Lumpy Demand Research Articles

An ES-based model with contemporaneous and temporal aggregation for forecasting intermittent and lumpy retail demand

The demand for products in the retail industry is often characterized by intermittent and volatile patterns. Specifically, at the SKU level, the demand exhibits intermittent and lumpy behavior, which presents challenges for accurate forecasting due to demand fluctuations and interval uncertainty. This study proposes an exponential smoothing (ES)-based model, called ES-C-T, that incorporates contemporaneous and temporal aggregation to forecast intermittent and lumpy retail demand. The ES-C-T model consists of three stages. Firstly, the ES model predicts the sales of each product by aggregating contemporaneously across all stores, and the resulting predictions are allocated to the SKU level using a weight vector. Secondly, the ES model forecasts the sales of each SKU by aggregating temporally within each store. Finally, the ES-C-T model derives a weight coefficient based on the predictions from the first and second stages, adjusts the initial predictions, and utilizes this as the final forecast. To validate the effectiveness of the ES-C-T model, sales data from a large Chinese convenience store chain are employed. The results demonstrate that the proposed ES-C-T model outperforms the benchmark model in terms of MAE, RMSE, and WRMSSE, effectively predicting retail sales for intermittent and lumpy demand.

The Influence of Repair Quality on Aircraft Spare Part Demand Variability

Accurate estimation of spare part demand is challenging in the case of intermittent or lumpy demand, characterised by infrequent demand occurrence and variability in demand size. While prior research has considered the effect of exogenous variables on spare part demand, there is a lack of research considering the effects of repair quality and aggregated spare part demand behaviour across fleets of assets under the influence of multiple simultaneously acting drivers of failure. This research provides new insights towards the problem of estimating variable spare part demand through modelling and simulation of the effects of multiple, simultaneously considered spare part demand drivers. In particular, a contribution to the state of the art is introduced by the use of a Branching Poisson Process (BPP) to model repair quality effects for spare part demand generation in conjunction with several demand drivers. The approach is applied in a numerical study which involves component failure characteristics based on real-life data from an aircraft maintenance, repair and overhaul (MRO) provider. It is shown that repair quality improvements drive down the variance in the demand and the total number of failures over time, and outperform the effect of environmental drivers of failure in terms of demand generation.

Switching robust neural network control of perishable inventory with fixed shelf life products under time-varying uncertain demand

Managing the inventories of perishable items becomes a more challenging task when the demand for such items is uncertain and has intermittent, lumpy or erratic character. In this study practical problem of perishable inventory products, and control is presented and solved. This is an extended version of the research presented in [Cholodowicz E, Orlowski P (2022) Robust control of perishable inventory with uncertain lead time using neural networks and genetic algorithm. In: International Conference on Computational Science. Springer, pp 46–59]. The objective of this study is to find order quantities for the perishable inventory system, that are optimal in terms of stock level, fill rate and outdating. To find the solution, a new approach is developed. The proposed approach is a combination of an artificial neural network, control theory and hybrid optimization. The proposed controller consists of robust neural network controllers which are tuned for selected perturbation bound. Weights switching operation is performed based on the demand uncertainty estimation. The validity of the results is tested on intermittent, lumpy, smooth and erratic demand data series coming from the food industry. One of the key findings of this study is that applying the proposed Switching Robust Neural Network controller provides a significant decrease in cost function in comparison to Robust Neural Network controllers. It is found that the biggest decrease is for smooth demand and the smallest one for the lumpy demand pattern. What distinguishes our work from the current state of the art is the fact that we do not limit that demand is deterministic and constant, we propose a method which calculates the optimal order quantities to minimize costs under different patterns of demand which is uncertain.

Lumpy and intermittent retail demand forecasts with score-driven models

Irregular demand in retail is characterized by stock keeping units (SKUs) that present high intermittency, and simultaneously, high erraticness (classified as lumpy demand) or low erraticness (classified as intermittent demand), following the classification of Syntetos et al. (2005). These SKUs are basically defined by periods of zero sales interleaved with positive sales producing series with some degree of variability. Many SKUs at the store/daily level can be characterized as presenting such a type of demand. Therefore methods for adequately forecasting irregular time series are necessary for proper inventory management. This article derives models for intermittent and lumpy time series using the framework of score-driven models as developed by Creal et al. (2013) and Harvey (2013). More precisely we derive Poisson, negative binomial, hurdle Poisson, and hurdle negative binomial models and apply them to real data obtained from a large Brazilian retail chain, comparing the performance of the proposed models to adequate competing methods from the ‘slow’/intermittent demand forecasting literature. Forecasting accuracy is evaluated based on point forecasts and the entire predictive distribution. Our results show that the score-driven models perform well compared to intermittent traditional forecasting methods, providing competitive forecasting models for irregular demand in retailing.

