Target Inventory Level Research Articles

METHODS FOR ANALYZING THE EFFECTIVENESS OF INFORMATION SYSTEMS FOR INVENTORY MANAGEMENT

Context. Information systems for inventory management are used to forecast, manage, coordinate, and monitor the resources needed to move goods smoothly, in a timely, cost-effective, and reliable manner. The more efficiently the system works, the better results a company can achieve. A common problem with existing performance measurement methods is the difficulty of interpreting the relationship between performance indicators and the factors that influence them. Objective. The purpose of the study is to describe a method for evaluating the effectiveness of information systems, which allows to establish a link between performance indicators and factors that influenced these indicators. Method. A set of indicators characterizing the effective operation of inventory management information systems is proposed. The rules for quantifying the factors that influence the performance indicators are proposed. The factors arise during events that affect the change in order, delivery, balance, target inventory level, parameters of the forecasting algorithm, etc. The proposed method performs an iterative distribution of the quantitative value of factors among performance indicators and thus establishes the relationship between performance indicators and factors. Results. The implementation of the proposed method in the software was carried out and calculations were made on actual data. Conclusions. The calculations carried out on the basis of the method have demonstrated the dependence of performance indicators on factors. The use of the method allows identifying the reasons for the decrease in efficiency and making the company’s management more efficient. Prospect for further research may be to detail the factors, optimize software implementations, and use the method in inventory management information systems in various areas of activity.

A Minibatch Stochastic Gradient Descent-Based Learning Metapolicy for Inventory Systems with Myopic Optimal Policy

Stochastic gradient descent (SGD) has proven effective in solving many inventory control problems with demand learning. However, it often faces the pitfall of an infeasible target inventory level that is lower than the current inventory level. Several recent works have been successful in resolving this issue in various inventory systems. However, their techniques are rather sophisticated and difficult to apply to more complicated scenarios, such as multiproduct and multiconstraint inventory systems. In this paper, we address the infeasible target inventory-level issue from a new technical perspective; we propose a novel minibatch SGD-based metapolicy. Our metapolicy is flexible enough to be applied to a general inventory systems framework covering a wide range of inventory management problems with myopic clairvoyant optimal policy. By devising the optimal minibatch scheme, our metapolicy achieves a regret bound of [Formula: see text] for the general convex case and [Formula: see text] for the strongly convex case. To demonstrate the power and flexibility of our metapolicy, we apply it to three important inventory control problems, multiproduct and multiconstraint systems, multiechelon serial systems, and one-warehouse and multistore systems, by carefully designing application-specific subroutines. We also conduct extensive numerical experiments to demonstrate that our metapolicy enjoys competitive regret performance, high computational efficiency, and low variances among a wide range of applications. This paper was accepted by J. George Shanthikumar, data science. Funding: J. Xie and S. Yuan are supported by the National Natural Science Foundation of China (NSFC) [Grant 72331011]. Supplemental Material: The online appendix is available at https://doi.org/10.1287/mnsc.2023.00920 .

Optimal production management when there is regime switching and production constraints

AbstractWe study a production problem in which the cumulative consumer demand for an item follows a Brownian motion with drift, with both the drift and the variance parameters modulated by a continuous-time Markov chain that represents the regime. The company wants to maintain the inventory level as close as possible to a target inventory level, but there is a linear cost of production. We assume that the production rate is nonnegative. The company is penalized for deviations from the inventory target level and the cost of production, and the objective is to minimize the total discounted penalty costs. We consider two models. In the first model, there is no upper bound for the production rate, and in the second model there is an upper bound for the production rate. We solve both problems analytically and obtain the optimal production policy and the minimal total expected discounted cost. Our solutions allow us to obtain interesting managerial insights.

A two-stage stochastic programming model for bike-sharing systems with rebalancing

We study the problem of determining the target inventory level of stations in a bike-sharing system, when bikes can be rebalanced later during the day. We propose a two-stage stochastic programming formulation, where the target inventory decisions are made at the first stage, while the recourse decisions, related to rebalancing, are made at the second stage. In the literature, the problem of determining the target inventory levels is solved without taking into account the rebalancing problem, or these two problems are solved sequentially. We prove that more efficient bike-sharing systems can be obtained by integrating these two problems. Moreover, we show that our methodology provides better results than the deterministic formulation, and consider an effective matheuristic, based on the solution of the deterministic problem, to solve the stochastic program. Finally, we compare the solutions obtained by our approach with the actual allocation of bikes in the real bike-sharing system of the city of San Francisco. The results show the effectiveness of our approach also in a realistic setting.

