Daily retail demand forecasting using machine learning with emphasis on calendric special days

Demand forecasting is an important task for retailers as it is required for various operational decisions. One key challenge is to forecast demand on special days that are subject to vastly different demand patterns than on regular days. We present the case of a bakery chain with an emphasis on special calendar days, for which we address the problem of forecasting the daily demand for different product categories at the store level. Such forecasts are an input for production and ordering decisions. We treat the forecasting problem as a supervised machine learning task and provide an evaluation of different methods, including artificial neural networks and gradient-boosted decision trees. In particular, we outline and discuss the possibility of formulating a classification instead of a regression problem. An empirical comparison with established approaches reveals the superiority of machine learning methods, while classification-based approaches outperform regression-based approaches. We also found that machine learning methods not only provide more accurate forecasts but are also more suitable for applications in a large-scale demand forecasting scenario that often occurs in the retail industry.     

A goal programming model for the siting of multilevel EMS systems.

Facility siting models known as location covering techniques have proven to be useful particularly for emergency medical services (EMS) planning, given the importance of ambulances responding to demand within some maximum time constraint. These models represent a set of methods which focus the health planner's attention on the access of people to health care, since they attempt to “cover” people in need of service within some specified time standard.This research develops a technique for the locational planning of sophisticated EMS systems, characterized by multiple levels of emergency health services. Specifically, a two-tiered system with “basic life support” and “advanced life support” capabilities is modeled as a goal program.By applying location covering techniques within a goal programming framework, this study develops a method for the siting of multilevel EMS systems so that (1) each service level maximizes coverage of its own demand population, and (2) “back-up” coordination between levels is assured. The usefulness of this goal program as a health planning tool is evidenced in the model's explicit articulation of EMS policy objectives and its ability to link system levels in terms of “goal-directed behavior”. The working of this multilevel covering model is demonstrated by reference to EMS planning scenarios and related numerical examples.     

M5 competition uncertainty: Overdispersion,distributional forecasting,GAMLSS, and beyond

The M5 competition uncertainty track aims for probabilistic forecasting of sales of thousands of Walmart retail goods. We show that the M5 competition data face strong overdispersion and sporadic demand, especially zero demand. We discuss modeling issues concerning adequate probabilistic forecasting of such count data processes. Unfortunately, the majority of popular prediction methods used in the M5 competition (e.g. lightgbm and xgboost GBMs) fail to address the data characteristics, due to the considered objective functions. Distributional forecasting provides a suitable modeling approach to overcome those problems. The GAMLSS framework allows for flexible probabilistic forecasting using low-dimensional distributions. We illustrate how the GAMLSS approach can be applied to M5 competition data by modeling the location and scale parameters of various distributions, e.g. the negative binomial distribution. Finally, we discuss software packages for distributional modeling and their drawbacks, like the R package gamlss with its package extensions, and (deep) distributional forecasting libraries such as TensorFlow Probability.     

Forecasting spare part demand with installed base information: A review

The classical spare part demand forecasting literature studies methods for forecasting intermittent demand. However, the majority of these methods do not consider the underlying demand-generating factors. The demand for spare parts originates from the replacement of parts in the installed base of machines, either preventively or upon breakdown of the part. This information from service operations, which we refer to as installed base information, can be used to forecast the future demand for spare parts. This paper reviews the literature on the use of such installed base information for spare part demand forecasting in order to asses (1) what type of installed base information can be useful; (2) how this information can be used to derive forecasts; (3) the value of using installed base information to improve forecasting; and (4) the limits of the existing methods. This serves as motivation for future research.     

方案规划:市场经济体系下城市总体规划的有效工具

城市规划方案的核心内容包括对下列问题的回答:哪种土地利用类型,多大土地开发强度,在哪里,什么时候,为什么开发,同时如何通过交通发展将新开发的土地有机地联系起来,如何提供城市基础设施满足新增的城市空间发展.当然,城市规划也要回答如何将城市经济发展与环境保护,社会发展,文化和历史文物保护等连接起来.本文介绍方案规划,内容,要素,及其评价.指出方案规划定量地模拟未来城市发展,客观定量地评价不同的城市规划方案,避免或减少规划方案评价的主观因素,提高决策的科学性.     

