the downside risk aversion and strategic customers is our purpose. By exploring a two-phase newsvendor model with a retailer selling to strategic customers, our work determines the downside-risk-averse retailer’s equilibrium ordering level and selling price. On this basis, effects of the downside risk aversion and the strategic behavior on the retailer’s optimum decisions and profit are analyzed. We find that the reverse effect of the strategic behavior can be mitigated by the retailer’s downside risk constraint. We also extend the model to a decentralized supply chain case. It is found that a low (high) downside risk aversion would mean that the supply chain profit in the decentralized case can (cannot) dominate the centralized under some (any) wholesale price contracts when customers are strategic. In addition, for different risk aversions, we also construct contracts to optimize the supply chain profit. Our results will provide reference evidence of making operational management decisions for the downside-risk-averse retailer in the case of strategic customers.

Inventory competition on electronic marketplaces – A competitive newsvendor problem with a unilateral sales commission fee

We present a competitive newsvendor problem with a sales commission paid by one newsvendor to another newsvendor when selling a product. Customer demand is stochastic, and customers individually decide with given probabilities from which newsvendor they want to order or whether they do not want to order at all. These probabilities can vary depending on which newsvendor is out of stock. The problem described arises when marketplace operators offer the same or substitutable products as third-party vendors and therefore directly compete with third-party vendors on their platform. Our research is motivated by practical cases such as the Amazon marketplace, where Amazon is the marketplace operator that sets the sales commission and, simultaneously, directly competes with third-party vendors. Both the marketplace operator and a competing third-party vendor should ideally account for the other party's behavior when deciding their order quantity. We calculate the noncooperative Nash equilibrium and the optimal cooperative order quantities (centralized solution). Additionally, we emphasize analyzing the effect of the sales commission on the optimal order quantities and the gross profits of the two parties.

Don't waste that free lettuce! Impact of BOGOF promotions on retail profit and food waste

Buy‐one‐get‐one‐free (BOGOF), a ubiquitous sales promotion scheme by which consumers get two items for the price of one, encourages consumers to buy and waste food. An alternative promotional scheme is one where consumers receive a coupon for a second item available for free at a later time. Our work is motivated by British supermarkets which, facing criticism from lawmakers for running BOGOF promotions on perishables, started a “BOGOF Later” campaign with the claim that it would reduce the amount of waste. Food waste is indeed a very pressing issue, which has not yet been explored in connection to sales promotions. We compare the impact of these promotion schemes on a retailer's profit as well as on the amount of product wasted at the retail and household levels. We consider two possible applications: unexpected high inventory of a fresh product with a short shelflife and excess leftover inventory for an item at the end of its season or product life. We propose a two‐period newsvendor model which captures the sales‐boosting effect of promotions, the postpromotion sales drop due to satiation, the coupon‐redemption behavior, and the increased consumer wastage rate from BOGOF promotions. We obtain analytical comparisons of order quantity, profit, and waste across the different promotion schemes and use numerical experiments to generate further insights. We find that, in general, BOGOF promotions are profitable ways to liquidate inventory. In many instances, the increase in waste at the consumers' homes is offset by the decrease in waste at the retail store. As a result, BOGOF promotions often constitute “win‐win propositions” by simultaneously increasing the retailer's profit and decreasing total waste. Overall, our results paint a more favorable picture of the BOGOF promotion scheme than commonly perceived and suggest that its environmental criticism emanates from a too narrow and too consumer‐centric view of the waste problem.

Optimizing price, order quantity, and return policy in the presence of consumer opportunistic behavior for online retailers

Product return rates are much higher for online retailers than brick-and-mortar retailers. In this paper, we develop a model for optimizing the retailer’s price, quantity, and terms of the product return policy in the presence of consumer opportunistic behavior (wardrobing). We consider a seasonal product and formulate and solve a newsvendor (e-tailer) model where an in-season price markdown may be used before any remaining inventory is salvaged at the end of the season. We compare a return policy in which refunds for returned products are in cash to one where refunds are in store credit or gift cards (SC/GC). Products sold at the clearance (salvage) price cannot be returned or exchanged. We find that with both cash and SC/GC refunds, consumer product match uncertainty, measured by the probability of the product matching consumers’ expectations, benefits consumers who keep the product more than consumers who return it. Moreover, under realistic conditions, using SC/GC refund increases the profits of the e-tailer and benefits consumers who keep the product by lowering the price. We also find that even when consumers redeem all SC/GC, using SC/GC refunds can still be beneficial to the retailer because SC/GC refunds deter proportionally more wardrobers from buying than consumers from buying. As a result, costly returns are reduced and the e-tailer benefits.