A heuristic approach for multi-echelon inventory optimisation in a closed-loop supply chain

This study deals with a closed-loop supply chain where inventory levels are controlled by an order-up-to inventory policy. The system under consideration is the cylinder-packaged gas supply chain of Air Liquide company, where empty cylinders used by customers are returned to be filled again by company plants. First, we examine the goodness of fit for demand distributions based on company real data. This enables us to better characterise demands pertaining to different classes of products. Then, we formulate the multi-echelon serial inventory model to be optimised and propose a heuristic to compute the target inventory levels that helps in achieving the desired customer service level while minimising the total inventory cost. The proposed heuristic is easy to implement in the field and gives results close those obtained using a simulation-optimisation approach that is more time-consuming. Finally, we perform a numerical analysis based on company real data and compare several methods that can be used to compute the target inventory levels by varying mainly two assumptions: parameters regarding demand distributions and metrics used to assess customer service levels.

Fuzzy Random Periodic Review Mixture Inventory Model With Shortage Dependent Backorder Rate

In most real-life inventory situations, it is observed that, during stock out period, an increase in the amount of shortage results in a decrease in the rate of backorder incurred. Therefore, backorder rate is dependent on shortages, and it may be assumed to be inversely proportional to the shortages. The present research describes a periodic review inventory model with a mixture of backorder and lost sales where the backorder rate is a control parameter. Furthermore, to incorporate two different types of uncertainties i.e., fuzziness and randomness, here the annual customer demand, lead-time demand and the lead-time plus one period's demand have been assumed to be continuous fuzzy random variable following the normal distribution with associated fuzzy probability density functions. An algorithm has been proposed to find the optimal backorder rate, the optimal period of review along with the target inventory level so that the crisp equivalent of the fuzzy random total annual inventory cost is a minimum.

Multiperspective Analysis of Pandemic Impacts on U.S. Import Trade: What Happened, and Why?

U.S. container ports have experienced unpresented congestion since mid-2020. The congestion is generally attributed to import surges triggered by heavy spending on consumer goods during the COVID-19 pandemic. Port congestion has been compounded by the inability of importers to retrieve, receive, and process all the inbound goods they have ordered, resulting in supply chain shortfalls and economic disruption. How can the shipping industry and government organizations predict the end of the current surge and anticipate future surges? Expected seasonal variations in import volume are associated with peak holiday shopping periods; nonseasonal import surges are signaled by other factors. The research goes beyond transportation data sources to examine broader connections between import volume and indicators of economic and retail industry conditions. The strongest and most useful relationship appears to be between retail inventory indicators and containerized import growth. From January 2018 through July 2021, there was a relatively strong negative correlation between retail inventory- and import TEU indices with a 4-month lag (corresponding roughly to the time between import orders and -arrival). In the 2020 to 2021 pandemic period the negative correlation was stronger, again with a 4-month lag. These findings suggest that observers might anticipate import surges after marked, nonseasonal drops in retail inventories, and that import surges are likely to last until target inventory levels are restored. In a broader sense, an awareness of the linkages between consumer demand, retail chain responses, and containerized import volumes could better inform port, freight transportation, and government planning and policy choices.

An enhanced artificial bee colony algorithm for the green bike repositioning problem with broken bikes

The Bike Repositioning Problem (BRP) has raised many researchers’ attention in recent years to improve the service quality of Bike Sharing Systems (BSSs). It is mainly about designing the routes and loading instructions for the vehicles to transfer bikes among stations in order to achieve a desirable state. This study tackles a static green BRP that aims to minimize the CO2 emissions of the repositioning vehicle besides achieving the target inventory level at stations as much as possible within the time budget. Two types of bikes are considered, including usable and broken bikes. The Enhanced Artificial Bee Colony (EABC) algorithm is adopted to generate the vehicle route. Two methods, namely heuristic and exact methods, are proposed and incorporated into the EABC algorithm to compute the loading/unloading quantities at each stop. Computational experiments were conducted on the real-world instances having 10–300 stations. The results indicate that the proposed solution methodology that relies on the heuristic loading method can provide optimal solutions for small instances. For large-scale instances, it can produce better feasible solutions than two benchmark methodologies in the literature.