Demand Forecasting Tool For Inventory Control Smart Systems

With the availability of data and the increasing capabilities of data processing tools, many businesses are leveraging historical sales and demand data to implement smart inventory management systems. Demand forecasting is the process of estimating the consumption of products or services for future time periods. It plays an important role in the field of inventory control and Supply Chain, since it enables production and supply planning and therefore can reduce delivery times and optimize Supply Chain decisions. This paper presents an extensive literature review about demand forecasting methods for time-series data. Based on analysis results and findings, a new demand forecasting tool for inventory control is proposed. First, a forecasting pipeline is designed to allow selecting the most accurate demand forecasting method. The validation of the proposed solution is executed on Stock&Buy case study, a growing online retail platform. For this reason, two new methods are proposed: (1) a hybrid method, Comb-TSB, is proposed for intermittent and lumpy demand patterns. Comb- TSB automatically selects the most accurate model among a set of methods. (2) a clustering-based approach (ClustAvg) is proposed to forecast demand for new products which have very few or no sales history data. The evaluation process showed that the proposed tool achieves good forecasting accuracy by making the most appropriate choice while defining the forecasting method to apply for each product selection.

Lean manufacturing implementation in time of crisis: the case of Estaleiro Atlântico Sul

The implementation of Lean Manufacturing (LM) philosophies in the 1980s and 1990s revolutionized manufacturing in high volume flow-oriented production processes. In project-oriented industries such as shipbuilding, long lead times, lumpy demand, and dependence on external and often international suppliers have made LM implementation challenging. This paper analyzes lean manufacturing implementation at Estaleiro Atlântico Sul (EAS) a shipyard located in an underdeveloped region in northeastern Brazil. EAS was the recipient of multiple oil tanker contracts from the Brazilian oil company Petrobras, but was unable to meet delivery deadlines and suffered cost overruns until a strong LM culture was introduced. From the EAS case, we make suggestions for a more appropriate lean manufacturing implementation in an emerging economy context. This is especially relevant in those situations associated with special project types of manufacturing initiatives such as shipbuilding, aviation, construction projects and other forms of low volume high complexity and other long-lead time production operations.

Fuzzy DEMATEL approach for agile supplier selections performance criteria

The strategy of agile supplier selections (ASS) process has adopted the recent era due to global competitive edges in a rapidly changing business environment. The sustainable agile performance criteria are the key necessity for market variations and more customer responsiveness. Therefore, the adaptation of ASS process is a key requirement to overcome the market variations and influence by number’s criteria. ASS is a major issue in Supply Chain Management (SCM), due to various uncertainties of market demand, lumpy demand, mismatch of supply and demand patterns, in these causes’ selection of supplier procedure is a difficult task in the automotive industry. Due to volatile market demand and more customer responsiveness, it is stimulating that inter-organization to balances the effective and efficient customer needs in volatile market demand patterns. This problem will be resolved by incorporating with human judgment skill capability in linguistic scale patterns. ASS has employed such method as the Fuzzy logic and DEMATEL approaches to perform better in global competitiveness. It strives to sustain the volatile market demand by appropriate ASS performance criteria. With the help of the literature survey, 14 agile supplier selection criteria have selected for better influence or support for ASS procedures.

A Novel Hybrid Artificial Intelligence Based Methodology for the Inventory Routing Problem

In this paper, a new hybrid method including simulation optimization and artificial intelligence based simulation is created to solve the inventory routing problem (IRP) in which three different routing strategies are evaluated for uneven demand patterns including intermittent, erratic, and lumpy demand. The proposed method includes two phases. In the first phase, a nondominated sorting genetic algorithm II based simulation is employed to perform a multi-objective search for the IRP where the objectives of the method are total supply chain cost minimization and average service level maximization. In the second phase, artificial neural network based simulation is used to adjust the reorder point and order-up-to-level by forecasting the customer demand at each replenishment time. The results of the study demonstrated that the average service level is at least 98.54% in the supply chain. From this, it can be concluded that the proposed method can provide a tremendous opportunity to improve the average service level under uncertain environments. In addition, it is determined that different routing strategies can be selected for different demand patterns according to the considered performance measures.

A comparative study of forecasting methods for sporadic demand in an Auto Service Station

Spare parts are essential in the automobile sector and forecasting of spare parts has always been the vital prospects in an automobile service parts station. In this paper, a comparison and efforts have been made at the service station of a reputed organisation to reduce the errors in demand forecasting of intermittent demand items. The errors are compared for various methods using mean absolute scaled error (MASE) and Syntetos and Boylan approximation (SBA) method which exhibited the least error for intermittent demand and lumpy demand pattern. While single exponential smoothing method is used for smooth and erratic demand pattern. All calculations are done in MS Excel and solver tool to find optimal values of smoothing parameters.

