Advance Demand Information Research Articles

How good must failure predictions be to make local spare parts stock superfluous?

Thanks to Industry 4.0 technologies, predictive algorithms can provide advance demand information on spare parts demand. Understanding how the goodness of predictions affects on-hand inventory and costs is important for decision makers before integrating these models into existing systems. We consider a spare parts inventory problem for multiple technical systems that are supported by one local stockpoint. Each system has a single critical component that is subject to random failures. Signals are generated to predict component failures. The signal that corresponds to a failure is generated a certain amount of time before the failure, referred to as the demand lead time. However, not every signal results in a failure and some failures are undetected. A component is replaced from the stock when a failure occurs. In case of stock-outs, an emergency shipment takes place. We formulate a discrete-time Markov decision process model to optimize the replenishment decisions with the objective of minimizing the long-run average cost per period. We investigate the effect of precision (i.e., the fraction of true signals among all signals) and sensitivity (i.e., the fraction of detected failures among all failures) of the predictions and the demand lead time on the costs, order-up-to levels, average on-hand inventory and emergency shipments under the optimal policy. In the worst case, the precision, sensitivity or demand lead time is zero. We show analytically that the optimal policy and optimal costs only depend on the sensitivity and the demand lead time through their product. In numerical experiments, we observe a Pareto principle for the reduction of costs in precision (e.g., a 30% perfectness in precision brings a 70% reduction in optimal cost compared to the worst case) and an inverse Pareto principle in the product of sensitivity and demand lead time (e.g., 70% perfectness in the sensitivity or demand lead time only brings 30% reduction in optimal cost compared to the worst case). Finally, we observe that the local spare parts stock only becomes superfluous when the signals are really close to perfect.

Managing production-inventory-maintenance systems with condition monitoring

Providing spare parts and maintenance services to customers has become an important revenue stream for equipment manufacturers. This paper studies a Production-Inventory-Maintenance (PIM) system where a manufacturer serves an installed base of machines. Each machine contains the same critical component, whose degradation behaviour is described by a Markov process and captured via condition monitoring. When the state of a component reaches a prespecified replacement threshold, the machine is considered to have failed and incurs downtime penalties until being repaired. There are a few repair servers and queueing dynamics follows the Machine Interference Problem (MIP). Component deterioration and server congestion provide advance demand information, which helps plan the production of spare parts in a make-to-stock routine. The unsatisfied requests for spare parts are fulfilled by emergency replenishments with lost-sales penalties. We formulate the production-control problem as a continuous-time Markov decision process, characterize the structure of the optimal policy, and develop an effective heuristic policy. Through numerical experiments, we reveal a number of notable differences between managing PIM systems and operating MIP systems alone: (1) Although identifying more degradation states has no value to MIP systems, PIM systems benefit substantially from such a refined state identification. (2) While MIP systems prefer more repair servers and higher repair operation efficiency, greater repair capacity may worsen the performance of PIM systems. (3) When the product of repair service rate and server number is fixed, a single server is always preferred in MIP systems. However, PIM systems could perform better with multiple less-efficient servers.

A Study on Behavioral Simulation of Single Chained Multi-Stage Supply Chain Planed by Advance Demand Information

A Study on Behavioral Simulation of Single Chained Multi-Stage Supply Chain Planed by Advance Demand Information

Configuring information updating schemes of partial imperfect advance demand information in production-inventory systems

We consider a make-to-stock system, where a supplier produces a single product to meet a single customer’s order. The order quantity is fixed, but the order time is random. Before the order becomes due, it goes through multiple stages, and the transition time from one stage to the next is random. The customer provides advance demand information (ADI) by updating the order status information to the supplier when the order progresses to a key stage. We study the supplier’s optimal production policy. By formulating this problem as a Markov decision process, we show that the optimal production policy is a state-dependent base-stock policy, and the optimal base-stock level after receiving the update is higher than before. We extend the model to the case with multiple updates. We numerically examine the configuration of information updating schemes, i.e. the timing and number of updates. We find that partial ADI with one update can capture most of the benefits of full ADI in most cases. However, the timing of update is crucial for the benefit of ADI. For a few cases where only one update is less effective, increasing the number of updates slightly can capture most of the benefits of full ADI.

