The performance of the global bottom-up approach in the M5 accuracy competition: A robustness check

The M5 accuracy competition has presented a large-scale hierarchical forecasting problem in a realistic grocery retail setting in order to evaluate an extended range of forecasting methods, particularly those adopting machine learning. The top ranking solutions adopted a global bottom-up approach, by which is meant using global forecasting methods to generate bottom level forecasts in the hierarchy and then using a bottom-up strategy to obtain coherent forecasts for aggregate levels. However, whether the observed superior performance of the global bottom-up approach is robust over various test periods or only an accidental result, is an important question for retail forecasting researchers and practitioners. We conduct experiments to explore the robustness of the global bottom-up approach, and make comments on the efforts made by the top-ranking teams to improve the core approach. We find that the top-ranking global bottom-up approaches lack robustness across time periods in the M5 data. This inconsistent performance makes the M5 final rankings somewhat of a lottery. In future forecasting competitions, we suggest the use of multiple rolling test sets to evaluate the forecasting performance in order to reward robustly performing forecasting methods, a much needed characteristic in any application.     

DeepAR: Probabilistic forecasting with autoregressive recurrent networks

Probabilistic forecasting, i.e., estimating a time series’ future probability distribution given its past, is a key enabler for optimizing business processes. In retail businesses, for example, probabilistic demand forecasts are crucial for having the right inventory available at the right time and in the right place. This paper proposes DeepAR, a methodology for producing accurate probabilistic forecasts, based on training an autoregressive recurrent neural network model on a large number of related time series. We demonstrate how the application of deep learning techniques to forecasting can overcome many of the challenges that are faced by widely-used classical approaches to the problem. By means of extensive empirical evaluations on several real-world forecasting datasets, we show that our methodology produces more accurate forecasts than other state-of-the-art methods, while requiring minimal manual work.     

组合负荷预测方法综述

电力系统负荷具有很多不确定因素,针对单一模型进行负荷预测时,预测精度不高这一问题,可采用组合预测法将多种预测方法所得的预测值进行加权平均而得到最终预测结果,以满足现代电力对负荷预测结果的准确性、快速性和智能化的要求。该文首先简要介绍了几种常用的负荷预测方法,接着详细介绍了组合负荷预测的研究现状及确定组合预测中各模型最优权重的几种方法,最后介绍了组合负荷预测模型的误差修正方法,对提高负荷预测的准确性有一定的现实意义。     

A fast and scalable ensemble of global models with long memory and data partitioning for the M5 forecasting competition

This work presents key insights on the model development strategies used in our cross-learning-based retail demand forecast framework. The proposed framework outperforms state-of-the-art univariate models in the time series forecasting literature. It has achieved 17th position in the accuracy track of the M5 forecasting competition, which is among the top 1% of solutions.     

Parameter-efficient deep probabilistic forecasting

Probabilistic time series forecasting is crucial in many application domains, such as retail, ecommerce, finance, and biology. With the increasing availability of large volumes of data, a number of neural architectures have been proposed for this problem. In particular, Transformer-based methods achieve state-of-the-art performance on real-world benchmarks. However, these methods require a large number of parameters to be learned, which imposes high memory requirements on the computational resources for training such models. To address this problem, we introduce a novel bidirectional temporal convolutional network that requires an order of magnitude fewer parameters than a common Transformer-based approach. Our model combines two temporal convolutional networks: the first network encodes future covariates of the time series, whereas the second network encodes past observations and covariates. We jointly estimate the parameters of an output distribution via these two networks. Experiments on four real-world datasets show that our method performs on par with four state-of-the-art probabilistic forecasting methods, including a Transformer-based approach and WaveNet, on two point metrics (sMAPE and NRMSE) as well as on a set of range metrics (quantile loss percentiles) in the majority of cases. We also demonstrate that our method requires significantly fewer parameters than Transformer-based methods, which means that the model can be trained faster with significantly lower memory requirements, which as a consequence reduces the infrastructure cost for deploying these models.     

Combination of long term and short term forecasts, with application to tourism demand forecasting

Forecast combination is a well-established and well-tested approach for improving the forecasting accuracy. One beneficial strategy is to use constituent forecasts that have diverse information. In this paper we consider the idea of diversity being accomplished by using different time aggregations. For example, we could create a yearly time series from a monthly time series and produce forecasts for both, then combine the forecasts. These forecasts would each be tracking the dynamics of different time scales, and would therefore add diverse types of information. A comparison of several forecast combination methods, performed in the context of this setup, shows that this is indeed a beneficial strategy and generally provides a forecasting performance that is better than the performances of the individual forecasts that are combined.As a case study, we consider the problem of forecasting monthly tourism numbers for inbound tourism to Egypt. Specifically, we consider 33 individual source countries, as well as the aggregate. The novel combination strategy also produces a generally improved forecasting accuracy.     