Inventory policy for relining roll spare parts to minimize total cost of inventory with periodic review (R,s,Q) and periodic review (R,S) (Case study: PT. Z)

PT. Z is a company that focus on steel industry in Indonesia. This company produces steel plates and coil. Relining roll is one kind of spare parts. The function is to reduce thickness of steel. Relining roll used in almost of machines in cold rolling mill. However, there is a problem in supply of spare parts called overstock in January-December 2017. The effect of overstock is high cost on holding inventory. The result of ABC analysis, there are seven spare parts with A category which are four spare parts with slow moving demand, two spare parts with erratic demand, and one spare parts with lumpy demand. Spare parts with slow and erratic demand use periodic review (R,s,Q) policy and spare parts with lumpy demand use periodic review (R,S) policy. The result of calculation of using periodic review in proposed condition is 99,98%. And the result of calculation of total cost inventory using periodic review (R,s,Q) and periodic review (R,S) is Rp 3.019.768 or 90,31% lower than actual condition.

LUMPY DEMAND FORECASTING USING LINEAR EXPONENTIAL SMOOTHING, ARTIFICIAL NEURAL NETWORK, AND BOOTSTRAP

Lumpy demand represents the circumstances when a demand for an item has a large proportion of periods having zero demand. This certain situation makes the time series methods might become inappropriate due to the model’s inability to capture the demand pattern. This research aims to compare several forecasting methods for lumpy demand that is represented by the demand of spare part. Three forecasting methods are chosen; Linear Exponential Smoothing (LES), Artificial Neural Network (ANN), and Bootstrap. The Mean Absolute Scaled Error (MASE) is used to measure the forecast performance. In order to gain more understanding on the effect of the forecasting method on spare parts inventory management, inventory simulation using oil and gas company’s data is then conducted. Two inventory parameters; average inventory and service level; are used to measure the performance. The result shows that ANN is found to be the best method for spare part forecasting with MASE of 0,761. From the inventory simulation, the appropriate forecasting method on spare parts inventory management is able to reduce average inventory by 11,9% and increase service level by 10,7%. This result justifies that selecting the appropriate forecasting method is one of the ways to achieve spare part inventory management’s goal.

Pengendalian Persediaan Untuk Mengurangi Biaya Total Persediaan Dengan Pendekatan Metode Periodic Review (R,s,S) Power Approximation Pada Suku Cadang Consumable (Studi Kasus : Job Pertamina Talisman Jambi Merang)

Spare parts is one of the production support components which plays an important role for the survival<br />of gas production in the gas processing facility owned by SKN JOB Pertamina Talisman Jambi Merang. The<br />high inventory level increased the high inventory cost for the industry which get the benefit from the efficiency<br />of processes and resources. This research involved consumable spare parts for Solar Turbine engine as much<br />as 25 SKUs with demand character patterned lumpy demand and Poisson distribution. The implementation<br />of policies using Periodic Review (R, s, S) with Power Approximation approach in the inventory system<br />capable to generate a lower total cost inventory by pressing the backorder volume, the booking volume and the<br />inventory levels in a balanced manner. Calculation of Periodic Review (R, s, S) with Power Approximation<br />approach resulted inventory parameter which was able to press the total cost of inventory at 8.54% lower and<br />increase the service level by 1.11%.

A hybrid spares demand forecasting method dedicated to mining industry

• A new method addressing the problem of spares lumpy demand forecasting is proposed. • The method combines information criteria, regression modeling and ANN. • An algorithm for efficiency analysis on variables selection methods was developed. • A new application domain is presented – the mining industry. • Research shows that the method is more efficient than traditional methods. The paper addresses the problem of lumpy demand forecasting which is typical for spare parts. Several prediction methods are presented in the paper - traditional techniques based on time series and advanced methods which use artificial neural networks. The paper presents a new hybrid spares demand forecasting method dedicated to mining companies. The method combines information criteria, regression modeling and artificial neural networks. The paper also discusses simulation research related to efficiency assessment of the chosen variable selection methods and its application in the newly developed forecasting method. The assessment of this method is conducted by a comparison with traditional methods and is based on selected forecast errors.

Capacity planning with technology replacement by stochastic dynamic programming

Technology replacement is capital intensive and highly risky in fast-paced high-tech industries along lumpy demand. This article proposes a solution to decision-making related to (i) technology replacement policy and (ii) capacity plan of resources to satisfy customer demand under technological changes. The addressed problem is modeled by stochastic dynamic programming for technology replacement in conjunction with an integer programming for simultaneous capacity planning. The overall objective is to maximize the expected net present profit over a finite time horizon. The problem is solved by a pattern search-genetic algorithm. Experiment results indicate that a near optimal solution is achieved in finite time.