Newsvendor model with voucher sales: a distributionally robust approach

AbstractVouchers as a popular short‐term marketing tool are widely used by many firms, through which retailers can lock in customers and obtain working capital in advance. Consumers can use the voucher to reduce the product purchase price to an equal face value or purchase the product at a discount. We apply the classical newsvendor model to study the merits of vouchers for the retailer's ordering decision in the face of uncertainties in both the market demand and voucher redemption rate. We propose a distributionally robust approach to solve this newsvendor problem. The approach only requires the first and second moments of the demand and redemption rate distributions and yields a lower bound on the expected profit. Specifically, we derive the optimal ordering decision in closed form and obtain the optimal expected profit based on the limited distribution information. We find that a higher redemption rate does not necessarily increase the retailer's profit and the voucher quantity, but always increases the retailer's order quantity. Interestingly, we show that when the buyback price of the voucher is relatively high, increasing the voucher redemption rate is more profitable for the retailer. In addition, the retailer's profit, and the quantities of the product and the voucher decrease with the buyback price of the voucher.

A new data-driven robust optimization approach to multi-item newsboy problems

<p style='text-indent:20px;'>A newsboy problem is a typical stochastic inventory management problem and has extensive applications in the fields of operational research, management sciences and marketing sciences. One of the challenges underlying such problems is to handle the uncertainty of demands. In the existing results, it is often to assume that the demand distribution is given to facilitate solution of the problems. In this paper, a novel data-driven robust optimization model for solving multi-item newsboy problems is proposed by combining the absolute robust optimization with a data-driven uncertainty set, and the latter is leveraged to address the uncertainty of demands. For the single-item situation, a closed-form solution is obtained and influences of parameters on the optimal solutions are analyzed. Owing to complexity of the multi-item situation, a uniform smoothing function is leveraged to smooth the proposed model. Then, an algorithm, called a modified Frank-Wolfe feasible direction algorithm, is developed to solve a series of smooth subproblems. Numerical simulation demonstrates that the proposed model in this paper can reduce over-conservation of robust optimization methods and is more robust than other similar well-established methods in the literature. By numerical simulation and sensitivity analysis, it is concluded that: (1) The proposed method can provide more stable optimal order policy and profits than the existing ones; (2) For a product with a higher unit purchase price, the optimal order quantities are more sensitive to its change; (3) In view of profitability, the newsboy should not to be too risk-averse.</p>

Newsvendor Problem and Forecasting based on Past Data

Newsvendor Problem and Forecasting based on Past Data

A new model to design the suppliers portfolio in newsvendor problem based on product reliability

<p style='text-indent:20px;'>Suppliers' selection problem has always been daunting challenges in the Newsvendor problem. Furthermore, since the failures in the supplier's products cause irreparable damage to the retailer, it is necessary to consider the reliability of products in ordering suppliers' products. This paper develops the Newsvendor model by considering the impactful criteria in supplier selection and product reliability so that the total cost of the chain is minimized in a multi-product and multi-period model with multiple suppliers. While multiple criteria decision making (MCDM) accounts for multiple criteria and their tradeoffs, its application in Newsvendor model is not considered. This paper applies the Bayesian best worst method (BWM), as one of the MCDM methods, for ranking criteria and the fuzzy technique for order of preference by similarity to ideal solution (TOPSIS) for prioritizing the suppliers. Then, the obtained weights are plugged into the model as the inputs of the designed model. A case study with real data in the electronic supply chain is considered. To validate the results obtained by the proposed method, genetic algorithm (GA) and particle swarm optimization (PSO) are leveraged to solve the proposed model. Finally, the efficiency of the designed model is verified through a case study.</p>

The opportunistic newsvendor problem: Defining the optimal purchase quantity of resalable items, whose value may appreciate

With Newsvendor Problem (NvP) we refer to a specific class of inventory management problems, valid for a single item with stochastic demand over a single period. In the standard version, the newsvendor is allowed to issue a single order, before he or she can observe the actual demand. Since the newsvendor can face both overage and underage costs, due to lost sales or residual stock, the objective is to define the optimal order size that maximizes the expected profit. In this paper, we consider a specific version of the NvP, in which the buyer has the opportunity to make a last and single order for opportunistic reasons. Specifically, we consider discontinued, collectible items, for which demand will not vanish and whose value might appreciate. Hence, the objective is to define the optimal quantity that should be purchased, just before the item is retired from the market or sold-out, and that should be sold as soon as the price rises over a predefined target level. An optimal solution, maximizing the expected profit, is obtained both in case of negligible and non-negligible stockholding costs. In the latter case, to obtain the optimal solution in implicit form, some simplifying assumptions are needed. Hence, a thorough numerical analysis is finally performed, as a way to empirically demonstrate both the robustness and the accuracy of the model, in several scenarios differentiated in terms of costs and customers’ demand.

Asymmetric loss function in product-level sales forecasting: An empirical comparison

In the paper we study the behavior of models estimated using asymmetric loss function for the prediction of product‐level sales. The paper is focused on the deriving of a loss function from the newsvendor model where the cost of sales over‐ and underprediction are not equal. We describe the properties of the asymmetric loss function and validate its performance on transactional sales data. The results show that when costs of sales over‐ and underprediction are non‐equal, the prediction function obtained using asymmetric loss leads to lower economic costs compared with symmetric one. Our findings suggest implementing this type of forecasting method to predict product‐level sales in the retail and restaurant industries to better accommodate business goals when solving inventory planning tasks.

