A learning-based ordering policy for transition to intelligent perishable inventory management

In this paper we develop a practical primal interior decomposition algorithm for two-stage stochastic programming problems. The framework of this algorithm is similar to the framework in [S. Mehrotra and M. G. Özevin, “Decomposition based interior point methods for two-stage stochastic convex quadratic programs with recourse,” to appear in Oper. Res.; S. Mehrotra and M. G. Özevin, SIAM J. Optim., 18 (2007), pp. 206–222] and [G. Zhao, Math. Program., 90 (2001), pp. 507–536], however, their algorithm is altered in a simple yet fundamental way to achieve practical performance. In particular, this new algorithm weighs the log-barrier terms in the second stage problems differently from the theoretical algorithms analyzed in [S. Mehrotra and M. G. Özevin, Oper. Res., to appear], [S. Mehrotra and M. G. Özevin, SIAM J. Optim., 18 (2007), pp. 206–222], and [G. Zhao, Math. Program., 90 (2001), pp. 507–536]. We give a method for generating a suitable starting point; a method for selecting a good starting barrier parameter; a heuristic for first stage step-length calculation without performing line searches; and a method for adaptive addition of new scenarios over the course of the algorithm. The decomposition algorithm is implemented to solve two-stage stochastic conic programs with recourse whose underlying cones are Cartesian products of linear, second order, and semidefinite cones. The performance of primal decomposition method is studied on a set of randomly generated test problems as well as a two-stage stochastic programming extension of the Markowitz portfolio selection model. The computational results show that an efficient and stable implementation of the primal decomposition method is possible. These results also show that in problems with a large number of scenarios, the adaptive addition of scenarios can yield computational savings of up to 80%.

Contributors

The inventory routing problem (IRP) arises in the joint practices of vendor-managed inventory (VMI) and vehicle routing problem (VRP), aiming to simultaneously optimize the distribution, inventory and vehicle routes. This paper studies the multi-vehicle multi-compartment inventory routing problem with stochastic demands (MCIRPSD) in the context of fuel delivery. The problem with maximum-to-level (ML) replenishment policy is modeled as a two-stage stochastic programming model with the purpose of minimizing the total cost, in which the inventory management and routing decisions are made in the first stage while the corresponding resource actions are implemented in the second stage. An acceleration strategy is incorporated into the exact single-cut Benders decomposition algorithm and its multi-cut version respectively to solve the MCIRPSD on the small instances. Two-phase heuristic approaches based on the single-cut decomposition algorithm and its multi-cut version are developed to deal with the MCIRPSD on the medium and large-scale instances. Comparing the performance of the proposed algorithms with the Gurobi solver within limited time, the average objective value obtained by the proposed algorithm has decreased more than 7.30% for the medium and large instances, which demonstrates the effectiveness of our algorithms. The impacts of the instance features on the results are further analyzed, and some managerial insights are concluded for the manager.

PurposeThis paper assembles the 100 most-cited journal articles and reviews on the blood supply chain to analyze the research trends and knowledge themes.Design/methodology/approachThe study conducted a bibliometric analysis of the 100 most-cited journal articles and reviews published between 2004 and 2023 in the context of the blood supply chain, as retrieved from the Scopus database. The study analyzed research trends in this area and knowledge themes through a keyword co-occurrence analysis and bibliographic coupling using VOSviewer.FindingsThe study reveals that the top 100 most-cited journal articles and reviews within the domain of the blood supply chain were published between 2004 and 2023, with a notable surge in research activity observed in the recent years. Through keyword analysis, five themes, which are “inventory management and supply chain management operations for blood products,” “stochastic and possibilistic programming for designing blood supply chain network and sustainability,” “robust optimization in blood supply chain network design under uncertainty and disaster conditions,” “Network design using multi-objective, possibilistic and two-stage stochastic programming in blood supply chains” and “perishable inventory management in blood supply chains,” were obtained. On the other hand, four themes from bibliographic coupling include “designing blood supply chain networks during the time of disasters and emergencies,” “optimizing and managing blood supply chains for enhancing efficiency and reducing wastage,” “inventory management and advanced techniques in the context blood supply chain management” and “enhancing safety, efficiency and continuous blood supply in the face of various challenges.”Originality/valueThis study uniquely analyzed 100 most-cited publications in the realm of the blood supply chain, which provides relevant knowledge themes that are crucial for future studies and contributing to the knowledge in this research domain.

