Intermittent Demand Forecasting Research Articles

A Sporadic Classification and Regression-Based Approach to Intermittent Demand Forecasting in Smart Supply Chain

A Sporadic Classification and Regression-Based Approach to Intermittent Demand Forecasting in Smart Supply Chain

Improving demand forecasting for customers with missing downstream data in intermittent demand supply chains with supervised multivariate clustering

AbstractIn a collaborative supply chain arrangement like vendor‐managed inventory, information on product demand at the point of sale is expected to be shared among members of the supply chain. However, in practice, obtaining such information can be costly, and some members may be unwilling or unable to provide the necessary access to the data. As such, large collaborative supply chains with multiple members may operate under a mixed‐information scenario where point‐of‐sale demand information is not known for all customers. Other sources of demand information exist and are becoming more available along supply chains using Industry 4.0 technologies and can serve as a substitute, but the data may be noisy, distorted, and partially missing. Under mixed information, leveraging existing customers' point‐of‐sale demand to improve the intermittent demand forecast of customers with missing information has yet to be explored. We propose a supervised demand forecasting method that uses multivariate time series clustering to map multiple sources of demand data. Members with missing downstream demand data have their resulting demand forecast improved by averaging over customers with similar delivery patterns for their final demand forecast. Our results show up to a 10% accuracy improvement over traditional intermittent demand forecasting methods with missing information.

Navigating Uncertainty: Intermittent Demand Forecasting in the Furniture Manufacturing Industry through Clustering and Predictive - Case Study

Navigating Uncertainty: Intermittent Demand Forecasting in the Furniture Manufacturing Industry through Clustering and Predictive - Case Study

An adaptive multi-objective optimal forecast combination and its application for predicting intermittent demand

While time series forecasting models are generally trained by optimising certain forms of error, the end-user’s forecasting needs in a multi-objective setting can be broader, and often mutually conflicting. A production manager may prioritise high product fill rates and low average inventory resulting from a forecast over just low error. The conflict among multiple objectives is notably worrisome in intermittent demand forecasting, where error-minimising approaches can devalue the practitioner’s objectives. To address such forecasting problems, we propose an Adaptive Multi-objective Optimal Combination (AMOC) of forecasts which incorporates the end-user’s preferences across multiple objectives. We demonstrate the use of AMOC in a real-life application of intermittent demand forecasting for optimising four distinct inventory management objectives using five specialised forecasting methods across single-period and multi-period inventory handling scenarios. Additionally, we conduct a comprehensive experiment on a subset of M5 competition data to exhibit the robustness of the AMOC using 13 diverse forecasting methods and four statistical objectives.

Feature-based intermittent demand forecast combinations: accuracy and inventory implications

Intermittent demand forecasting is a ubiquitous and challenging problem in production systems and supply chain management. In recent years, there has been a growing focus on developing forecasting approaches for intermittent demand from academic and practical perspectives. However, limited attention has been given to forecast combination methods, which have achieved competitive performance in forecasting fast-moving time series. The current study examines the empirical outcomes of some existing forecast combination methods and proposes a generalised feature-based framework for intermittent demand forecasting. The proposed framework has been shown to improve the accuracy of point and quantile forecasts based on two real data sets. Further, some analysis of features, forecasting pools and computational efficiency is also provided. The findings indicate the intelligibility and flexibility of the proposed approach in intermittent demand forecasting and offer insights regarding inventory decisions.

Intermittent Demand Forecasting Using LSTM With Single and Multiple Aggregation

Intermittent demand data is data with infrequent demand with varying number of demand sizes. Intermittent demand forecasting is useful for providing inventory control decisions. It is very important to produce accurate forecasts. Based on previous research, deep learning models, especially MLP and RNN-based architectures, have not been able to provide better intermittent data forecasting results compared to traditional methods. This research will focus on analyzing the results of intermittent data forecasting using deep learning with several levels of aggregation and a combination of several levels of aggregation. In this research, the LSTM model is implemented into two traditional models that use aggregation techniques and are specifically used for intermittent data forecasting, namely ADIDA and MAPA. The result, based on tests on the six predetermined data, the LSTM model with aggregation and disaggregation is able to provide better test results than the LSTM model without aggregation and disaggregation.

