Incorporating support vector machines with multiple criteria decision making for financial crisis analysis

Feature selection is an essential pre-processing technique in data mining that eliminates redundant or unrepresentative attributes and improves the performance of classifiers. However, a classifier with different feature selection approaches results in diverse outcomes. Thus, determining how to integrate feature selection methods and yield an appropriate feature set is an issue worth further study. Based on ensemble learning, this investigation develops a SVMMCDM (support vector machines with multiple criteria decision making) model that employs various feature selection techniques as data preprocessing schemes and then uses SVM for financial crisis prediction. The study uses MCDM to determine the most suitable feature selection mechanism when many performance criteria are considered. After the feature selection mechanism has been determined, the study decomposes the SVM to obtain support vectors and predicted labels which are then fed into a decision tree to generate rules. The numerical results for the ex-ante and ex-post periods relative to the financial tsunami show that the proposed SVMMCDM model is an effective way to predict a financial crisis and can provide useful rules for decision makers.     

GMADM-based attributes selection method in developing prediction model

Attribute Selection is an important issue for developing a prediction model, however, how to determine an effective attribute selection algorithm is an important but difficult issue. Attribute selection can effectively delete the irrelevant and redundant attributes to increase the prediction accuracy, and evaluating attribute selection methods usually need to consider several criteria such as accuracy, type I error, and type II error. In this paper, the selected attribute process is modeled as a group multiple attributes decision making (GMADM) problem. In evaluating different GMACD methods, the most results usually are consistently, But there are some situations where the evaluated outcomes have different results. The GMADM method is useful tool for evaluating attribute selection algorithms, and the TOPSIS is capable of identifying a compromised solution when different GMADM method result in conflicting rankings. Therefore, this paper proposes an objective (persuasive) GMADM-based attributes selection method to solve this disagreement and help decision makers pick the most suitable method. After verification, the proposed model is more persuasive to evaluate the attributes selection methods for developing prediction model.     

Empirical Bayesball Remixed: Empirical Bayes Methods for Longitudinal Data

Empirical Bayes methods for Gaussian and binomial compound decision problems involving longitudinal data are considered. A recent convex optimization reformulation of the nonparametric maximum likelihood estimator of Kiefer and Wolfowitz (Annals of Mathematical Statistics 1956; 27 : 887–906) is employed to construct nonparametric Bayes rules for compound decisions. The methods are illustrated with an application to predict baseball batting averages, and the age profile of batting performance. An important aspect of the empirical application is the general bivariate specification of the distribution of heterogeneous location and scale effects for players that exhibits a weak positive association between location and scale attributes. Prediction of players' batting averages for 2012 based on performance in the prior decade using the proposed methods shows substantially improved performance over more naive methods with more restrictive treatment of unobserved heterogeneity. Comparisons are also made with nonparametric Bayesian methods based on Dirichlet process priors, which can be viewed as a regularized, or smoothed, version of the Kiefer–Wolfowitz method. Copyright © 2016 John Wiley & Sons, Ltd.     

Stratified network mapping decision making technique based decision support framework for R&D budget allocation in South Korea

In this research work, we proposed and developed a stratified network mapping (SNM) decision making method and used it to improve the industry–university specialization in R&D in each region selected in this study. The proposed method considers the influence of criteria on and their priority in alternatives performance evaluation process. By analyzing the influence of these criteria on decision-making, we can easily improve the performance of alternatives. The SNM gives a clear understanding of each alternatives performance efficiency level. It explores possible and inefficient states and high-level influence states in inefficient states. Narrowly using multi-criteria decision-making methods to rank alternatives does not improve the performance of alternatives. The proposed method helps rank alternatives and improve the performance level of alternatives in each state. We analyzed the R&D investment of central and local governments of South Korea. It is an attempt to invigorate and facilitate R&D collaboration using a decision support model. We analyzed industry–academia research networks and enhanced the efficiency of the research.     