Investigating risk and robustness measures for supply chain network design under demand uncertainty: A case study of glass supply chain

The supply-chain-to-supply-chain business competition model creates the Vendor Managed Inventory (VMI) management model for the retailers. The previous studies show that most of the conventional inventory management strategies apply fixed-quantity or order-up-to-level supplement methods, rarely mentioning the impact of supplement quantity cutting or non-order-up-to-level strategy on the total cost of the inventory routing of VMI management model. This study proposes the inventory management strategy with supplement threshold and upper limit, builds an inventory management model by the systematic analogical method and analyzes the effects of the inventory management strategy with combinations of different supplement thresholds and upper limits on the total cost of the inventory routing as well as the relatively changing situation of the inventories and transportation costs of the suppliers and retailers in a two-phase supply chain system of one supplier and multiple retailers under the condition that the demand time point and demand quantity of the retailers' customers are fixed and undetermined. When the system simulates the supplier to execute the inventory management, it firstly applies the supplement threshold after each supplement cycle to update the minimum inventory level, thus determining the collection of the supplement objects for the next supplement cycle and secondly determines the supplement quantity based on the upper limit of supplement. After that, it works out the optimal routine for supplement delivery and calculates the total cost of the inventory routing for the supplement cycle by linear programming method based on the analogue results. The study results indicate that the inventory management strategy combining the supplement-quantity-cut upper limit of supplement with the slightly-raised supplement threshold can effectively reduce the total cost, improve the vehicle utilization rate and maintain a certain service performance; moreover, it can delivery the supplement to more retailers during the supplement cycle to offer a new inventory routing management strategy for reference by the practitioner when making decisions.

Inventory management remains a cornerstone of effective supply chain performance, directly influencing cost efficiency, service quality, and organizational agility. In today’s hypercompetitive and uncertain market environment, inventory decisions must account for complex variables such as fluctuating demand, supply disruptions, lead time variability, and market seasonality. Traditional inventory control models such as the Economic Order Quantity (EOQ), base-stock policies, and (s, S) strategies are often static in nature. They rely on pre-defined parameters and assume stationarity in demand and supply, limiting their ability to respond dynamically to real-time changes. In contrast, Reinforcement Learning (RL) offers a paradigm shift in how inventory decisions can be optimized. As a subfield of machine learning, RL enables agents to learn optimal strategies through repeated interactions with an environment, using trial-and-error exploration and reward-based feedback. RL agents can observe the system state (e.g., inventory levels, demand signals, lead time status), choose actions (e.g., place an order or wait), and receive feedback in the form of rewards (e.g., service level achievements or cost penalties), thus iteratively improving their policies. This study explores how RL can be applied to optimize inventory management in environments characterized by uncertainty and real-time decision-making needs. Specifically, we investigate how different RL algorithms such as Q-learning, Deep Q Networks (DQN), and Policy Gradient methods perform in various inventory scenarios. Additionally, we examine the computational and operational implications of deploying RL in real-world settings, including issues of model convergence, exploration-exploitation tradeoffs, data requirements, and scalability. We also discuss how RL can complement other AI techniques such as demand forecasting models and predictive analytics in creating end-to-end intelligent supply chain solutions. By bridging the gap between theoretical RL frameworks and practical inventory management applications, this paper contributes to both the academic literature and industrial practice. Our goal is to demonstrate that RL is not only a theoretically elegant solution but also a viable tool for achieving inventory efficiency and supply chain resilience.

ABSTRACTThis paper studies the complex strategic planning problem faced by truckload (TL) companies related to finding the allocation of vehicles serving lanes with stochastic demand within their networks. Lanes are origin–destination pairs associated with volumes of TLs per unit of time that follow discrete probability distributions. Finding strategic vehicle allocations that anticipate demand variability is critical because unrealized demands increase repositioning costs and reduce perceived revenues. The allocation problem is formulated as a two-stage stochastic program. The paper proposes a novel procedure based on network transformations that formulate the complex stochastic problem as a minimum cost-flow problem (MCFP), which can be efficiently solved with classic MCFP algorithms. Numerical experiments demonstrate the computational efficiencies of the method (instances with 1404 nodes and 98,904 arcs solved in 20.74 seconds) and reinforce the necessity of incorporating stochastic effects to avoid overestimation from deterministic approaches.

Stock markets are the result of the interaction of multiple participants, and market makers are one of them. Their main goal is to provide liquidity and market depth to the stock market by streaming bids and offers at both sides of the order book, at different price levels. This activity allows the rest of the participants to have more available prices to buy or sell stocks. In the last years, reinforcement learning market maker agents have been able to be profitable. But profit is not the only measure to evaluate the quality of a market maker. Inventory management arises as a risk source that must be under control. In this paper, we focus on inventory risk management designing an adaptive reward function able to control inventory depending on designer preferences. To achieve this, we introduce two control coefficients, AIIF (Alpha Inventory Impact Factor) and DITF (Dynamic Inventory Threshold Factor), which modulate dynamically the behavior of the market maker agent according to its evolving liquidity with good results. In addition, we analyze the impact of these factors in the trading operative, detailing the underlying strategies performed by these intelligent agents in terms of operative, profitability and inventory management. Last, we present a comparison with other existing reward functions to illustrate the robustness of our approach.Graphic