Decision-making and sub-coordination in a newsvendor model with a third party logistics service provider

Decision-making and sub-coordination in a newsvendor model with a third party logistics service provider

Mean-variance analysis of sustainable newsvendor problems with stochastic demand under cap-and-trade policy

Mean-variance analysis of sustainable newsvendor problems with stochastic demand under cap-and-trade policy

A comparative study to find the optimal ordering quantity of the risk-neutral and risk-averse newsvendor

In the classical newsvendor problem, it is considered that the newsvendor is risk-neutral and the Optimal Ordering Quantity (OOQ) was found which maximizes the newsvendor expected profit. In the real world, different investors have different attitudes towards risk. Accordingly, this paper considers the utility function which is commonly being used to model the attitude of the investor who makes the investment decision to maximize his expected utility instead of expected profit. This study considers the quadratic utility function and demonstrates that it can be used to describe the riskaverse as well as a risk-neutral investor with some conditions. Finally, by considering the risk profile of the investor at different levels of investor initial wealth, we have developed a method to determine the OOQ which maximizes the expected utility. From the numerical examples, it is clear that the OOQ and hence the expected utility varies depending on an investor?s attitude toward the risk and investment decision. At different levels of initial wealth, the attitudes toward the risk of the investors are different and the sensitivity analysis demonstrates how an investor can choose the initial wealth and OOQ to maximize his expected utility.

A knapsack approach to solving the capacitated newsvendor problem

A knapsack approach to solving the capacitated newsvendor problem

Competitive strategies for two-product, multi-period stationary newsvendor problem with budget constraint

In this paper, we study a two-product, multi-period stationary newsvendor problem with budget constraint. In the problem, the inventory of each product is not allowed to be carried between one period and another. At the beginning of each period, the newsvendor has to determine the order quantities of the two products with budget constraint. We apply the weak aggregating algorithm (WAA) to study this problem. WAA, developed in the field of computer science, is a competitive online prediction method of combining expert opinions. By regarding each fixed stock level as an expert opinion and updating its weight according to the cumulative loss it achieves, we first provide an online ordering strategy to decide each period's order quantity. Furthermore, we theoretically prove that this online ordering strategy possess competitive property, i.e., the cumulative loss it achieves is as small as that achieved by the optimal expert. The salvage value and stock-out cost are further considered to obtain extended results. Finally, the numerical analysis illustrates that the online ordering strategies proposed in this paper are competitive whether with or without salvage value and stock-out cost.

Additional-Ordering Newsvendor Model Based on CVaR Criterion and Lost Sale Penalty Cost

Additional-Ordering Newsvendor Model Based on CVaR Criterion and Lost Sale Penalty Cost

Channel structures of transnational supply chains

<p style='text-indent:20px;'>There are two fundamental and important problems for enterprises with an existing domestic supply chain: whether to build a new transnational supply chain and which channel should be chosen to build the new transnational supply chain. In this paper, we assume that the enterprise's existing domestic supply chain structure and the transnational supply chain structure to be considered are likely to be distributor channels and direct sales channels. By considering different channel scenarios at home and abroad, we establish a robust newsvendor model with profit maximization motivation to study the above-mentioned problems. We find that exchange rate risk and foreign price are key factors that determine whether an enterprise chooses to build a new transnational supply chain. However, the channel preference of enterprises when constructing transnational supply chains depends not only on exchange rate risk and foreign price, but also on the drive of foreign demand attributes (demand scale and demand uncertainty). We also find that enterprises have a humanitarian "principle of equality" when considering the construction of transnational supply chains <inline-formula><tex-math id="M1">\begin{document}$ - $\end{document}</tex-math></inline-formula> the operational characteristics and channel structure of domestic supply chains will not affect whether and how enterprises build a new transnational supply chain.</p>

When Yield is Not the Only Supply Uncertainty: Newsvendor Model of a Trade Agent

When Yield is Not the Only Supply Uncertainty: Newsvendor Model of a Trade Agent

Distributionally Robust Newsvendor Model for Fresh Products under Cap-and-Offset Regulation

The cap-and-offset regulation is a practical scheme to lessen carbon emissions. The retailer selling fresh products can adopt sustainable technologies to lessen greenhouse gas emissions. We aim to analyze the optimal joint strategies on order quantity and sustainable technology investment when the retailer faces stochastic market demand and can only acquire the mean and variance of distribution information. We construct a distributionally robust optimization model and use the Karush-Kuhn-Tucker (KKT) conditions to solve the analytic formula of optimal solutions. By comparing the models with and without investing in sustainable technologies, we examine the effect of sustainable technologies on the operational management decisions of the retailer. Finally, some computational examples are applied to analyze the impact of critical factors on operational strategies, and some managerial insights are given based on the analysis results.

An Open-Source Intelligence-Driven Analysis of International Students’ Blended Learning in China

This paper examines the management of international students’ online blended learning based on a comprehensive analysis through open-source intelligence and data mining of associated discourses. This work reconstructs the assessment model of the online blended learning effect for overseas students and rebalances the process of this educational experience, leading to the forecast of China’s strategic manoeuvres through the lenses of the newsboy model and game theory. This study concludes with three suggestions: boosting the entire experience via scaled growth, enhancing and preventing resilience, and reaching out to a third party for skills reinforcement.