Nonparametric Learning Algorithms for Joint Pricing and Inventory Control with Lost Sales and Censored Demand

We consider a joint pricing and inventory control problem in which the customer’s response to selling price and the demand distribution are not known a priori. Unsatisfied demand is lost and unobserved, and the only available information for decision making is the observed sales data (also known as censored demand). Conventional approaches, such as stochastic approximation, online convex optimization, and continuum-armed bandit algorithms, cannot be employed, because neither the realized values of the profit function nor its derivatives are known. A major challenge of this problem lies in that the estimated profit function constructed from observed sales data is multimodal in price. We develop a nonparametric spline approximation–based learning algorithm. The algorithm separates the planning horizon into a disjoint exploration phase and an exploitation phase. During the exploration phase, a spline approximation of the demand-price function is constructed based on sales data, and then the corresponding surrogate optimization problem is solved on a sparse grid to obtain a pair of recommended price and target inventory level. During the exploitation phase, the algorithm implements the recommended strategies. We establish a (nearly) square-root regret rate, which (almost) matches the theoretical lower bound.

Optimal Learning Algorithms for Stochastic Inventory Systems with Random Capacities

We propose the first learning algorithm for single‐product, periodic‐review, backlogging inventory systems with random production capacity. Different than the existing literature on this class of problems, we assume that the firm has neither prior information about the demand distribution nor the capacity distribution, and only has access to past demand and supply realizations. The supply realizations are censored capacity realizations in periods where the policy need not produce full capacity to reach its target inventory levels. If both the demand and capacity distributions were known at the beginning of the planning horizon, the well‐known target interval policies would be optimal, and the corresponding optimal cost is referred to as the clairvoyant optimal cost. When such distributional information is not available a priori to the firm, we propose a cyclic stochastic gradient descent type of algorithm whose running average cost asymptotically converges to the clairvoyant optimal cost. We prove that the rate of convergence guarantee of our algorithm is [Formula: see text], which is provably tight for this class of problems. We also conduct numerical experiments to demonstrate the effectiveness of our proposed algorithms.

Blockchain Design for Supply Chain Management

Blockchain related research is still in its infancy, and is mostly focused on security and scalability. Very little of this research examines at its impact and design issues from management perspectives, especially from the perspective of Supply Chain Management (SCM). To investigate the impact of blockchain technology (BCT) on SCM and the inherent design issues, we consider a generic stochastic model, where a firm seeks to maximize the total expected discounted profit, by jointly managing (i) blockchain design, (ii) production and ordering decisions, and (iii) dynamic pricing and selling. We first show that the deployment of BCT can assist firms in reducing order quantities, lowering selling prices and reducing target-inventory levels. It is also shown that volatility of either supply or demand lowers the expected profit. The analysis is robust with some major extensions, such as lost-sales of demand and random capacity. Finally, our numerical study accumulates useful managerial insights. For example, subject to tech-savvy customer behavior, some types of goods (e.g., credence goods and experience goods) greatly benefit from the adoption of BCT, but it may not prove beneficial to leverage BCT for certain others (e.g., search goods). Considering the lifecycle of a typical good, it is recommended to adopt BCT as early as possible and to adopt it to a higher degree at an earlier stage.

Optimal Learning Algorithms for Stochastic Inventory Systems with Random Capacities

We propose the first learning algorithm for single-product, periodic-review, backlogging inventory systems with random production capacity. Different than the existing literature on this class of problems, we assume that the firm has neither prior information about the demand distribution nor the capacity distribution, and only has access to past demand and supply realizations. The supply realizations are censored capacity realizations in periods where the policy need not produce full capacity to reach its target inventory levels. If both the demand and capacity distributions were known at the beginning of the planning horizon, the well-known target interval policies would be optimal, and the corresponding optimal cost is referred to as the clairvoyant optimal cost. When such distributional information is not available a priori to the firm, we propose a cyclic stochastic gradient descent type of algorithm whose running average cost asymptotically converges to the clairvoyant optimal cost. We prove that the rate of convergence guarantee of our algorithm is $O(1/\sqrt{T})$, which is provably tight for this class of problems. We also conduct numerical experiments to demonstrate the effectiveness of our proposed algorithms.