A combined forecasting method for intermittent demand using the automotive aftermarket data

Intermittent demand forecasting is an important challenge in the process of smart supply chain transformation, and accurate demand forecasting can reduce costs and increase efficiency for enterprises. This study proposes an intermittent demand combination forecasting method based on internal and external data, builds intermittent demand feature engineering from the perspective of machine learning, predicts the occurrence of demand by classification model, and predicts non-zero demand quantity by regression model. Based on the strategy selection on the inventory side and the stocking needs on the replenishment side, this study focuses on the optimization of the classification problem, incorporates the internal and external data of the enterprise, and proposes two combination forecasting optimization methods on the basis of the best classification threshold searching and transfer learning, respectively. Based on the real data of auto after-sales business, these methods are evaluated and validated in multiple dimensions. Compared with other intermittent forecasting methods, the models proposed in this study have been improved significantly in terms of classification accuracy and forecasting precision, which validates the potential of combined forecasting framework for intermittent demand and provides an empirical study of the framework in industry practice. The results show that this research can further provide accurate upstream inputs for smart inventory and guarantee intelligent supply chain decision-making in terms of accuracy and efficiency.

Biasedness of forecast errors: an intermittent demand perspective

In the article it is claimed that certain ex post forecast errors demonstrate such a property as biasedness. A definition of forecast error biasedness is proposed and discussed. In the theoretical part, the most popular forecast errors, including errors useful in intermittent demand forecasting, are analyzed with regard to their biasedness. In the empirical part, properties of the considered forecast errors are verified for real intermittent demand time series. Forecasts are obtained, inter alia, by means of Croston's and TSB methods. In the conclusions unbiased forecast errors are emphasized. Furthermore, the best forecast errors for intermittent demand data are proposed. The presented considerations, aside from the theoretical part, might support decision systems in enterprises dealing with intermittent demand forecasting, such as distribution centers, warehouse centers etc.

Machine Learning Algorithms with Intermittent Demand Forecasting: An Application in Retail Apparel with Plenty of Predictors

Demand forecasting is a key factor for apparel retail stores to sustain their business, especially where there are variety of products and intermittent demand. In this study, two of the most popular machine learning methods, random forest (RF) and k-nearest neighbour (KNN), have been used to forecast retail apparel’s intermittent demand. Numerous variables that may have an effect on the sales, have been taken into account one of which is defined as “special day” that might trigger intermittence in the demand. During the application of the forecast, four different datasets were used to provide reliability. 28 different variables were used to increase accuracy of the forecasting and experience of the behaviours of the algorithms. Root mean square error (RMSE) was used to evaluate performance of the methods and as a result of this study, RF showed better performance in all four datasets comparing to KNN.

Forecasting of intermittent demands under the risk of inventory obsolescence

AbstractCroston and the other related methods, such as Syntetos‐Boylan approximation (SBA), are the most popular methods recommended in the literature for intermittent demand forecasting. However, these conventional methods are not considered suitable in inventory obsolescence as they do not update their forecast in the periods of zero demand. Therefore, in order to add to the methods suitable for the inventory obsolescence issue, we propose a new method that imparts flexibility to the SBA method. The proposed method updates forecast each period by the use of distinct smoothing constants for interdemand intervals. The method is further examined extensively on a simulated dataset considering gradual and abrupt obsolescence and an empirical dataset from the automotive sector. The study is not limited to assessing the forecasting accuracy but also focuses upon the inventory performance of the considered methods. The study results indicate the effectiveness of the proposed method, particularly under increased risk of obsolescence.

Accuracy of Intermittent Demand Forecasting Systems in the Enterprise

Purpose: The main purpose of this article is to find the best forecasting method for intermittent demand times series, from the company’s point of view. Design/Methodology/Approach: Intermittent demand forecasting systems were constructed based on the Croston’s, SBA, TSB, SES and MA methods. A real database from the warehouse center, containing over sixteen thousand items, was used. Accuracy measures were also discussed. Forecasting methods were compared for all products and for separate demand categories (intermittent, lumpy, erratic, smooth). Findings: It was determined that the TSB method outperforms other methods for all products. The worst procedures were found to be Croston’s and SBA, which performed even worse than SES or MA. The same conclusions were true for intermittent and lumpy categories. In case of erratic and smooth items different results were obtained. It was determined that the SBA method performed best, while the TSB method yielded the poorest results. Practical Implications: The main conclusion is that to judge accuracy of forecasting systems first the proper forecast error measures should be chosen. Based on obtained results, TSB method seems to be the best for intermittent demand times series and this method is recommended for enterprises dealing with intermittent demand. Originality/value: Since such error measures as MASE or scaled MAE favored an underestimated (or even zero) forecast, in the article a new error metric is proposed, which was named scaled Compound Error (sCE). It is a scaled error, and it considers forecast biasedness.