Sustainable Supplier Selection in Megaprojects: Grey Ordinal Priority Approach

Due to mounting environmental and social challenges, supplier selection has become one of the most critical tasks of project-oriented organizations. Because supplier selection can affect the long-term success and profitability of the organizations and their projects, directly, embracing sustainability can add value in the equation. Considering sustainability measures can positively guide project managers in making better decisions for the projects in the long term. Therefore, the current study attempts to provide a conceptual model for selecting the best supplier based on a sustainability framework in megaprojects. Meanwhile, decision-making methods can be employed as a proper tool to find the best supplier. Ordinal priority approach (OPA) is a recent development in multiple criteria decision making (MCDM), while it has many benefits compared with other methods like analytic hierarchy process (AHP) and technique for order of preference by similarity to ideal solution (TOPSIS). However, this method cannot consider multiple ranks during the decision-making process, and using an uncertainty approach feels strongly. Grey systems theory (GST) can consider uncertainties with no need for large sample or proposing membership function. Hence, the current study employed the GST to consider multiple ranks for criteria and alternatives in the OPA method. This is the first time that a sustainable supplier selection framework has been presented for megaprojects with the aid of the Grey OPA (OPA-G) method. Finally, a case study has been examined to evaluate the performance of the proposed approach. The results show that the proposed approach can be used in real-world situations and it has acceptable performance under uncertainty conditions.     

A hybrid multi-criteria decision making approach for strategic retail location investment: Application to Turkish food retailing

Retail location selection decision is a critical and complex process which requires the evaluation and aggregation of multiple criteria and also the usage of appropriate data related to them. This study handles the problem at a strategic level and proposes a Monte Carlo simulation based multi-criteria strategic location decision model for food retailing. This model integrates two multi-criteria decision making (MCDM) methods which are Hesitant Analytic Hierarchy Process (H-AHP) and Grey Relational Analysis (GRA) methods. Firstly, H-AHP method is used to obtain the weights of criteria to be used in GRA based on the experts' judgements. Secondly, simulation based GRA is used for ranking the alternative locations. Finally, the effectiveness and the applicability of the proposed model is illustrated with an application of strategic location investment decision of food retail stores in Turkey.     

Mining the R&D innovation performance processes for high-tech firms based on rough set theory

The research and development (R&D) innovation of firms continues to be viewed as an important source of competitive advantage to academics and practitioners. To explore and extract the R&D innovation decision rules, it is important to understand how the R&D innovation rule-base works. However, many studies have not yet adequately induced and extracted the decision rule of R&D innovation and performance based on the characteristics and components of the original data rather than on post-determination models. The analysis of this study is grounded in the taxonomy of induction-related activities using a rough set theory approach or rule-based decision-making technique to infer R&D innovation decision rules and models linking R&D innovation to sales growth. The rules developed using rough set theory can be directly translated into a path-dependent flow network to infer decision paths and parameters. The flow network graph and cause-and-effect relationship of decision rules are heavily exploited in R&D innovation characteristics. In addition, an empirical case of R&D innovation performance will be illustrated to show that the rough sets model and the flow network graph are useful and efficient tools for building R&D innovation decision rules and providing predictions. We will then illustrate that integrating the flow network graph with rough set theory can fully reflect the characteristics of R&D innovation, and, through the established model, we can obtain a more reasonable result than with artificial influence.     

Decisionmetrics: A decision-based approach to econometric modelling

An approach to developing a possibly misspecified econometric model that will be used as the beliefs of an expected utility maximiser is proposed. This approach builds on a novel objective function that measures the value of predictive distributions in decision-making and is used in model estimation, selection and evaluation. The methods proposed also provide an econometric approach for developing arbitrary parametric action rules such as technical trading rules. The approach is compared in detail with existing methods and is applied in the context of a CARA investor's decision problem where analytical and empirical results suggest it is very effective.     

Forecasting consumer credit card adoption: what can we learn about the utility function?

How to accurately predict customers’ adoption behavior is becoming more important and challenging to many credit card marketers as competition increases. This calls for more knowledge about the consumer utility function and the corresponding decision behavior. In this study, we challenge the commonly used logit model which implies linear utility function and constant marginal rate of substitution (MRS) with a neural network model that can accommodate nonlinear utility function and changing MRS between card attributes. Using the data from a national survey of credit card usage, we find that the neural network model significantly outperforms the logit in predicting consumer card adoption decisions. Our results indicate that consumers do not make linear tradeoffs between card attributes and the MRS between card features does not remain constant even within the same demographic group.     