The Impact of Committing to Customer Orders in Online Retail

Problem definition: Online retailers are on a consistent drive to increase on-time delivery and reduce customer lead time. However, in reality, an increasing share of consumers places orders early. Academic/practical relevance: Such advance demand information can be deployed strategically to reduce costs and improve the customer service experience. This requires inventory and allocation policies that make optimal use of this information and that induce consumers to place their orders early. An increasing number of online retailers not only offer customers a choice of lead time but also, actively back-order missing items from a consumer basket. Methodology: We develop new allocation policies that commit to a customer order upon arrival of the order rather than at the moment the order is due. We provide analytical results for the performance of these allocation policies and evaluate their behavior with real data from a large food retailer. Results: Our policy leads to a higher fill rate at the expense of a slight increase in average delay. The analysis based on real-life data suggests a sizeable impact that should impact current best practices in online retail. Managerial implications: With the changing landscape in online retail, customers increasingly place baskets of orders that they would like to receive at a planned and confirmed moment in time. Especially in grocery, this has grown fast. This fundamentally changes the strategic management of inventory. We demonstrate that online retailers should commit early to customer orders to enhance the customer service experience and eventually, to also create opportunities for reducing the cost of operations. Supplemental Material: The online appendix is available at https://doi.org/10.1287/msom.2022.1124 .

The added value of advance demand information for the planning of a repair kit

In this paper the repair kit problem is studied, where technicians have to visit several customers to repair broken appliances (such as copiers or heating systems) and they can only take a limited set of parts with them (called the repair kit). In this problem, it has to be decided which spare parts to include in the repair kit. We consider a version of this problem in which partial advance demand information is available. That means we divide the set of parts into two subsets, where the condition of parts in one subset is monitored by sensors. In case an appliance fails and a repair job is requested by a customer the service provider is able to access this sensor data before a technician visits the customer. For this setting, we derive an expression for the job fill rate, which is used as a constraint in the optimization model, where holding and replenishment costs are minimized. We use a greedy heuristic to determine near-optimal repair kits. In a numerical study, we find that integrating advance demand information yields substantial cost savings. In order to find out for which parts having advance demand information is most valuable, we examine the effect of parts’ demand probabilities and their prices. We find that monitoring parts that are expensive and likely to fail leads to the largest cost savings. In particular, the price of the monitored parts and the achievable cost savings are strongly correlated.

Inventory management with advance demand information and flexible shipment consolidation

In this paper, we study a stochastic single-item, single-stage inventory system, in which orders from several production facilities are placed at one warehouse. An (R, Q) policy is applied to control the inventory at the warehouse, and orders arrive according to a Poisson process and include a due date such that some information about future demand is available. This advance demand information (ADI) can be used to adapt a time-based shipment consolidation policy applied to replenish stock at the production facilities. We develop a model to incorporate flexible deliveries, indicating that orders can be shipped before their due date if sufficient reserved transportation capacity is available. We derive analytical, approximate expressions for the expected inventory and shipment costs and therefore enable the evaluation of different inventory and shipment policies including outbound transportation capacities. We additionally show how to compute the optimal policy parameters and conduct a detailed numerical study. Our computational experiments indicate that our approximation works extremely well, with an average total cost deviation of 0.20%, and finds optimal policy parameters in more than 90% of our instances. In line with existing research, we can show that ADI leads to large cost reductions. However, the main cause of the cost reduction is the flexible delivery option. To be able to completely utilize this option, even larger safety stocks are obtained compared to systems without ADI, but savings due to a more efficient transportation policy far exceed the cost increase due to higher safety stocks.

