Advances in Business and Management Forecasting: Volume 12

Cover of Advances in Business and Management Forecasting
Subject:

Table of contents

(12 chapters)

Section A Forecasting Applications

Abstract

The problem of missing children draws much attention of both governmental and nongovernmental organizations in China due to huge numbers of the missing children. According to the records of Baby Back Home network (BBHNet), a professional website to search missing children in China, 1,666 missing children have been found via releasing information on BBHNet; however, there are still 30,561 families searching for their children and 24,603 missing children are searching for biological parents through this website and have not succeeded yet. What is the difference between successful and unsuccessful cases in the aspect of released information? Motivated by this question, our research proposes to determine the crucial information in the process of searching missing children. A logistic regression model was developed on the data summarized from 500 succeed cases and 500 cases which have not succeed yet from BBHNet for forecasting success rate of searching missing children. The model identifies that the differences in terms of released information, number of children, address, and natural geographical features are the three most crucial factors that cause differences in the result of searching. This research can be used as a guide for improving the success rate of searching missing children and provide reference for developing a missing children information-sharing platform.

Abstract

The purpose of this paper is to introduce a new forecasting approach that involves a multicriteria scoring model, which is enhanced with regression analysis and optimization. We compare regression analysis versus our Enhanced Multicriteria Scoring Model by comparing the Error Sum of the Squares in case studies involving top selling automobiles and top Fortune 500 companies. In both the automobile and Fortune 500 case studies, our Enhanced Multicriteria Scoring was more accurate than regression analysis. In practice, our Enhanced Multicriteria Scoring Model should be compared with regression analysis, and the better of the two techniques should be used to forecast. In short, our Enhanced Multicriteria Scoring model is a “breakthrough” modeling technique that will help companies and organizations improve their forecasting.

Abstract

This is the second in a series of papers focused on alcohol and substance abuse rehabilitation centers. Centers face the ongoing challenge of validating outcomes to meet the burden of evidence for insurance companies. In the first paper, data mining was used to establish baseline patterns in treatment success rates, for the Futures: Palm Beach Rehabilitation Center, that have a direct impact on a client’s ability to receive insurance coverage for treatment programs. In this paper, we examine 2016 outcomes and report on facility efficacy, alumni progression and sobriety, and forecast treatment success rates (short and long term) in support of client insurability. Data collection has been standardized and includes admissions data, electronic medical records data, satisfaction survey data, post-discharge survey data, Centers for Disease Control (CDC) data, and demographic data. Clustering, partitioning, ANOVA, stepwise regression and stepwise Logistic regression are applied to the data to determine statistically significant drivers of treatment success.

Section B Predictive Analytics, Regression Analysis and Clustering in Forecasting

Abstract

We propose an oversampling technique to increase the true positive rate (sensitivity) in classifying imbalanced datasets (i.e., those with a value for the target variable that occurs with a small frequency) and hence boost the overall performance measurements such as balanced accuracy, G-mean and area under the receiver operating characteristic (ROC) curve, AUC. This oversampling method is based on the idea of applying the Synthetic Minority Oversampling Technique (SMOTE) on only a selective portion of the dataset instead of the entire dataset. We demonstrate the effectiveness of our oversampling method with four real and simulated datasets generated from three models.

Abstract

This research is directed toward predicting constituent behaviors of university giving from its alumni. A regression modeling analysis of the alumni giving of a major state university is developed using best subsets regression. Based on an extension of this modeling effort a clustering of alumni giving patterns will be developed.

Abstract

Multiple linear regression (MLR) is a commonly used statistical technique to predict future values. In this paper, we examine the situation in which a given time series dataset contains numerous observations of important predictor variables that can effectively be classified into groups based on their values. In such situations, cluster analysis is often employed to improve the MLR models predictive accuracy, usually by creating separate regressions for each cluster. We introduce a novel approach in which we use the clusters and cluster centroids as input data for the predictor variables to improve the predictive accuracy of the MLR model. We illustrate and test this approach with a real dataset on fleet maintenance.

Abstract

Forecasting is a vital part of the planning process of most private and public organizations. A number of extant measures: Mean Absolute Deviation (MAD), Mean Square Error (MSE) and Mean Absolute Percentage Error (MAPE), have been used to assist in judging the forecast accuracy, and concomitantly, the consequences of those forecasts. In this paper we introduce, evolve, and implement a practical and effective method for assessing the accuracy of forecasts, the Percent Forecast Error (PFE). We test and evaluate the PFE, and modified optimized PFE (MOPFE), against the MAD, MSE, and MAPE measures of forecast accuracy using three time series datasets.