Simulation modeling and optimization for ambulance allocation considering spatiotemporal stochastic demand

To ensure a timely response to emergencies, governments are obliged to implement effective ambulance allocation plans. In practice, an emergency medical service (EMS) system works in an uncertain environment, with stochastic demand, response-times, and travel-times. This uncertainty significantly affects ambulance allocation planning. However, few studies in this field adequately consider the effect of spatiotemporal uncertainty in demand, because it is difficult to measure it quantitatively. As a result, few analytic models capture the dynamic nature of an EMS system and, thus, the allocation plans they generate are not efficient in practice. Therefore, this study proposes a simulation-based optimization method for ambulance allocation. A simulation model is constructed to mimic the operational processes of an EMS system, and to evaluate the performance of an ambulance allocation plan in an uncertain environment. Gaussian mixture model clustering is used to derive the uncertain spatial demand. Then, the simulation generates emergency demand based on the obtained spatial distribution. A Gaussian-process-based search algorithm is used together with the simulation model to identify optimal solutions. To validate the proposed method, a case study is conducted using data on emergency patients in the Shanghai Songjiang District. Compared with the current plan adopted in Songjiang, the experimental results demonstrate that the delay time and frequency of the EMS system can be reduced significantly by employing the proposed methods. Furthermore, nearly 41% of the allocation cost can be saved.     

Forecasting systems in managing hospital services demand: a review of applicability and a measure of utility.

A comprehensive literature review of forecasting methodologies and their specific applications to managing hospital services demand provided a credible base for the ensuing study of current forecasting usage. A sample of 40 hospitals was analyzed to measure the current perceived urgency to utilize forecasting systems. These findings were then compared with perceived actual usage. The incidence of formal forecasting systems actually being utilized was lower than the perceived need to use such systems. Identification of principal methodologies utilized and an assessment of computer-assisted forecasting indicated that a strong reliance on qualitative, manually-derived methodologies still remains. Correlation analyses of key exogenous variables indicated that the larger sized hospitals utilized computerized methodologies and had the highest measures of perceived need for, and actual practice of, formal forecasting programs.     

Anticipating special events in Emergency Department forecasting

Accurate daily forecast of Emergency Department (ED) attendance helps roster planners in allocating available resources more effectively and potentially influences staffing. Since special events affect human behaviours, they may increase or decrease the demand for ED services. Therefore, it is crucial to model their impact and use them to forecast future attendance to improve roster planning and avoid reactive strategies. In this paper, we propose, for the first time, a forecasting model to generate both point and probabilistic daily forecast of ED attendance. We model the impact of special events on ED attendance by considering real-life ED data. We benchmark the accuracy of our model against three time-series techniques and a regression model that does not consider special events. We show that the proposed model outperforms its benchmarks across all horizons for both point and probabilistic forecasts. Results also show that our model is more robust with an increasing forecasting horizon. Moreover, we provide evidence on how different types of special events may increase or decrease ED attendance. Our model can easily be adapted for use not only by EDs but also by other health services. It could also be generalised to include more types of special events.     

Forecasting sales in the supply chain: Consumer analytics in the big data era

Forecasts have traditionally served as the basis for planning and executing supply chain activities. Forecasts drive supply chain decisions, and they have become critically important due to increasing customer expectations, shortening lead times, and the need to manage scarce resources. Over the last ten years, advances in technology and data collection systems have resulted in the generation of huge volumes of data on a wide variety of topics and at great speed. This paper reviews the impact that this explosion of data is having on product forecasting and how it is improving it. While much of this review will focus on time series data, we will also explore how such data can be used to obtain insights into consumer behavior, and the impact of such data on organizational forecasting.     

Classification-based model selection in retail demand forecasting

Retailers supply a wide range of stock keeping units (SKUs), which may differ for example in terms of demand quantity, demand frequency, demand regularity, and demand variation. Given this diversity in demand patterns, it is unlikely that any single model for demand forecasting can yield the highest forecasting accuracy across all SKUs. To save costs through improved forecasting, there is thus a need to match any given demand pattern to its most appropriate prediction model. To this end, we propose an automated model selection framework for retail demand forecasting. Specifically, we consider model selection as a classification problem, where classes correspond to the different models available for forecasting. We first build labeled training data based on the models’ performances in previous demand periods with similar demand characteristics. For future data, we then automatically select the most promising model via classification based on the labeled training data. The performance is measured by economic profitability, taking into account asymmetric shortage and inventory costs. In an exploratory case study using data from an e-grocery retailer, we compare our approach to established benchmarks. We find promising results, but also that no single approach clearly outperforms its competitors, underlying the need for case-specific solutions.     