医疗数据挖掘的特点、过程及方法

近年来,医疗数据资料持续爆炸性增长,在治疗技术不断提升的同时也带来了新的问题——数据丰富,知识贫乏。由此,引入了新的处理方式——数据挖掘。医疗数据挖掘面向整个医疗数据库或医疗信息集合,为其提供知识、规则和决策。本文分析了医疗数据的特点和该领域知识获取的特点、步骤及方法。     

基于任人唯亲视角的组织任用分析

人是组织的核心,组织选拔、任用人才是组织发展的关键环节。任人唯亲作为组织任用的一种表现形式,在所有文化中广泛存在,但是人们一直对其持批判态度。通过观察组织任用现实可以发现,任人唯亲具有一定的合理性。领导根据"亲"的关系准则(信任准则、信任预期准则、任务绩效准则和亲缘准则)来决定任用对象,这些关系准则受领导价值准则的影响,因此要规范领导的价值准则,才能确保组织任用成效。     

基于启发式规则的现货配船算法研究

针对远洋运输行业船舶承租人的现货配船问题,以快速地找出尽可能多的潜在的匹配方案,减少匹配误差为最终目标;从多属性匹配的思想出发,提出有效的属性描述方法、属性匹配损失惩罚的计算方法以及收益计算方法。借助启发式算法的灵活性、易于与业务特定相结合的优势,构建了对应的多属性约束模型,定义了合理的启发式规则,将各种约束分散在多个阶段考虑,又很好地限制了解空间规模,从而快速地寻求较佳匹配方案。     

基于粗糙集和C-均值聚类支持向量机的员工绩效评估方法

利用粗糙集的约简算法及类边界集分别选出影响绩效的核心因素和样本的边界集,将其应用于C-均值聚类网络得到具有概率信息(权重)的样本,作为支持向量机(SVM)的输入建立员工绩效评估模型。实例表明,该方法拟合率高,且性能优于SVM算法。     

Predicting the failures of prediction markets: A procedure of decision making using classification models

Prediction markets have been an important source of information for decision makers due to their high ex post accuracies. Nevertheless, recent failures of prediction markets remind us of the importance of ex ante assessments of their prediction accuracy. This paper proposes a systematic procedure for decision makers to acquire prediction models which may be used to predict the correctness of winner-take-all markets. We commence with a set of classification models and generate combined models following various rules. We also create artificial records in the training datasets to overcome the imbalanced data issue in classification problems. These models are then empirically trained and tested with a large dataset to see which may best be used to predict the failures of prediction markets. We find that no model can universally outperform others in terms of different performance measures. Despite this, we clearly demonstrate a result of capable models for decision makers based on different decision goals.     

Modelling and Forecasting Fiscal Variables for the Euro Area*

In this paper, we assess the possibility of producing unbiased forecasts for fiscal variables in the Euro area by comparing a set of procedures that rely on different information sets and econometric techniques. In particular, we consider autoregressive moving average models, Vector autoregressions, small‐scale semistructural models at the national and Euro area level, institutional forecasts (Organization for Economic Co‐operation and Development), and pooling. Our small‐scale models are characterized by the joint modelling of fiscal and monetary policy using simple rules, combined with equations for the evolution of all the relevant fundamentals for the Maastricht Treaty and the Stability and Growth Pact. We rank models on the basis of their forecasting performance using the mean square and mean absolute error criteria at different horizons. Overall, simple time‐series methods and pooling work well and are able to deliver unbiased forecasts, or slightly upward‐biased forecast for the debt–GDP dynamics. This result is mostly due to the short sample available, the robustness of simple methods to structural breaks, and to the difficulty of modelling the joint behaviour of several variables in a period of substantial institutional and economic changes. A bootstrap experiment highlights that, even when the data are generated using the estimated small‐scale multi‐country model, simple time‐series models can produce more accurate forecasts, because of their parsimonious specification.     