Intermittent demand forecasting for medical consumables with short life cycle using a dynamic neural network during the COVID-19 epidemic

Accurate demand forecasting is always critical to supply chain management. However, many uncertain factors in the market make this issue a huge challenge. Especially during the current COVID-19 outbreak, the shortage of certain types of medical consumables has become a global problem. The intermittent demand forecast of medical consumables with a short life cycle brings some new challenges, such as the demand occurring randomly in many time periods with zero demand. In this research, a seasonal adjustment method is introduced to deal with seasonal influences, and a dynamic neural network model with optimized model selection procedure and an appropriate model selection criterion are introduced as the main forecasting models. In addition, in order to reduce the impact of zero demand, it adds some input nodes to the neural network by preprocessing the original input data. Lastly, a modified error measurement method is proposed for performance evaluation. Experimental results show that the proposed forecasting framework is superior to other intermittent demand models.

Intermittent demand forecasting: a guideline for method selection

Intermittent demand shows irregular pattern that differentiates it from all other demand types. It is hard to forecasting intermittent demand due to irregular occurrences and demand size variability. Due to this reason, researchers developed ad hoc intermittent demand forecasting methods. Since intermittent demand has peculiar characteristics, it is grouped into categories for better management. In this paper, specialized methods with a focus of method selection for each intermittent demand category are considered. This work simplifies the intermittent demand forecasting and provides guidance to market players by leading the way to method selection based on demand categorization. By doing so, the paper will serve as a useful tool for practitioners to manage intermittent demand more easily.

We need to talk about intermittent demand forecasting

Operational Research (OR) is the ‘science of better’. People constantly try to get better, in practically all aspects of their personal and professional life, and thus OR is de facto a ubiquitous science. What might however not be that clear, is that the way we improve is driven by the very OR science, and the scientific results that constitute the respective body of literature, theory and practice. Of all the tasks, that can be related to the OR science, the one that more frequently we do, is forecasting. We do constantly try to estimate what is coming next, and we drive our decisions for each and every situation based on these forecasts: from where to put our money to who will be the best surgeon to operate us. Within the broad boundaries of OR, forecasting stands out as the most ubiquitous sub-discipline. In the forecasting literature, a lot of attention has been given to modeling fast-moving time series and building causal models; however, very limited attention has been given to intermittent time series and intermittent demand forecasting. In this research, we advocate for the broader use of intermittent demand forecasting methods for forecasting special events, as a simpler, faster, and robust alternative to more complex non-OR models. Furthermore, in a foresight context, we argue for a novel way of deciding the strategic planning horizon for phenomena prone to appearance of special events.

KESİKLİ TALEPLERİN TAHMİNLENMESİNDE ATA METOT VE CROSTON TEMELLİ METOTLARIN KARŞILAŞTIRILMASI

Intermittent demand forecasting is crucial for firms and commercial activities. Recently, many researchers have focused on forecasting methods for intermittent demand and proposed various forecasting techniques. The most prominent methods among these proposed techniques are the Croston method, which is based on exponential smoothing, and its two popular variations: SBA (Syntetos-Boylan Approximation), SBJ (Shale-Boylan-Johnston Approximation). Croston method is widely used in forecasting of intermittent demand and inventory (stock) control. Since these demands usually include zero values, using the ground breaking method developed by Croston in this data becomes inevitable. Nevertheless, there are some shortcomings to this method such as producing biased forecasts and for this reason its variations have been proposed. ATA method is a recently developed forecasting method which is an alternative to exponential smoothing. In this paper we propose a modification of ATA method that can be used for forecasting of intermittent demand. We will compare the results of the proposed approach to those of Croston and other forecasting methods used for intermittent demand forecasting.

A greedy aggregation–decomposition method for intermittent demand forecasting in fashion retailing

In this study, we solve a real-world intermittent demand forecasting problem for a fashion retailer in Singapore, where it has been operating retail stores and a warehouse for several decades. The demand for each stock keeping unit (SKU) at each store on each day needs to be determined to develop an effective and efficient inventory and logistics system for the retailer. The SKU-store-day demand is highly intermittent. In order to solve this challenging intermittent demand forecasting problem, we propose a greedy aggregation–decomposition method. It involves a new hierarchical forecasting structure and utilizes both aggregate and disaggregate forecasts, which differs from the classical bottom-up and top-down approach. The method is investigated on the real-world SKU-store-day demand database from this retailer in Singapore, and significantly outperforms other widely used intermittent demand forecasting methods. The proposed method also serves as a general self-improvement procedure for any intermittent time series forecasting method taking dual source of variations into account. Moreover, we introduce a revised mean absolute scaled error (RMASE) as a new accuracy measure for intermittent demand forecasting. It is a relative error measure, scale-independent, and compares with the error of zero forecasts.