Improving demand forecasting in the air cargo handling industry: a case study

Air transportation plays a crucial role in the agile and dynamic environment of contemporary supply chains. This industry is characterised by high air cargo demand uncertainty, making forecasting extremely challenging. An in-depth case study has been undertaken in order to explore and untangle the factors influencing demand forecasting and consequently to improve the operational performance of an air cargo handling company. It has been identified that in practice, the demand forecasting process does not provide the necessary level of accuracy, to effectively cope with the high demand uncertainty. This has a negative impact on a whole range of air cargo operations, but especially on the management of the workforce, which is the most expensive resource in the air cargo handling industry. Besides forecast inaccuracy, a range of additional hidden factors that affect operations management have been identified. A number of recommendations have been made to improve demand forecasting and workforce management.     

Screening the impacts of municipal service policy changes

The planning of municipal service delivery systems requires accurate forecasts of demand, and particularly of the effects the quality of service delivery has on demand. A metholology for this problem should meet three criteria, if it is to be useful for municipal planning: it must be low-cost and use generally available data; it must be based on user behavior, so that the effects of policy changes can be correctly attributed; and it must allow testing of the transferability of the results, since this is required for general forecasting use. This paper develops such a methodology, based on econometric analysis of data from a number of service areas within a number of regions, forming a double cross-section. Empirical tests of the methodology were performed for two local government services where the effect of service quality on demand is important: sewer and highway construction, which have been hypothesized to affect the patterns of development within regions; and solid waste collection, where the level of service provided affects how much waste enters the collection system and how much is littered, burned or recycled. The two case studies and other analyses suggest that the methodology is a useful tool for testing whether policy changes have an effect on the demand for service, but not for accurate demand forecasting. Thus, these simple models are relevant for the role of screening the effect of policy changes, but more detailed and localized approaches are necessary for system design.     

Forecasting high resolution electricity demand data with additive models including smooth and jagged components

Short-Term Load Forecasting (STLF) is a fundamental instrument in the efficient operational management and planning of electric utilities. Emerging smart grid technologies pose new challenges and opportunities. Although load forecasting at the aggregate level has been extensively studied, electrical load forecasting at fine-grained geographical scales of households is more challenging. Among existing approaches, semi-parametric generalized additive models (GAM) have been increasingly popular due to their accuracy, flexibility, and interpretability. Their applicability is justified when forecasting is addressed at higher levels of aggregation, since the aggregated load pattern contains relatively smooth additive components. High resolution data are highly volatile, forecasting the average load using GAM models with smooth components does not provide meaningful information about the future demand. Instead, we need to incorporate irregular and volatile effects to enhance the forecast accuracy. We focus on the analysis of such hybrid additive models applied on smart meters data and show that it leads to improvement of the forecasting performances of classical additive models at low aggregation levels.     

Retail forecasting: Research and practice

This paper reviews the research literature on forecasting retail demand. We begin by introducing the forecasting problems that retailers face, from the strategic to the operational, as sales are aggregated over products to stores and to the company overall. Aggregated forecasting supports strategic decisions on location. Product-level forecasts usually relate to operational decisions at the store level. The factors that influence demand, and in particular promotional information, add considerable complexity, so that forecasters potentially face the dimensionality problem of too many variables and too little data. The paper goes on to evaluate evidence on comparative forecasting accuracy. Although causal models outperform simple benchmarks, adequate evidence on machine learning methods has not yet accumulated. Methods for forecasting new products are examined separately, with little evidence being found on the effectiveness of the various approaches. The paper concludes by describing company forecasting practices, offering conclusions as to both research gaps and barriers to improved practice.     