Assessing the effectiveness of the Malcolm Baldrige National Quality Award model with municipal government

This study examines the applicability of the MBNQA 2002 criteria to the government sector and contributes to the growing body of literature that addresses the need for performance metrics for government organizations. As the MBNQA is being proposed and pilot tested in government organizations, this work provides support for the transference and application of the model to government services in a municipal government.This study demonstrates the first structural model test using Partial Least Square (PLS) of an instrument that was based on a one-to-one item to criteria correspondence. We collected data from a city government and used PLS to analyze the survey data and tested the MBNQA model fit. The findings of this study show that the proposed Malcolm Baldrige National Quality Award (MBNQA) criteria-based instrument provides a viable set of measures for a municipal government to review and measure their business (organization) processes. These measures can enhance decision making about resource allocations because such measures allow evaluation of processes and a better understanding of the integration among these processes.     

Ethical climate and pro-social rule breaking in the workplace

Pro-social rule breaking (PSRB), rule-breaking to promote the interests of the organization, is a burgeoning topic on the scholarly landscape, but drivers of this behavior remain largely unexplained. This paper seeks to extend theory on PSRB by conceptualizing this behavior as an ethical decision requiring tradeoffs and ethical assessments. Specifically, we offer a model of PSRB that contextualizes the behavior within Victor and Cullen's (1988) five-dimensional typology of organizational ethical climate. We offer a set of propositions that provides theory on the role of each climate type on PSRB, as well as additional theorizing about salient individual attributes that impact PSRB. In addition to clarifying PSRB as an ethical decision, this paper offers theory at multiple levels of analysis on what drives PSRB. Specifically core self-evaluations are proposed as antecedents to PSRB. This theorizing is also integrated into literature on HR policy and HR decision-making implications of the model for HR practitioners are discussed, and a set of future research directions are offered.     

贝叶斯非线性分层模型在多元索赔准备金评估中的应用

本文将贝叶斯非线性分层模型应用于基于不同业务线的多元索赔准备金评估中,设计了一种合适的模型结构,将非线性分层模型与贝叶斯方法结合起来,应用WinBUGS软件对精算实务中经典流量三角形数据进行建模分析,并使用MCMC方法得到了索赔准备金完整的预测分布。这种方法扩展并超越了已有多元评估方法中最佳估计和预测均方误差估计的研究范畴。在贝叶斯框架下结合后验分布实施推断对非寿险公司偿付能力监管和行业决策具有重要作用。     

Multi-cultural leadership teams and organizational identification in international joint ventures

Many international joint ventures (IJVs) fare poorly. An important factor is that members of an IJV top management team (TMT), which generally comprises people from different cultures, often find it difficult to work together. In this paper we argue that social identity theory and organizational identification processes can help us understand why this is so. We propose that factionalism in a TMT is a significant hazard posed by member identification with different parents. In addition, identification with both the IJV and a parent firm can lead to significant role conflict for IJV top managers. Factionalism and role conflict in turn can result in poor intra-TMT communications and inefficient decision making. Literature in social identity theory and organizational identification suggests that the relative status and power of parents as well as successes of IJVs can affect TMT members' identification with the IJV or the parent company. Preliminary field interviews provide general support for these propositions. Our analysis suggests that organizational identity and identification can be a valuable tool to facilitate the understanding of TMT functioning and IJV performance.     

Supplier selection using a multi-criteria decision aid method

An ever-increasing trend in today's industrial firms is to exploit outsourcing for those products and activities deemed to be outside the company's core business. Given the financial importance and the multi-objective nature of supplier selection decision, in this paper an effort is made to highlight those aspects that are crucial to process qualitative and quantitative performance measures. In this paper, the contribution of a multi-criteria decision aid method ( ) to such problems is investigated, together with how to allow for a simultaneous change of the weights (importance of performance criteria), generating results that can be easily analysed statistically, performing an innovative sensitivity analysis. By way of example, the model is applied to a mid-sized Italian firm operating in the field of public road and rail transportation. The whole suppliers selection model presented ( techniques plus high-dimensional sensitivity analysis) seems to be a useful additional tool inside the final choice phase of a supplier selection process. Finally, potential issues for future research are presented.