Search results

This study presents finite element (FE) and generalized regression neural network (GRNN) approaches for modeling multiple crack growth problems and predicting crack-growth directions under the influence of multiple crack parameters.

To determine the crack-growth direction in aluminum specimens, multiple crack parameters representing some degree of crack propagation complexity, including crack length, inclination angle, offset and distance, were examined. FE method models were developed for multiple crack growth simulations. To capture the complex relationships among multiple crack-growth variables, GRNN models were developed as nonlinear regression models. Six input variables and one output variable comprising 65 training and 20 test datasets were established.

The FE model could conveniently simulate the crack-growth directions. However, several multiple crack parameters could affect the simulation accuracy. The GRNN offers a reliable method for modeling the growth of multiple cracks. Using 76% of the total dataset, the NN model attained an R2 value of 0.985.

The models are presented for static multiple crack growth problems. No material anisotropy is observed.

In practical crack-growth analyses, the NN approach provides significant benefits and savings.

The proposed GRNN model is simple to develop and accurate. Its performance was superior to that of other NN models. This model is also suitable for modeling multiple crack growths with arbitrary geometries. The proposed GRNN model demonstrates its prediction capability with a simpler learning process, thus producing efficient multiple crack growth predictions and assessments.

Alongside structural equation modeling (SEM), the complementary technique of partial least squares (PLS) path modeling helps researchers understand relations among sets of observed variables. Like SEM, PLS began with an assumption of homogeneity – one population and one model – but has developed techniques for modeling data from heterogeneous populations, consistent with a marketing emphasis on segmentation. Heterogeneity can be expressed through interactions and nonlinear terms. Additionally, researchers can use multiple group analysis and latent class methods. This chapter reviews these techniques for modeling heterogeneous data in PLS, and illustrates key developments in finite mixture modeling in PLS using the SmartPLS 2.0 package.

Artificial neural network (ANN) models, part of the discipline of machine learning and artificial intelligence, are becoming more popular in the marketing literature and in marketing practice. This paper aims to provide a series of tests between ANN models and competing predictive models.

A total of 46 pairs of models were evaluated in an objective model-building environment. Either logistic regression or multiple regression models were developed and then were compared to ANN models using the same set of input variables. Three sets of B2B data were used to test the models. Emphasis also was placed on evaluating small samples.

ANN models tend to generate model predictions that are more accurate or the same as logistic regression models. However, when ANN models are compared to multiple regression models, the results are mixed. For small sample sizes, the modeling results are the same as for larger samples.

Like all marketing research, this application is limited by the methods and the data used to conduct the research. The findings strongly suggest that, because of their predictive accuracy, ANN models will have an important role in the future of B2B marketing research and model-building applications.

ANN models should be carefully considered for potential use in marketing research and model-building applications by B2B academics and practitioners alike.

The research contributes to the B2B marketing literature by providing a more rigorous test on ANN models using B2B data than has been conducted before.

This chapter describes tenets of complexity theory including the precept that within the same set of data X relates to Y positively, negatively, and not at all. A consequence to this first precept is that reporting how X relates positively to Y with and without additional terms in multiple regression models ignores important information available in a data set. Performing contrarian case analysis indicates that cases having low X with high Y and high X with low Y occur even when the relationship between X and Y is positive and the effect size of the relationship is large. Findings from contrarian case analysis support the necessity of modeling multiple realities using complex antecedent configurations. Complex antecedent configurations (i.e., 2–7 features per recipe) can show that high X is an indicator of high Y when high X combines with certain additional antecedent conditions (e.g., high A, high B, and low C) – and low X is an indicator of high Y as well when low X combines in other recipes (e.g., high A, low R, and high S), where A, B, C, R, and S are additional antecedent conditions. Thus, modeling multiple realities – configural analysis – is necessary, to learn the configurations of multiple indicators for high Y outcomes and the negation of high Y. For a number of X antecedent conditions, a high X may be necessary for high Y to occur but high X alone is almost never sufficient for a high Y outcome.

This paper aims to overcome the problem that the single structure of the driving term of the grey prediction model is not adapted to the complexity and diversity of the actual modeling objects, which leads to poor modeling results.

Firstly, the nonlinear law between the raw data and time point is fully mined by expanding the nonlinear term and the range of order. Secondly, through the synchronous optimization of model structure and parameter, the dynamic adjustment of the model with the change of the modeled object is realized. Finally, the objective optimization of nonlinear driving term and cumulative order of the model is realized by particle swarm optimization PSO algorithm.

The model can achieve strong compatibility with multiple existing models through parameter transformation. The synchronous optimization of model structure and parameter has a significant improvement over the single optimization method. The new model has a wide range of applications and strong modeling capabilities.

A novel grey prediction model with structure variability and optimizing parameter synchronization is proposed.

The highlights of the paper are as follows:

1. A new grey prediction model with a unified nonlinear structure is proposed.

2. The new model can be fully compatible with multiple traditional grey models.

3. The new model solves the defect of poor adaptability of the traditional grey models.

4. The parameters of the new model are optimized by PSO algorithm.

5. Cases verify that the new model outperforms other models significantly.

A new grey prediction model with a unified nonlinear structure is proposed.

The new model can be fully compatible with multiple traditional grey models.

The new model solves the defect of poor adaptability of the traditional grey models.

The parameters of the new model are optimized by PSO algorithm.

Cases verify that the new model outperforms other models significantly.

To review and address current approaches and limitations to modeling change over time in social entrepreneurship research.