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.     

The integration of forecasting and strategic planning

The paper analyzes the use of information in companies planning strategically versus those which are not. This contrast is used to build the case for developing strategic forecasting capability which focuses on a variety of environments, is proactive and interactive, and creates a need for different kinds of data bases and forecasting techniques.     

Forecasting retail sales using alternative models

This paper explores the issues associated with adapting forecasting techniques used by manufacturers to produce accurate forecasts for retail sales. A case study is presented that is developed using a retail situation because retailers often view their sales forecasting problems as being very different from a manufacturer's problems. Sales volumes are dramatically impacted by competitor promotional actions, discounts, store promotions and weather. Finally, consumption holidays like Christmas, Easter, Mother's day, have a large impact on sales as well as back to school shopping. The findings in this paper indicate that forecasting retail sales can be accomplished with a high degree of accuracy.     

Forecast combinations of computational intelligence and linear models for the NN5 time series forecasting competition

In this work we introduce the forecasting model with which we participated in the NN5 forecasting competition (the forecasting of 111 time series representing daily cash withdrawal amounts at ATM machines). The main idea of this model is to utilize the concept of forecast combination, which has proven to be an effective methodology in the forecasting literature. In the proposed system we attempted to follow a principled approach, and make use of some of the guidelines and concepts that are known in the forecasting literature to lead to superior performance. For example, we considered various previous comparison studies and time series competitions as guidance in determining which individual forecasting models to test (for possible inclusion in the forecast combination system). The final model ended up consisting of neural networks, Gaussian process regression, and linear models, combined by simple average. We also paid extra attention to the seasonality aspect, decomposing the seasonality into weekly (which is the strongest one), day of the month, and month of the year seasonality.     

Macroeconomic forecasting using structural factor analysis

The use of a small number of underlying factors to summarize the information from a much larger set of information variables is one of the new frontiers in forecasting. In prior work, the estimated factors have not usually had a structural interpretation and the factors have not been chosen on a theoretical basis. In this paper we propose several variants of a general structural factor forecasting model, and use these to forecast certain key macroeconomic variables. We make the choice of factors more structurally meaningful by estimating factors from subsets of information variables, where these variables can be assigned to subsets on the basis of economic theory. We compare the forecasting performance of the structural factor forecasting model with that of a univariate AR model, a standard VAR model, and some non-structural factor forecasting models. The results suggest that our structural factor forecasting model performs significantly better in forecasting real activity variables, especially at short horizons.     

Becoming A Leader In A Complex Organization

For a new leader, the process of entering and establishing a position of leadership in a complex organization presents a major challenge. This challenge seems particularly acute when authority, goals and technology are ambiguous, as in many professional service organizations. In this paper, we integrate ideas from the literature on socialization and role theory as well as that on executive succession processes to view new leader integration as a mutual adjustment process between two trajectories – that of the organization and that of the new leader. It is argued that this may lead to four possible types of integration outcomes: assimilation, transformation, accommodation and parallelism. Drawing on a case study of a large hospital, the paper identifies several mechanisms that can be mobilized by the new leader to enhance his or her room for manœuvre as the integration process evolves. The mechanisms can be classified as collaborative or affirmative, with each type having different risks and advantages. The case analysis further reveals that leader integration processes may be differentiated between different activity domains, dynamic over time (as the use of one type of integration approach alters the potential for another later), and interactive across different activity domains (as events in one part of the organization have consequences for those occurring in another).     

销售预测在成品油物流配送中的应用

通过对成品油在零售端的销售进行预测,可以确定未来油品的销售趋势。结合该销售趋势,可以提供对油品合理的配送时间和配送数量,从而保证成品油零售端处于合理的库存水平。     

Automatic selection of unobserved components models for supply chain forecasting

For many companies, automatic forecasting has come to be an essential part of business analytics applications. The large amounts of data available, the short life-cycle of the analysis and the acceleration of business operations make traditional manual data analysis unfeasible in such environments. In this paper, an automatic forecasting support system that comprises several methods and models is developed in a general state space framework built in the SSpace toolbox written for Matlab. Some of the models included are well-known, such as exponential smoothing and ARIMA, but we also propose a new model family that has been used only very rarely in this context, namely unobserved components models. Additional novelties include the use of unobserved components models in an automatic identification environment and the comparison of their forecasting performances with those of exponential smoothing and ARIMA models estimated using different software packages. The new system is tested empirically on a daily dataset of all of the products sold by a franchise chain in Spain (166 products over a period of 517 days). The system works well in practice and the proposed automatic unobserved components models compare very favorably with other methods and other well-known software packages in forecasting terms.     