Forecasting Spare Part Demand with Installed Base Information: A Review

The majority of the spare part literature studies intermittent demand forecasting. However, these methods typically do not consider the underlying demand generating factors. It seems reasonable to presume that the spare part demand can be explained by the service operations that require the use of these parts. This information can be helpful for forecasting purposes. In this article, we review the literature of such information from service operations, which we refer to as installed base information. The aim is twofold: First, by providing the academic community with a review on the literature concerning the use of installed base information (which is to the best of our knowledge non-existent), it can serve as a foundation for future academic research. Second, we offer practitioners insight on the potential of installed base information to improve their forecasts. This way we aim to stimulate appropriate data collection and implementation of installed base forecasting methods.

Intermittent Demand Forecasting in a Tertiary Pediatric Intensive Care Unit.

Forecasts of the demand for medical supplies both directly and indirectly affect the operating costs and the quality of the care provided by health care institutions. Specifically, overestimating demand induces an inventory surplus, whereas underestimating demand possibly compromises patient safety. Uncertainty in forecasting the consumption of medical supplies generates intermittent demand events. The intermittent demand patterns for medical supplies are generally classified as lumpy, erratic, smooth, and slow-moving demand. This study was conducted with the purpose of advancing a tertiary pediatric intensive care unit's efforts to achieve a high level of accuracy in its forecasting of the demand for medical supplies. On this point, several demand forecasting methods were compared in terms of the forecast accuracy of each. The results confirm that applying Croston's method combined with a single exponential smoothing method yields the most accurate results for forecasting lumpy, erratic, and slow-moving demand, whereas the Simple Moving Average (SMA) method is the most suitable for forecasting smooth demand. In addition, when the classification of demand consumption patterns were combined with the demand forecasting models, the forecasting errors were minimized, indicating that this classification framework can play a role in improving patient safety and reducing inventory management costs in health care institutions.

Parameter optimization of intermittent demand forecasting by using spreadsheet

Purpose – Accurate forecasting of intermittent demand is very important since parts with intermittent demand characteristics are very common. The purpose of this paper is to bring an easier way of handling the hard work of intermittent demand forecasting by using commonly used Excel spreadsheet and also performing parameter optimization. Design/methodology/approach – Smoothing parameters of the forecasting methods are optimized dynamically by Excel Solver in order to achieve the best performance. Application is done on real data of Turkish Airlines’ spare parts comprising 262 weekly periods from January 2009 to December 2013. The data set are composed of 500 stock-keeping units, so there are 131,000 data points in total. Findings – From the results of implementation, it is shown that using the optimum parameter values yields better performance for each of the methods. Research limitations/implications – Although it is an intensive study, this research has some limitations. Since only real data are considered, this research is limited to the aviation industry. Practical implications – This study guides market players by explaining the features of intermittent demand. With the help of the study, decision makers dealing with intermittent demand are capable of applying specialized intermittent demand forecasting methods. Originality/value – The study brings simplicity to intermittent demand forecasting work by using commonly used spreadsheet software. The study is valuable for giving insights to market players dealing with items having intermittent demand characteristics, and it is one of the first study which is optimizing the smoothing parameters of the forecasting methods by using spreadsheet in the area of intermittent demand forecasting.

간헐적 수요예측을 위한 부트스트랩 시뮬레이션 방법론 개발

Demand forecasting is the basis of management activities including marketing strategy. Especially, the demand of a part is remarkably important in supply chain management (SCM). In the fields of various industries, the part demand usually has the intermittent characteristic. The intermittent characteristic implies a phenomenon that there frequently occurs zero demands. In the intermittent demands, non-zero demands have large variance and their appearances also have stochastic nature. Accordingly, in the intermittent demand forecasting, it is inappropriate to apply the traditional time series models and/or cause-effect methods such as linear regression; they cannot describe the behaviors of intermittent demand. Markov bootstrap method was developed to forecast the intermittent demand. It assumes that first-order autocorrelation and independence of lead time demands. To release the assumption of independent lead time demands, this paper proposes a modified bootstrap method. The method produces the pseudo data having the characteristics of historical data approximately. A numerical example for real data will be provided as a case study.