Feasibility on the integration of passenger and freight transportation in rural areas: A service mode and an optimization model

Public transport operators in rural areas have been under pressure from weak profitability and emission issues. At the same time, scattered demand for transport has been preventing logistics systems from reaching the last mile in residential areas. Multimodal transport can synergistically integrate passenger and freight demand, increase transportation network coverage, and reduce the cost of transportation, while demand-driven services improve the flexibility and reliability of operational decisions. Therefore, this paper proposes a demand-driven passenger-and-freight-integration service (DDPFIS) mode. From the perspective of routing decisions, a new mixed-integer linear programming model based on the green vehicle routing problem is formulated to assist public transport operator’s complex decision-making. In the proposed model, vehicle capacity is fully utilized through a combination of passenger and freight demand so that optimal decisions are made about vehicle routing. Numerical experiments are designed and conducted based on realistic instances with the results indicating that: the DDPFIS mode enables effective integration of different demands, leading to high-level vehicle capacity utilization and cost reduction; and compared with two conventional models of vehicle routing problems, the proposed model achieves lower fuel consumption and cost for all problem sizes. In addition, some important management insights are provided, e.g., a greater proportion of integrated service nodes is not necessarily better; and it is more suitable to provide a service for rural residents who are relatively insensitive to time.     

Tracing business and environmental effects of environmental management systems—a study of networking small and medium‐sized enterprises using a joint environmental management system

In Hackefors Industrial District in Sweden, 26 small and medium‐sized enterprises (SMEs) have formed an environmental network and implemented a joint environmental management system (EMS) according to ISO 14001. Based on interviews with the environmental co‐ordinators at these enterprises, the effects on business and environmental efforts and impacts are analysed. It can be concluded that the joint EMS has resulted in better relations with important stakeholders, such as existing and potential customers. For example, three‐fifths said that their EMS had made it easier to receive a contract for the sale of products and services. Several environmental improvements have been observed and are presented in the paper, many of which are considered as consequences of the EMSs. Moreover, based on observations during the study, this paper discusses how boundaries and screening affect the connection between EMSs and environmental performance. Copyright © 2003 John Wiley & Sons, Ltd. and ERP Environment     

The Importance of the Diverse Drivers and Types of Environmental Innovation for Firm Performance

Today, firms are faced with a number of environmental challenges, such as global warming, pollution control and declining natural resources. While there is increasing pressure to deliver environmentally friendly products and services, little is known about what drives the many different types of environmental innovation, or how such pursuits' impact firm performance. Using a sample of 2181 firms, this paper examines the factors that drive nine different types of eco‐innovation in Ireland, and assesses how such innovations impact firm performance. We find that, while demand‐side, supply‐side and regulatory drivers impact on the likelihood of a firm engaging in eco‐innovation, the relative magnitudes of these impacts vary across the types of eco‐innovation considered. Moreover, we find that only two of the nine types of eco‐innovation positively impact firm performance. The results point to regulation and customer pressure as viable mechanisms through which firms can be encouraged to eco‐innovate. Copyright © 2014 John Wiley & Sons, Ltd and ERP Environment     

Challenges in designing,implementing and operating an environmental management system

Introducing an effective environmental management system (EMS) to an organization is a complex process. This complexity is belied by current EMS models that concentrate on EMS frameworks and components, and present a relatively simple approach to the process, especially the introduction and implementation phases. While these models outline what should be introduced, they provide little guidance on how EMSs may be implemented. Experience indicates that effective EMS introduction may be adversely affected by a number of conditions, but EMS literature has yet to recognize these barriers. There is a significant gap between EMS theory and application. This paper discusses the degree to which current EMS models address practical EMS design and implementation, barriers to successful EMS introduction, strategies and tactics for overcoming these barriers and implications for EMS practice. Copyright © 1999 John Wiley & Sons, Ltd and ERP Environment.     

Really changing the course: the limitations of environmental management systems for innovation

The paper broadens the scope of environmental management system (EMS) research by describing how EMSs can contribute to inertia in present production systems. In conjunction with other factors this inertia can inhibit dramatic shifts toward more sustainable technologies and systems. Our approach builds upon technological lock‐in theory, which focuses on market coordination and technological interdependencies as generators of inertia in technological systems. Building on this framework, we call attention to previously under appreciated non‐market social forces and institutional structures that can further reinforce lock‐in. We argue that the co‐evolutionary mechanisms that generate increasing returns for physical technologies may also be applied to social technologies, such as management systems. The paper describes the emergence of ‘EMS lock‐in’ as a path dependent evolution occurring within the context of the larger quality management paradigm. While EMS may initially produce improvements in environmental performance, EMS may also constrain organizational focus to the exploitation of present production systems, rather than exploring for superior innovations that are discontinuous. The paper questions the enthusiastic private and public sector support for EMS implementation and instead recommends an ambidextrous management approach that integrates foresight and broader stakeholder collaboration. Copyright © 2006 John Wiley & Sons, Ltd and ERP Environment.