Multi-step forecasting in emerging economies: An investigation of the South African GDP

To forecast at several, say h, periods into the future, a modeller faces a choice between iterating one-step-ahead forecasts (the IMS technique), or directly modeling the relationship between observations separated by an h-period interval and using it for forecasting (DMS forecasting). It is known that structural breaks, unit-root non-stationarity and residual autocorrelation may improve DMS accuracy in finite samples, all of which occur when modelling the South African GDP over the period 1965–2000. This paper analyzes the forecasting properties of 779 multivariate and univariate models that combine different techniques of robust forecasting. We find strong evidence supporting the use of DMS and intercept correction, and attribute their superior forecasting performance to their robustness in the presence of breaks.     

Global energy forecasting competition 2017: Hierarchical probabilistic load forecasting

The Global Energy Forecasting Competition 2017 (GEFCom2017) attracted more than 300 students and professionals from over 30 countries for solving hierarchical probabilistic load forecasting problems. Of the series of global energy forecasting competitions that have been held, GEFCom2017 is the most challenging one to date: the first one to have a qualifying match, the first one to use hierarchical data with more than two levels, the first one to allow the usage of external data sources, the first one to ask for real-time ex-ante forecasts, and the longest one. This paper introduces the qualifying and final matches of GEFCom2017, summarizes the top-ranked methods, publishes the data used in the competition, and presents several reflections on the competition series and a vision for future energy forecasting competitions.     

Recent advances in intra-hour solar forecasting: A review of ground-based sky image methods

As the penetration of solar energy generation into power systems keeps rising, intra-hour solar forecasting (IHSF) is becoming increasingly important for the secure and economical operation of a power system. One major difficulty in providing very accurate IHSF emanates from rapid cloud changes in the sky. The ground-based sky image (GSI) provides the intuitive information of intra-hour cloud changes and has thus been widely utilized in studies on IHSF. This paper presents a systematic review of the state-of-the-art of ground-based sky image-based intra-hour solar forecasting (GSI-IHSF). To our knowledge, we first propose a generic framework of GSI-IHSF consisting of four modules, i.e., sky image acquisition, sky image preprocessing, cloud forecasting, and solar forecasting. Then, as for each module, this paper introduces its core function, shows the major challenges, briefly reviews several extensively used techniques, summarizing research trends. Finally, this paper offers a prospect of GSI-IHSF research, discusses recent advances that demonstrate the potential for a great improvement in forecast accuracy, pointing out some new requirements and challenges that should be further investigated in the future.     

Long-term forecasting of fuel demand at theater entry points

Managing the distribution of fuel in theater requires Army fuel planners to forecast demand at the strategic level to ensure that fuel will be in the right place, at the right time, and in the amounts needed. This work presents a simulation approach to forecasting that accounts for the structure of the supply chain network when aggregating the demand of war fighters across the theater over the forecasting horizon. The resulting empirical distribution of demand at the theater entry point enables planners to identify forecast characteristics that impact their planning process, including the amplitudes and temporal positions of peaks in demand, and the estimated lead time to the point of use. Experimentation indicates that the forecasts are sensitive to the pattern of war fighter demand, the precise structure of the in-theater supply chain network, and the constraints and uncertainty present in the network, all of which are critical planning considerations.     

The M5 competition: Background,organization, and implementation

The M5 competition follows the previous four M competitions, whose purpose is to learn from empirical evidence how to improve forecasting performance and advance the theory and practice of forecasting. M5 focused on a retail sales forecasting application with the objective to produce the most accurate point forecasts for 42,840 time series that represent the hierarchical unit sales of the largest retail company in the world, Walmart, as well as to provide the most accurate estimates of the uncertainty of these forecasts. Hence, the competition consisted of two parallel challenges, namely the Accuracy and Uncertainty forecasting competitions. M5 extended the results of the previous M competitions by: (a) significantly expanding the number of participating methods, especially those in the category of machine learning; (b) evaluating the performance of the uncertainty distribution along with point forecast accuracy; (c) including exogenous/explanatory variables in addition to the time series data; (d) using grouped, correlated time series; and (e) focusing on series that display intermittency. This paper describes the background, organization, and implementations of the competition, and it presents the data used and their characteristics. Consequently, it serves as introductory material to the results of the two forecasting challenges to facilitate their understanding.     

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.