Section C Time Series, Intermittent Data and Supply Chain Applications

Abstract

Control charts are designed to be effective in detecting a shift in the distribution of a process. Typically, these charts assume that the data for these processes follow an approximately normal distribution or some known distribution. However, if a data-generating process has a large proportion of zeros, that is, the data is intermittent, then traditional control charts may not adequately monitor these processes. The purpose of this study is to examine proposed control chart methods designed for monitoring a process with intermittent data to determine if they have a sufficiently small percentage of false out-of-control signals. Forecasting techniques for slow-moving/intermittent product demand have been extensively explored as intermittent data is common to operational management applications (Syntetos & Boylan, 2001, 2005, 2011; Willemain, Smart, & Schwarz, 2004). Extensions and modifications of traditional forecasting models have been proposed to model intermittent or slow-moving demand, including the associated trends, correlated demand, seasonality and other characteristics (Altay, Litteral, & Rudisill, 2012). Croston’s (1972) method and its adaptations have been among the principal procedures used in these applications. This paper proposes adapting Croston’s methodology to design control charts, similar to Exponentially Weighted Moving Average (EWMA) control charts, to be effective in monitoring processes with intermittent data. A simulation study is conducted to assess the performance of these proposed control charts by evaluating their Average Run Lengths (ARLs), or equivalently, their percent of false positive signals.

Abstract

There is a growing interest in fuzzy time series (FTS) forecasting, and several improvements are presented in the last few decades. Among these improvements, the development of causal models (i.e., multiple factor FTS) has sparked a particular literature dealing with the causal inference and its integration in the FTS framework. However, causality among variables is usually introduced as a subjective assumption rather than empirical evidence. As a result of arbitrary causal modeling, the existing multiple factor FTS models are developed with implicit forecasting failure. Since post-sample control (unknown future, as in the business practice) is usually ignored, the spurious accuracy gain through increasing factors is not identified by scholars. This paper discloses the use of causality in the FTS method, and investigates the spurious causal inference problem in the literature with a justification approach. It invalidates the contribution of dozens of previously published papers while justifying its claim with illustrative examples and a comprehensive set of experiments with random data, as well as real business data from maritime transportation (Baltic Dry Index).

Abstract

In the last few decades, there has been growing interest in forecasting with computer intelligence, and both fuzzy time series (FTS) and artificial neural networks (ANNs) have gained particular popularity, among others. Rather than the conventional methods (e.g., econometrics), FTS and ANN are usually thought to be immune to fundamental concepts such as stationarity, theoretical causality, post-sample control, among others. On the other hand, a number of studies significantly indicated that these fundamental controls are required in terms of the theory of forecasting, and even application of such essential procedures substantially improves the forecasting accuracy. The aim of this paper is to fill the existing gap on modeling and forecasting in the FTS and ANN methods and figure out the fundamental concepts in a comprehensive work through merits and common failures in the literature. In addition to these merits, this paper may also be a guideline for eliminating unethical empirical settings in the forecasting studies.

Abstract

The chapter examines a comprehensive review of cross-disciplinary literature in the domain of supply chain forecasting during research period 1991–2017, with the primary aim of exploring the growth of literature from operational to demand centric forecasting and decision making in service supply chain systems. A noted list of 15,000 articles from journals and search results are used from academic databases (viz. Science Direct, Web of Sciences). Out of various content analysis techniques (Seuring & Gold, 2012), latent sementic analysis (LSA) is used as a content analysis tool (Wei, Yang, & Lin, 2008; Kundu et al., 2015). The reason for adoption of LSA over existing bibliometric techniques is to use the combination of text analysis and mining method to formulate latent factors. LSA creates the scientific grounding to understand the trends. Using LSA, Understanding future research trends will assist researchers in the area of service supply chain forecasting. The study will be beneficial for practitioners of the strategic and operational aspects of service supply chain decision making. The chapter incorporates four sections. The first section describes the introduction to service supply chain management and research development in this domain. The second section describes usage of LSA for current study. The third section describes the finding and results. The fourth and final sections conclude the chapter with a brief discussion on research findings, its limitations, and the implications for future research. The outcomes of analysis presented in this chapter also provide opportunities for researchers/professionals to position their future service supply chain research and/or implementation strategies.

Cover of Advances in Business and Management Forecasting
DOI
10.1108/S1477-4070201712
Publication date
2017-10-26
Book series
Advances in Business and Management Forecasting
Editors
Series copyright holder
Emerald Publishing Limited
ISBN
978-1-78743-070-9
eISBN
978-1-78743-069-3
Book series ISSN
1477-4070