Replacement and inventory control for a multi-customer product service system with decreasing replacement costs

In a Use-Oriented Product Service System, the customers pay for a particular service without owning the product, and the profitability of the service provider (usually also the owner of the product) is determined by the product availability and how replacement and inventory control are implemented. With the advances in modern sensor and wireless communication technologies, service providers can monitor the health status of each product in use and then conduct condition-based maintenance accordingly. Meanwhile, the waste of the remaining life of replaced products should also be considered in the system's operation due to the increasing concerns about environmental impact and lean production. To improve the profitability of a Use-Oriented Product Service System, we formulate a discrete-time Markov Decision Process that maximizes the long-term revenue per period. To overcome the computational challenge of this problem, we propose a sequential heuristic solution incorporating a heuristic replacement policy along with a heuristic inventory control approach to solve the integrated model. The heuristic replacement policy is derived from the optimal control policy for the subsystem of a single customer. The inventory control heuristic determines the target inventory level according to a one-period look-ahead myopic optimization policy. The performance of the proposed solution and some useful management insights are investigated in a numerical study. In addition, sensitivity analyses by varying the replacement costs, holding cost, unit service revenue and deterioration rates are also conducted.

Can irrelevant benchmark information help when making business decisions under uncertainty? An empirical investigation of the newsvendor game

Firms often compensate employees based on their relative performance in the most recent business period. These firms need to consider what type of performance information to share with their employees in order to obtain better outcomes in the long run, without diminishing staff motivation. In this paper, we empirically investigate the impact of sharing irrelevant benchmark “information” (e.g., information about the interim winner's performance) when individuals are making repeated decisions under uncertainty. The decision-making context used is the newsvendor problem, which is a canonical framework for operations management decision making. The newsvendor problem occurs in many business contexts, such as buying fashion goods for retail, setting safety stock levels, setting target inventory levels for perishable goods, selecting the right capacity for a service facility, and overbooking customers. Theoretically, information about the interim winner's performance has no value for making improved decisions in future rounds, and it might even be misleading. Surprisingly, we find that displaying such irrelevant benchmark information results in significantly improved decisions overall, as compared to a control group; this additional display may motivate participants to perform better. We also identify two personality traits related to impulsivity which moderate this positive information display effect.

Setting Inventory Levels in a Bike Sharing Network

Bike sharing systems (BSSs) allow customers to rent bicycles at automatic rental stations distributed throughout a city, use them for a short period of time, and return them to any station. One of the major issues that BSS operators must address is nonhomogeneous asymmetric demand processes. These demand processes create an inherent imbalance, thus leading to shortages either of bicycles when users are attempting to rent them and of vacant lockers when users are attempting to return them. The predominant approach taken by operators to cope with this difficulty is to reposition bicycles to rebalance the inventory levels at the different stations. Most repositioning studies assume that a target inventory level or range of inventory levels is known for each station. In this paper, we focus on determining the correct target level for repositioning according to a well-defined objective. This is a challenging task because of the nature of the user behavior that creates the interactions among the inventory levels at different stations. For example, if bicycles are not available at the user’s origin, the user may abandon the system, use other means of transportation, or look for available bicycles at a neighboring station. If, in another case, a locker is not available at a user’s destination, then that user is obliged to find a station with available space to return the bicycle to the system. Thus, an empty/full station can create a spillover of demand to nearby stations. In addition, stations are related by origin–destination pairing. In this paper, we take this effect into consideration for the first time when setting target inventory levels and develop a robust guided local search algorithm for that purpose. We show that neglecting the interactions among stations leads to inferior decision making.

Periodic review inventory model with normally distributed fuzzy random variable demand

ABSTRACTIn this article, a periodic review inventory model has been analysed in a fuzzy random framework. In order to incorporate the two different kind of uncertainties, namely fuzziness and randomness, that characterise any real-life inventory situation simultaneously, the model has been developed in the mixed fuzzy random environment. The amalgamation of these two uncertainties has been accomplished by assuming the annual customer demand to be a continuous fuzzy random variable following the normal distribution. The lead-time has been assumed to be constant. The lead-time demand and the lead-time plus one period's demand have also been assumed to be normally distributed fuzzy random variables by connecting them to the annual customer demand through the length of the lead-time and the lead-time plus one period's demand, respectively. An algorithm has been proposed to determine the optimal period of review and the optimal target inventory level so as to minimise the total expected annual inventory cost. The proposed methodology has been illustrated by way of a numerical example.