The repair kit problem with imperfect advance demand information

To promote customer loyalty and generate revenue in after-sales service, many companies provide field repair services to their customers. Service technicians who perform these repair jobs typically carry a set of spare parts called a repair kit in their company van. The repair kit problem aims to determine which parts to include in this kit and in what quantity. Currently, many appliances are equipped with sensors that monitor their different functionalities. If an appliance breaks down because one of these functionalities is disturbed, then the respective sensor triggers a failure code that describes the appliance’s condition. From the service technician’s perspective, this failure code serves as potentially imperfect advance demand information for spare parts. In this paper, we present an extension of the repair kit problem that uses this information for the replenishment decision. We formulate this repair kit problem with advance demand information as a Markov decision process and propose two heuristic solution procedures. Our first heuristic is far-sighted and optimizes the inventory of all parts individually, while our second heuristic is a myopic greedy algorithm that considers all parts at once. We conduct an extensive numerical study to evaluate the performance of both heuristics and to identify which heuristic performs best under which circumstances. Comparing both heuristics to a state-of-the-art algorithm that disregards any available advance demand information, we find that utilizing this information yields substantial cost savings.

Advance Demand Information as a Tool for Value Chain Planning of Biofortified Foods in Brazil

Biofortified foods represent an alternative to minimize extreme and “hidden” hunger in people. Aiming to look at this sector as a business, this study seeks to identify potential demand in the consumer market regarding fortified foods in Brazil. In order to do these, multiple sources of data collection were adopted to access different markets for these products. In the first part of the research a survey of Brazilian government programs was carried out, which could encourage the demand of biofortified foods. In addition a conversation was undertaken with stakeholders seeking to identify the perception of agents who take part in the value chain, which included the project developer in Brazil (Embrapa) to the food industry. Additionally a quantitative research was carried out using Mann-Witney and Chi-square tests, and also Multiple Correspondence Analysis, aiming to evaluate the perception of final consumers regarding biofortified foods. Looking at the results a potential demand was identified for biofortified foods, through government programs as well as via the food industry, despite needing larger promotion amongst the Brazilian population, as the sample showed a considerable lack of awareness. In relation to biofortified foods each market showed different interests, such as Cascavel, Parana, which showed greater interst in School Meals with corn and cassava. While in the food industry the interest was more considerable for sweet potato, and amongst the final consumers there was a bigger interest in corn and beans. A potential demand in several markets for all biofortified foods was also shown.

Modeling and analyzing a simple multi-stage supply chain using advance demand information

Modeling and analyzing a simple multi-stage supply chain using advance demand information

Using supervised machine learning for B2B sales forecasting: A case study of spare parts sales forecasting at an after-sales service provider

In this paper, we present a method to use advance demand information (ADI), taking the form of request for quotation (RFQ) data, in B2B sales forecasting. We apply supervised machine learning and Natural Language Processing techniques to analyze and learn from RFQs. We apply and test our approach in a case study at a large after-sales service and maintenance provider. After evaluation we found that our approach identifies ∼ 70% of actual sales (recall) with a precision rate of ∼ 50%, which represents a performance improvement of slightly more than a factor 2.5 over the current labor-intensive manual process at the service and maintenance provider. Our research contributes to literature by giving step-by-step guidance on incorporating artificial intelligence in B2B sales forecasting and revealing potential pitfalls along the way. Furthermore, our research gives an indication of the performance improvement that can be expected when adopting supervised machine learning into B2B sales forecasting.

Benefits of Carrier Collaboration Under Incomplete Advance Demand Information: A Case of Indian Truckload Carriers

Benefits of Carrier Collaboration Under Incomplete Advance Demand Information: A Case of Indian Truckload Carriers

A contract portfolio perspective on the role of customer order lead times in demand fulfilment processes with supply shortage

When demands exceed capacities, suppliers allocate available supply to customers based on customer importance and advance demand information. The accuracy of advance demand information interacts with the length of customer order lead times and influences overall customer service levels. In this paper, we analyse industrial contract portfolios with customer-specific terms in order to derive insights for contract portfolio management and the design of demand fulfilment processes. For this purpose, we develop a framework for analysis of contract portfolios capturing the dynamics of industrial planning processes. The framework is applied to portfolios from the semiconductor sector. Our numerical analysis shows that, in order to improve service levels, demand fulfilment processes and contract portfolio management must especially take into account the length of order lead times and the accuracy of advance demand information. Even though suppliers often prefer long order lead times, our analysis shows that demand fulfilment performance is not primarily determined by the absolute length of the order lead times but by the presence of a negative correlation with the accuracy of advance demand information in the entire contract portfolio. Consequently, these factors require increased attention in the management of contract portfolios and in the negotiation of individual contracts.