Inventory management plays a critical role to track inventory levels, orders, and sales of the retailing business. Effective inventory management is a capability necessary to lead in the global marketplace. In the current retailing market, a huge amount of data regarding stocked items in inventory is generated and collected every day. Due to the increasing volume of transaction data and their correlated relations, it is often a non-trivial task to efficiently manage stocked goods, yet it is imperative to explore the underlying dependencies of the inventory items and give insights into implementing intelligent management systems. However, existing inventory management systems rely on statistical analysis of the historical inventory data, and have a limited capability of intelligent management. For example, they usually do not have the ability to forecast item demand and detect anomalous patterns of item inventory transactions. There is little work reported in implementing intelligent inventory management solutions to reveal hidden relations with integrated data-driven analysis. In this paper, we present an intelligent system, called iMiner, to facilitate managing enormous inventory data. We utilize distributed computing resources to process the huge volume of inventory data and incorporate the latest advances in data mining technologies. iMiner provides comprehensive support for conducting many inventory management tasks, such as forecasting inventory, detecting anomalous items, and analyzing inventory aging.

The stochastic location-allocation p-hub median problems are related to long-term decisions made in risky situations. Due to the importance of this type of problems in real-world applications, the authors were motivated to propose an approach to obtain more reliable policies in stochastic environments considering the decision makers’ preferences. Therefore, a systematic approach to make robust decisions for the single location-allocation p-hub median problem based on mean-variance theory and two-stage stochastic programming was developed. The approach involves three main phases, namely location modeling, risk modeling, and decision making, each including several steps. In the first phase, the pertinent location-allocation model of the problem is developed in the form of a two-stage stochastic model based on its deterministic version. A risk measure, based on total cost function and mean-variance theory, is derived in the second phase. Furthermore, two heterogeneous terms of the risk measure have been normalized and an innovative procedure has been proposed to significantly improve the calculation efficiency. In the third phase, the Pareto solution is obtained, the frontier curve is depicted to determine the decision maker’s risk aversion coefficient, and a robust policy is obtained through optimization based on decision makers’ preferences. Finally, a case study of an automobile part distribution system with stochastic demand is described to further illustrate our risk management and analysis approach.

Adaptive traffic signal control with equilibrium constraints under stochastic demand

A matheuristic approach based on a reduced two-stage Stochastic Integer Linear Programming (SILP) model is presented. The proposed approach is suitable for obtaining a policy constructed dynamically on the go during the rollout algorithm. The rollout algorithm is part of the Approximate Dynamic Programming (ADP) lookahead solution approach for a Markov Decision Processes (MDP) framed Multi-Depot Dynamic Vehicle Routing Problem with Stochastic Road Capacity (MDDVRPSRC). First, a Deterministic Multi-Depot VRP with Road Capacity (D-MDVRPRC) is presented. Then an extension, MDVRPSRC-2S, is presented as an offline two-stage SILP model of the MDDVRPSRC. These models are validated using small simulated instances with CPLEX. Next, two reduced versions of the MDVRPSRC-2S model (MDVRPSRC-2S1 and MDVRPSRC-2S2) are derived. They have a specific task in routing: replenishment and delivering supplies. These reduced models are to be utilised interchangeably depending on the capacity of the vehicle, and repeatedly during the execution of rollout in reinforcement learning. As a result, it is shown that a base policy consisting of an exact optimal decision at each decision epoch can be obtained constructively through these reduced two-stage stochastic integer linear programming models. The results obtained from the resulting rollout policy with CPLEX execution during rollout are also presented to validate the reduced model and the matheuristic algorithm. This approach is proposed as a simple implementation when performing rollout for the lookahead approach in ADP.

Inventory management is central to production planning and control particularly in multi-stage production environment where production output is stochastic and customer demand is also stochastic. Surplus inventory ties down money and stock-out situation result in loss of value and goodwill. Therefore, it is necessary determine optimal inventory policies for different manufacturing scenarios to maintain a balance between safety stock inventory and customer demand satisfaction at all time. Consequently, this review attempts to identify and document the underlying trends and most recent methods of inventory replenishment under stochastic demand with emphasis on multi-stage production setting. Prominent in literature among the models used to treat inventory problem in stochastic demand situation is “Approximation by Probabilistic Distribution”. Other models used include, Genetic Algorithm (GA), Just-in-time with Kanban simulation, Markov Process Decision, Fuzzy Inventory Model, Multi-stage inventory-queue model and Demand forecasting among others. It appears that there exist only approximate solutions than exact solutions in solving stochastic demand inventory problem suggesting that there is need for more work to be done in the area toward achieving exact solutions to the problem than approximation.

A stochastic optimization approach for the supply vessel planning problem under uncertain demand