The article provides a narrative review of different practices used to assess change over time. It also shows how different research questions require different methodologies for assessing changes over time. Finally, it presents worked examples for modeling these changes.

Our review suggests that there is a lack of research in social entrepreneurship that takes into account the many different considerations for addressing how time influences outcomes.

This chapter introduces an analytic technique to social entrepreneurship that effectively models changes in predictors and outcomes even when data are non-normal or nested across time or levels of analysis.

The techniques for representing and analyzing business processes are referred to as business process modeling. Many business process modeling methods and their associated tools have been used to capture the characteristics of business processes. However, most methods view business processes from different perspectives and have different features and capabilities. Thus, an important research question is how process designers should select appropriate modeling methods for their BPR initiatives. In this paper, we propose a framework for selecting business process modeling methods based on modeling objectives. This framework can serve as the basis for evaluating modeling methods and generating selection procedures. A general selection procedure is also described. We use an expense claim process as an example to illustrate the application of the selection procedure.

The purpose of this paper is to propose an effective knowledge elicitation method and representation scheme that empowers humanitarian assistance/disaster relief (HA/DR) analysts and experts to create analytic models without the aid of data scientists and methodologists while addressing the issues of complexity, collaboration, and emerging technology across a diverse global network of HA/DR organizations.

The paper used a mixed-methods research approach, with qualitative research and analysis to select the model elicitation method, followed by quantitative data collection and evaluation to test the representation scheme. A simplified analytic modeling approach was created based on emerging activity-based intelligence (ABI) analytic methods.

Using open source data on the Syrian humanitarian crisis as the reference mission, ABI analytic models were proven capable in modeling HA/DR scenarios of physical systems, nonphysical systems, and thinking.

As a data-agnostic approach to develop object and network knowledge, ABI aligns with the objectives of modeling within multiple HA/DR organizations.

Using an analytic method as the basis for model creation allows for immediate adoption by analysts and removes the need for data scientists and methodologists in the elicitation phase. Applying this highly effective cross-domain ABI data fusion technique should also supplant the accuracy weaknesses created by traditional simplified analytic models.

Previous researches on credit scoring mainly focussed on static modeling on panel sample data set in a certain period of time, and did not pay enough attention on dynamic incremental modeling. The purpose of this paper is to address the integration of branch and bound algorithm with incremental support vector machine (SVM) ensemble to make dynamic modeling of credit scoring.

This new model hybridizes support vectors of old data with incremental financial data of corporate in the process of dynamic ensemble modeling based on bagged SVM. In the incremental stage, multiple base SVM models are dynamically adjusted according to bagged new updated information for credit scoring. These updated base models are further combined to generate a dynamic credit scoring. In the empirical experiment, the new method was compared with the traditional model of non-incremental SVM ensemble for credit scoring.

The results show that the new model is able to continuously and dynamically adjust credit scoring according to corporate incremental information, which helps produce better evaluation ability than the traditional model.

This research pioneered on dynamic modeling for credit scoring with incremental SVM ensemble. As time pasts, new incremental samples will be combined with support vectors of old samples to construct SVM ensemble credit scoring model. The incremental model will continuously adjust itself to keep good evaluation performance.

The objective of this paper is twofold: first, to model the value of the firm in the presence of contingent capital and multiple growth options over its life cycle in a stochastic universe to ensure financial stability and recover losses in case of default and second, to clarify how contingent convertible (CoCo) bonds as financial instruments impact the leverage-ratio policies, inefficiencies generated by debt overhang and asset substitution for a firm that has multiple growth options. Additionally, what is its impact on investment timing, capital structure and asset volatility?

The current paper elaborates the modeling of a dynamic problem with respect to the interaction between funding and investment policies during multiple sequential investment cycles simultaneously with dynamic funding. The authors model the value of the firm in the presence of contingent capital that provides flexibility in dealing with default risks as well as growth options in a stochastic universe. The authors examine the firm's closed-form solutions at each stage of its decision-making process before and after the exercise of the growth options (with and without conversion of CoCo) through applying the backward indication method and the risk-neutral pricing theory.

The numerical results show that inefficiencies related to debt overhang and asset substitution can go down with a higher conversion ratio and a larger number of growth options. Additionally, the authors’ analysis reveals that the firm systematically opts for conservative leverage to minimize the effect of debt overhang on decisions so as to exercise growth options in the future. However, the capital structure of the firm has a substantial effect on the leverage ratio and the asset substitution. In fact, the effect of the leverage ratio and the risk-shifting incentive will be greater when the capital structure changes during the firm's decision-making process. Contrarily to traditional corporate finance theory, the study displays that the value of the firm before the investment expansion decreases and then increases with asset volatility, instead of decreasing overall with asset volatility.

The study’s findings reveal that funding, default and conversion decisions have crucial implications on growth option exercise decisions and leverage ratio policy. The model also shows that the firm consistently chooses conservative leverage to reduce the effect of debt overhang on decisions to exercise growth options in the future. The risk-shifting incentive and the debt overhang inefficiency basically decrease with a higher conversion ratio and multiple growth options. However, the effect of the leverage ratio and the risk-shifting incentive will be greater when the capital structure changes during the firm's decision-making process.

The firm's composition between assets in place and growth options evolves endogenously with its investment opportunity and growth option financing, as well as its default decision. In contrast to the standard capital structure models of Leland (1994), the model reveals that both exogenous conversion decisions and endogenous default decisions have significant implications for firms' growth option exercise decisions and debt policies. The model induces some predictions about the dynamics of the firm's choice of leverage as well as the link between the dynamics of leverage and the firm's life cycle.