An empirical investigation of comparative performance of approximate and exact corrections of the bias in Croston's method in forecasting lumpy demand

An empirical investigation of comparative performance of approximate and exact corrections of the bias in Croston's method in forecasting lumpy demand

An empirical investigation of comparative performance of approximate and exact corrections of the bias in Croston's method in forecasting lumpy demand

A positive bias in Croston's method, which had been developed to forecast intermittent demand, was reported by Syntetos and Boylan (2001). They proposed an approximate correction. Subsequently, Shale et al. (2006) proposed an 'exact' correction. Both corrections were derived analytically. The mathematical analysis establishes the superiority of the exact correction over both Croston's method and the approximate correction. We empirically investigate whether or not there are significant improvements in statistical forecast accuracy as well as inventory control performance obtained by applying the approximate or exact correction when forecasting lumpy demand. Using extensive simulation experiments, we find overall superior forecast accuracy of the bias correction methods over both simple exponential smoothing and Croston's methods. However, the exact correction yielded the same or only marginally better accuracy measures compared with the approximate correction. Moreover, in terms of inventory control performance, we observe marginal differences in inventory on hand and backlogs.

Another look at estimators for intermittent demand

In this paper we focus on forecasting for intermittent demand data. We propose a new aggregation framework for intermittent demand forecasting that performs aggregation over the demand volumes, in contrast to the standard framework that employs temporal (over time) aggregation. To achieve this we construct a transformed time series, the inverse intermittent demand series. The new algorithm is expected to work best on erratic and lumpy demand, as a result of the variance reduction of the non-zero demands. The improvement in forecasting performance is empirically demonstrated through an extensive evaluation in more than 8000time series of two well-researched spare parts data sets from the automotive and defence sectors. Furthermore, a simulation is performed so as to provide a stock-control evaluation. The proposed framework could find popularity among practitioners given its suitability when dealing with clump sizes. As such it could be used in conjunction with existing popular forecasting methods for intermittent demand as an exception handling mechanism when certain types of demand are observed.

Managing inventory systems of slow-moving items

Slow-moving demand patterns frequently occur with spare parts as well as items in decentralized retail supply chains with large assortments. These patterns are commonly called lumpy since they exhibit comparably high demand variation and a high fraction of zero-demand events. In this paper, we examine two distribution-based approaches to model lumpy demand processes for inventory control: (i) a generalized hurdle negative binomial model, and (ii) a worst-case non-parametric model that is derived using a test-based approach. Considering a base stock inventory policy, we examine a set of lumpy time series from the industry to exemplify the suitability and benefit of the proposed approaches for managing inventory systems of slow-moving items.

JOINT MAINTENANCE AND SPARE COMPONENT PROVISIONING POLICY FOR k-OUT-OF-n SYSTEMS

This study develops an analytic framework for joint modeling of age-based preventive maintenance and (s, Q) spare component provisioning policy for k-out-of-n:G systems with i.i.d. nonrepairable components. We assume that during system maintenance, instead of discarding the whole system, only failed components are replaced by spares if the on-handspares are sufficient. The objective is to determine a proper preventive maintenance interval and the ordering parameters to minimize the undiscounted long run average cost under a system availability constraint. Our study sheds light on the lumpy demand scenario in the problems of joint modeling of preventive maintenance and spare provisioning.

Collaborative capacity sharing among manufacturers on the same supply network horizontal layer for sustainable and balanced returns

To deal with volatile demand and rapidly changing manufacturing technologies for sustainable returns, as a solution, collaborative capacity sharing (CCS) among manufacturers at the same horizontal layer in supply networks is discussed in this research, especially focusing on a long-term aspect. Such horizontal collaboration can minimise manufacturers’ lost sales, as well as maximise their production capacity utilisation in a long-term period against lumpy demand. Hence, to help manufacturers determine whether and with whom they have to collaborate a CCS protocol based on a theoretical analysis is developed. It is a distributed decision protocol suggesting an effective coalition for each manufacturer. Furthermore, for well-balanced distribution of resulting profits to each manufacturer, two procedures are proposed: (1) determination of appropriate substitution production cost and (2) bids among manufacturers/coalitions. To evaluate the effect of those processes, two types of CCS protocols are designed – CCS-(1) and CCS-(2); only CCS-(2) performs those procedures. A numerical experiment is conducted to compare the performance of four models: No collaboration, complete collaboration, and two types of selective collaboration by CCS-(1) and CCS-(2). The performance of CCS-(2) is at least equal to or better than other models with higher and balanced returns.