Search results

Discusses and empirically tests special cases of multiple‐chain mixed Markov latent class models with business data. The switches between negative and positive changes in earnings‐per‐share of firms are captured by alternative Markov models. The estimated response probabilities and state transition probabilities show interesting changes in the transformation patterns of the firms over time. Shows that Markov models can be valuable tools in predicting switches in profitability of firms.

Prediction problems raised in uncertain environments require different solution approaches such as grey prediction models, which consider uncertainty in information and also enable the use of small data sets. The purpose of this paper is to investigate the comparative performances of grey prediction models (GM) and Markov chain integrated grey models in a demand prediction problem.

The modeling process of grey models is initially described, and then an integrated model called the Grey-Markov model is presented for the convenience of applications. The analyses are conducted on a monthly demand prediction problem to demonstrate the modeling accuracies of the GM (1,1), GM (2,1), GM (1,1)-Markov, and GM (2,1)-Markov models.

Numerical results reveal that the Grey-Markov model based on GM (2,1) achieves better prediction performance than the other models.

It is thought that the methodology and the findings of the study will be a significant reference for both academics and executives who struggle with similar demand prediction problems in their fields of interest.

The novelty of this study comes from the fact that the GM (2,1)-Markov model has been first used for demand prediction. Furthermore, the GM (2,1)-Markov model represents a relatively new approach, and this is the second paper that addresses the GM (2,1)-Markov model in any area.

Credit ratings serve as an important input in several applications in risk management of the financial firms. The level of credit rating changes from time to time because of random credit risk and, thus, can be modeled by an appropriate stochastic process. Markov chain models have been widely used in the literature to generate credit migration matrices; however, emergent empirical evidences suggest that the Markov property is not appropriate for credit rating dynamics. The purpose of this article is to address the non-Markov behavior of the rating dynamics.

This paper proposes a model based on Markov regenerative process (MRGP) with subordinated semi-Markov process (SMP) to obtain the estimates of rating migration probability matrices and default probabilities. Numerical example is given to illustrate the applicability of the proposed model with the help of historical Standard & Poor’s (S&P) credit rating data.

The proposed model implies that rating of a firm in the future not only depends on its present rating, but also on its previous ratings. If a firm gets a rating lower than its previous ratings, there are higher chances of further downgrades, and the issue is called the rating momentum. The model also addresses the ageing problem of credit rating evolution.

The contribution of this paper is a more general approach to study the rating dynamics and overcome the issues of inappropriateness of Markov process applied in rating dynamics.

Purpose – The purpose of this chapter is to introduce new methods to behavioral research on group negotiation.

Design/methodology/approach – We describe three techniques from the field of Machine Learning and discuss their possible application to modeling dynamic processes in group negotiation: Markov Models, Hidden Markov Models, and Inverse Reinforcement Learning. Although negotiation research has employed Markov modeling in the past, the latter two methods are even more novel and cutting-edge. They provide the opportunity for researchers to build more comprehensive models and to use data more efficiently. To demonstrate their potential, we use scenarios from group negotiation research and discuss their hypothetical application to these methods. We conclude by suggestions for researchers interested in pursuing this line of work.

Originality/value – This chapter introduces methods that have been successfully used in other fields and discusses how these methods can be used in behavioral negotiation research. This chapter can be a valuable guide to researchers that would like to pursue computational modeling of group negotiation.

I review the burgeoning literature on applications of Markov regime switching models in empirical finance. In particular, distinct attention is devoted to the ability of Markov Switching models to fit the data, filter unknown regimes and states on the basis of the data, to allow a powerful tool to test hypotheses formulated in light of financial theories, and to their forecasting performance with reference to both point and density predictions. The review covers papers concerning a multiplicity of sub-fields in financial economics, ranging from empirical analyses of stock returns, the term structure of default-free interest rates, the dynamics of exchange rates, as well as the joint process of stock and bond returns.

The purpose of this paper is to review the Fuzzy Markov development for assessing the structural integrity of buried transportation bridges. In doing so, the appropriateness of Fuzzy Markov will be assessed, leading to the subsequent model.

This research will utilize the Fuzzy Markov techniques as the conceptual framework. Such methodology is further supported via the utilization and evaluation of 30 buried transportation bridges using the developed Fuzzy Markov model.

Subsequently, through a developed Fuzzy Markov model, this research found that as the basis of structural resilience, specific matrices for age-dependent transition probability can be compiled using conditional survival probabilities in the various structural states; as the basis of structural integrity, specific environmental and economic schemes can also be established based on inspection intervals, intervention systems and failure phases; exact inspection and maintenance intervals can be scheduled to further prolong an asset’s life; and clear and early warning signs can also be formulated for immediate intervention when the structural integrity of the asset are indeed compromised.