Offsetting omnichannel grocery fulfillment cost through advance ordering of perishables

With the rise of online grocery adoption, customers are now placing more delivery and pickup orders. This mode of interaction allows the grocer to collect advance demand information, which has been shown to reduce inventory costs in non-perishables. For perishable items where spoilage is a major cost driver, the effects of advance ordering on a grocer's daily operation is not yet clear. To investigate this, we develop an MDP-based model that reflects a modern grocer's inventory decision system. Key model characteristics are stochastic demand and random product shelf lives. The model solves for the optimal replenishment policy, and facilitates quantifying how next-day or two-day orders influence profitability. A numerical study is presented for various short-life products, and the results indicate that two-day orders can increase profit, reduce inventory and spoilage, while maintaining the overall availability level. These benefits increase as the replenishment product's shelf life decreases. We show that the average cart value, proportion of short life items, handling time, and order pick rate are strong determinants of the extent that two-day orders can offset omnichannel fulfillment cost. In some cases, there exists an attainable breakeven pick rate, such that the grocer's expected profit is higher with curbside advance orders than with traditional in-store purchases.

Predictive 3D Printing with IoT

Industry 4.0 marks a new industrial revolution centered around technologies that connect digital and physical realms, revamping how information is used to manage work. Two core enablers are the Internet of Things (IoT) and 3D printing. The former monitors the real-time status of a complex system, and the latter responds to that information with agile manufacturing. Nevertheless, how exactly this can be done remains unclear. To gain insights, we consider the context of a 3D printer supplying a critical part installed in multiple machines embedded with sensors and interconnected via IoT. While it is tempting to perceive that the marriage of 3D printing and IoT would make on-demand printing a reality, our results indicate that this is not necessarily so. The true benefit of the marriage is enabling predictive printing. In particular, it is optimal for the 3D printer to print-to-stock predictively in advance of demand, triggered by a system-lifetime-status dependent threshold. Whether it is optimal to print-on-advance-demand to achieve minimum inventory depends crucially on the printing speed. We further quantify the impact of IoT on system cost and inventory by separately assessing the impact of advance demand information from embedded sensors and that of IoT’s real-time information fusion from sensor interconnections. We demonstrate that information fusion intensifies the inventory reduction through advance demand information, and IoT’s impact hinges upon the effectiveness of embedded sensors. Our framework can be leveraged to aid IoT investment decisions and to help develop operating policies for predictive 3D printing.

Karışık Talep Bilgisi Kapsamında Toplu Sipariş Envanter Yönetimi: Bir Durum Çalışması

This study is concerned with analysing the past demand data and development of aninventory model with demand arising from deterministic which is known in advance and random sourcessimultaneously. Two different shortages are created for each demand type and in order to prevent modelto backlog the deterministic demand, very high shortage cost is given for deterministic demand. Thenumerical value of the parameters are obtained from a real case which the inventory system of aninformation and technological organization of a university. The main difference of this study from theprevious studies is that the order amount must be in palette quantity for a deterministic and stochasticdemand inventory problem. Under this constraint, an inventory model is developed and tested withseveral datasets. Assuming lead time as constant, the value of deterministic demand present in the systemand impact of palette constraint are investigated. These investigations are compared with the status quoin the case study. It has seen that the palette quantity behaves as safety stock for high level randomdemand. Recommendations based on the impacts of advance demand information, lead time and palletquantity are presented in terms of changing in ordering costs, holding costs and service level.