Can Irrelevant Benchmark Information Help When Making Business Decisions Under Uncertainty? An Empirical Investigation of the Newsvendor Game

Firms often compensate employees based on their relative performance in the most recent business period. These firms need to consider what type of performance information to share with their employees in order to obtain better outcomes in the long run, without diminishing staff motivation. In this paper, we empirically investigate the impact of sharing irrelevant benchmark information (e.g., information about the interim winner's performance) when individuals are making repeated decisions under uncertainty. The decision-making context used is the newsvendor problem, which is a canonical framework for operations management decision making. The newsvendor problem occurs in many business contexts, such as buying fashion goods for retail, setting safety stock levels, setting target inventory levels for perishable goods, selecting the right capacity for a service facility, and overbooking customers. Theoretically, information about the interim winner's performance has no value for making improved decisions in future rounds, and it might even be misleading. Surprisingly, we find that displaying such irrelevant benchmark information results in significantly improved decisions overall, as compared to a control group; this additional display may motivate participants to perform better. We also identify two personality traits related to impulsivity which moderate this positive information display effect. Irrelevant benchmark information matters for decision making under uncertainty.Displaying such information significantly improves repetitive newsvendor decisions.Premeditation and urgency moderate the effect of such information on decision making.A pull-to-center bias is observed when displaying irrelevant benchmark information.

Ordinal optimization based metaheuristic algorithm for optimal inventory policy of assemble-to-order systems

Assemble-to-order (ATO) systems refer to a manufacturing process in which a customer must first place an order before the ordered item is manufactured. An ATO system that operates under a continuous-review base-stock policy can be formulated as a stochastic simulation optimization problem (SSOP) with a huge search space, which is known as NP-hard. This work develops an ordinal optimization (OO) based metaheuristic algorithm, abbreviated to OOMH, to determine a near-optimal design (target inventory level) in ATO systems. The proposed approach covers three main modules, which are meta-modeling, exploration, and exploitation. In the meta-modeling module, the extreme learning machine (ELM) is used as a meta-model to estimate the approximate objective value of a design. In the exploration module, the elite teaching-learning-based optimization (TLBO) approach is utilized to select N candidate designs from the entire search space, where the fitness of a design is evaluated using the ELM. In the exploitation module, the sequential ranking-and-selection (R&S) scheme is used to optimally allocate the computing resource and budget for effective selecting the critical designs from the N candidate designs. Finally, the proposed algorithm is applied to two general ATO systems. The large ATO system comprises 12 items on eight products and the moderately sized ATO system is composed of eight items on five products. Test results that are obtained using the OOMH approach are compared with those obtained using three heuristic methods and a discrete optimization-via-simulation (DOvS) algorithm. Analytical results reveal that the proposed method yields solutions of much higher quality with a much higher computational efficiency than the three heuristic methods and the DOvS algorithm.

Quasi-fixed cyclic production schemes for multiple products with stochastic demand

In this paper we present an approach to generate cyclic production schemes for multiple products with stochastic demand to be produced on a single production unit. This scheme specifies a fixed and periodic production sequence, called a cycle, where each product may occur more than once in the sequence. In order to stabilize the cycle length alternative control strategies are introduced. These strategies keep the cycle length close to a target length by means of adding idle time to the cycle, cutting production short or overproduction. On basis of the selected control strategy as well as a base-stock policy target inventory levels are determined for each production run in the cycle. Demand can be backlogged but a certain service level is required. Setup times are sequence-dependent and the storage is capacitated. Employing the developed strategies we investigate the tradeoff between stability of cycle length and total cost induced by the production schedule in a computational study based on both, real world data and random test instances.

The impact of financial constraints on inventory investment: Empirical evidence from Jordan

This study aims at investigating whether Jordanian industrial firms have a target inventory level, and how fast they move toward it when any deviation exists. In addition, it investigates whether the financial constraints have an impact on inventory investment related to the target level, and the speed of adjustment. Using the panel data for a sample of 50 industrial firms listed on the Amman Stock Exchange (ASE) over the period (2001-2014). The empirical results suggest that Jordanian industrial firms have a target inventory level. However, Jordanian industrial firms adjust their actual inventory holding to their target level slower than their counterparts in developed and developing countries. Moreover, the results show that the financial constraint do affect inversely the adjustment speed, and makes the financially constrained firms reduce their level of inventory beyond the target level by more than others.