The gap within the literature currently surrounds the limitation of computational analysis for some buried structures such as bridges. Specifically, to streamline such evaluation and regimes, a Fuzzy Markov is developed and reviewed.

The demand for the cold chain logistics of agricultural products was investigated through demand forecasting; targeted suggestions and countermeasures are provided. This paper aims to discuss the aforementioned statement.

A Markov-optimised mean GM (1, 1) model is proposed to forecast the demand for the cold chain logistics of agricultural products. The mean GM (1, 1) model was used to forecast the demand trend, and the Markov chain model was used for optimisation. Considering Guangxi province as an example, the feasibility and effectiveness of the proposed method were verified, and relevant suggestions are made.

Compared with other models, the Markov-optimised mean GM (1, 1) model can more effectively forecast the demand for the cold chain logistics of agricultural products, is closer to the actual value and has better accuracy and minor error. It shows that the demand forecast can provide specific suggestions and theoretical support for the development of cold chain logistics.

This study evaluated the development trend of the cold chain logistics of agricultural products based on the research horizon of demand forecasting for cold chain logistics. A Markov-optimised mean GM (1, 1) model is proposed to overcome the problem of poor prediction for series with considerable fluctuation in the modelling process, and improve the prediction accuracy. It finds a breakthrough to promote the development of cold chain logistics through empirical analysis, and give relevant suggestions based on the obtained results.

The purpose of this paper is to analyze the usability of a remote learning system in its initial development phase, using a quantitative usability evaluation method through Markov models.

The paper opted for an exploratory study. The data of interest of the research correspond to the possible accesses of users in a learning system's pre‐project. The present research is intended to answer questions of the type “how”, evaluating the usability through Markov models and the interaction of the learning system's users.

The paper provides a study which allowed the generation of a probability matrix among states and actions, which was utilized in the evaluation of usability based on Markov models, where the usability criteria specified were analyzed. Markov models allow a series of measures of interest to be calculated and they have been successfully utilized in the evaluation of computing and communication systems.

This research aimed to investigate the utilization of Markov models in the evaluation of usability in a remote learning system in its pre‐project phase and to help in proposing improvement suggestions.

Pavement deterioration prediction models play a crucial role in determining maintenance strategies and future funding needs. While deterioration prediction models have been studied extensively in the past, applications of these models to local street networks have been limited. This study aims to address this gap by sharing the results of network level deterioration prediction models developed at a local level.

Network level pavement deterioration prediction models are developed using Markov chains for the local street network in Syracuse, New York, based on pavement condition rating data collected over a 15-year time period. Transition probability matrices are generated by calculating the percentage of street sections that transition from one state to another within one duty cycle. Bootstrap sampling with replacement is used to numerically generate 95% confidence intervals around the transition probability values.

The overall local street network is divided into three cohorts based on street type (i.e. avenues, streets and roads) and two cohorts based on pavement type. All cohorts demonstrated very similar deterioration trends, indicating the existence of a fast-paced deterioration mechanism for the local street network of Syracuse.

This study contributes to the body of knowledge in deterioration modeling of local street networks, especially in the absence of key predictor variables. Furthermore, this study introduces the use of bootstrap sampling with replacement method in generating confidence intervals for transition probability values.

Markov chains and queuing theory are widely used analysis, optimization and decision‐making tools in many areas of science and engineering. Real life systems could be modelled and analysed for their steady‐state and time‐dependent behaviour. Performance measures such as blocking probability of a system can be calculated by computing the probability distributions. A major hurdle in the applicability of these tools to complex large problems is the curse of dimensionality problem because models for even trivial real life systems comprise millions of states and hence require large computational resources. This paper describes the various computational dimensions in Markov chains modelling and briefly reports on the author's experiences and developed techniques to combat the curse of dimensionality problem.

The paper formulates the Markovian modelling problem mathematically and shows, using case studies, that it poses both storage and computational time challenges when applied to the analysis of large complex systems.

The paper demonstrates using intelligent storage techniques, and concurrent and parallel computing methods that it is possible to solve very large systems on a single or multiple computers.

The paper has developed an interesting case study to motivate the reader and have computed and visualised data for steady‐state analysis of the system performance for a set of seven scenarios. The developed methods reviewed in this paper allow efficient solution of very large Markov chains. Contemporary methods for the solution of Markov chains cannot solve Markov models of the sizes considered in this paper using similar computing machines.