An extension of the reorder point method by using advance demand spike information

This article addresses a reorder point method with an extended inventory position. The inventory position is decreased by near future known demand spikes. This advance demand information helps to improve the performance of the reorder point method. The proposed extension leads to a hybrid model: make-to-stock for demand less than the spike threshold and make-to-order for demand greater than the spike threshold. Furthermore, the number of cycles is modeled more generally and takes into account that the replenishment order has lot-size Q or an integer multiple of Q. An iterative solution procedure is developed for the proposed model, and the numerical results are shown to underpin the usefulness of the approach.

Effects of different types of imperfect advance demand information in production systems

ABSTRACT One strategy to reduce inventories and increase on-time delivery is to use Advanced Demand Information (ADI) in which customers place their orders ahead of their due date. ADI can be divided into perfect or imperfect information. Under perfect ADI, customers send accurate demand information to the suppliers, specifying exact quantities and due dates. Under imperfect ADI, customer orders’ quantities and/or due dates may change over time or order cancellations may occur. This research focuses on the effects of three types of imperfect ADI on different production systems: changing due dates, changing order quantities, and cancellations. Three different model variations simulate a pull system, a push system, and a hybrid system. We found that only cancellations and changing order quantities had a significant effect on system performance. Generally, the pull and the hybrid system behaved similarly and proved to be more suitable for managing imperfect ADI than the push system.

Optimizing stock levels for service-differentiated demand classes with inventory rationing and demand lead times

In this paper, we study a service parts inventory management system for a single product at a parts distribution center serving two priority-demand classes: critical and non-critical. Distribution center keeps a common inventory pool to serve the two demand classes, and provides differentiated levels of service by means of inventory rationing. We assume a continuous review one-for-one ordering policy with backorders and Poisson demand arrivals. Only one demand class provides advance demand information whose orders are due after a deterministic demand lead time, whereas the orders of the other demand class need to be satisfied immediately. The problem has been studied before, but remained a challenging problem. The quality of the existing heuristic for estimating the critical class service levels can diminish significantly in some settings and the search routine for the service level optimization model relies on a brute force approach. Our contribution to the literature is twofold. For the given class of inventory replenishment and allocation policies, first we determine the form of the optimal solution to the service level optimization model, and then we derive an exact optimization routine to determine the optimal policy parameters provided the steady-state distribution is available. The computation of steady-state probabilities is needed only once. Second, we propose an alternative approach to estimate steady-state probabilities. By analyzing the limiting behavior of transition probabilities during infinitesimal time intervals, we are able to characterize the relationships between the steady-state probabilities, which satisfy nicely formed balance equations under the so-called Independence Assumption. In the numerical study section, we show that our approach provides superior performance in estimating service levels than the existing heuristic for all the examples considered. We also compare the performance of using the critical class service levels computed according to our method against the service levels computed by the existing heuristic, and show that our method can provide inventory savings up to 16.67%.

The Impact of Committing to Customer Orders in Online Retail

Online retailers are on a consistent drive to increase on-time delivery and reduce customer lead-time. However, in reality, an increasing share of consumers place orders early. Such Advance Demand Information can be deployed strategically to reduce costs and improve the customer service experience. This requires inventory and allocation policies that make optimal use of this information and that induce consumers to place their orders early. Online retail has been growing steadily, and an increasing number of online retailers not only offer customers a choice of lead-time, but also actively back-order missing items from a consumer basket. We develop new allocation policies that commit to a customer order upon arrival of the order rather than at the moment the order is due. We provide analytical results for the performance of these allocation policies and evaluate their behavior with real data from a large food retailer. Our policy leads to a higher fill-rate at the expense of a slight increase in average delay. The analysis based on real-life data suggests a size-able impact that should impact current best practices in online retail. With the changing landscape in online retail, customers are increasingly placing baskets of orders that they would like to receive at a planned and confirmed moment in time. Especially in grocery this has been growing fast. This fundamentally changes the strategic management of inventory. We demonstrate that online retailers should commit early to customer orders to enhance the customer service experience, and — eventually — to also create opportunities for reducing the cost of operations.