Risk assessment for financial accounting: modeling probability of default

2021 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Tobias Filusch
Keyword(s):  
Markov Chain ◽  
Business Cycle ◽  
Markov Chain Model ◽  
Accounting Standards ◽  
Financial Accounting ◽  
Homogeneous Markov Chain ◽  
Chain Model ◽  
Probability Of Default ◽  
Content Type ◽  
Term Structures

Purpose This paper aims to introduce and tests models for point-in-time probability of default (PD) term structures as required by international accounting standards. Corresponding accounting standards prescribe that expected credit losses (ECLs) be recognized for the impairment of financial instruments, for which the probability of default strongly embodies the included default risk. This paper fills the research gap resulting from a lack of models that expand upon existing risk management techniques, link PD term structures of different risk classes and are compliant with accounting standards, e.g. offering the flexibility for business cycle-related variations. Design/methodology/approach The author modifies the non-homogeneous continuous-time Markov chain model (NHCTMCM) by Bluhm and Overbeck (2007a, 2007b) and introduces the generalized through-the-cycle model (GTTCM), which generalizes the homogeneous Markov chain approach to a point-in-time model. As part of the overall ECL estimation, an empirical study using Standard and Poor’s (S&P) transition data compares the performance of these models using the mean squared error. Findings The models can reflect observed PD term structures associated with different time periods. The modified NHCTMCM performs best at the expense of higher complexity and only its cumulative PD term structures can be transferred to valid ECL-relevant unconditional PD term structures. For direct calibration to these unconditional PD term structures, the GTTCM is only slightly worse. Moreover, it requires only half of the number of parameters that its competitor does. Both models are useful additions to the implementation of accounting regulations. Research limitations/implications The tests are only carried out for 15-year samples within a 35-year span of available S&P transition data. Furthermore, a point-in-time forecast of the PD term structure requires a link to the business cycle, which seems difficult to find, but is in principle necessary corresponding to the accounting requirements. Practical implications Research findings are useful for practitioners, who apply and develop the ECL models of financial accounting. Originality/value The innovative models expand upon the existing methodologies for assessing financial risks, motivated by the practical requirements of new financial accounting standards.

On the limiting behaviour of a non-homogeneous Markovian manpower model with independent Poisson input

1982 ◽  
Vol 19 (2) ◽  
pp. 433-438 ◽  
Author(s):  
P.-C. G. Vassiliou
Keyword(s):  
Markov Chain ◽  
Markov Chain Model ◽  
Random Variable ◽  
Homogeneous Markov Chain ◽  
Chain Model ◽  
Poisson Random Variable ◽  
Poisson Input ◽  
Manpower System ◽  
Limiting Behaviour ◽  
Mutually Independent

We study the limiting behaviour of a manpower system where the non-homogeneous Markov chain model proposed by Young and Vassiliou (1974) is applicable. This is done in the cases where the input is a time-homogeneous and time-inhomogeneous Poisson random variable. It is also found that the number in the various grades are asymptotically mutually independent Poisson variates.

scholarly journals Will this search end up with booking? Modeling airline booking conversion of anonymous visitors

2020 ◽  
Vol 27 (2) ◽  
pp. 237-250
Author(s):  
Misuk Lee
Keyword(s):  
Markov Chain ◽  
Transition Probabilities ◽  
Markov Chain Model ◽  
Distribution Channel ◽  
Stochastic Approach ◽  
Tourism Industry ◽  
Chain Model ◽  
Online Search ◽  
Clickstream Data ◽  
Content Type

Purpose Over the past two decades, online booking has become a predominant distribution channel of tourism products. As online sales have become more important, understanding booking conversion behavior remains a critical topic in the tourism industry. The purpose of this study is to model airline search and booking activities of anonymous visitors. Design/methodology/approach This study proposes a stochastic approach to explicitly model dynamics of airline customers’ search, revisit and booking activities. A Markov chain model simultaneously captures transition probabilities and the timing of search, revisit and booking decisions. The suggested model is demonstrated on clickstream data from an airline booking website. Findings Empirical results show that low prices (captured as discount rates) lead to not only booking propensities but also overall stickiness to a website, increasing search and revisit probabilities. From the decision timing of search and revisit activities, the author observes customers’ learning effect on browsing time and heterogeneous intentions of website visits. Originality/value This study presents both theoretical and managerial implications of online search and booking behavior for airline and tourism marketing. The dynamic Markov chain model provides a systematic framework to predict online search, revisit and booking conversion and the time of the online activities.

On the limiting behaviour of a non-homogeneous Markovian manpower model with independent Poisson input

1982 ◽  
Vol 19 (02) ◽  
pp. 433-438 ◽  
Author(s):  
P.-C. G. Vassiliou
Keyword(s):  
Markov Chain ◽  
Markov Chain Model ◽  
Random Variable ◽  
Homogeneous Markov Chain ◽  
Chain Model ◽  
Poisson Random Variable ◽  
Poisson Input ◽  
Manpower System ◽  
Limiting Behaviour ◽  
Mutually Independent

We study the limiting behaviour of a manpower system where the non-homogeneous Markov chain model proposed by Young and Vassiliou (1974) is applicable. This is done in the cases where the input is a time-homogeneous and time-inhomogeneous Poisson random variable. It is also found that the number in the various grades are asymptotically mutually independent Poisson variates.

scholarly journals Markov degree of the three-state toric homogeneous Markov chain model

2013 ◽  
Vol 55 (1) ◽  
pp. 161-188 ◽  
Author(s):  
David Haws ◽  
Abraham Martín del Campo ◽  
Akimichi Takemura ◽  
Ruriko Yoshida
Keyword(s):  
Markov Chain ◽  
Markov Chain Model ◽  
Homogeneous Markov Chain ◽  
Chain Model

Stability in a non-homogeneous Markov chain model in manpower systems

1981 ◽  
Vol 18 (04) ◽  
pp. 924-930 ◽  
Author(s):  
P.-C. G. Vassiliou
Keyword(s):  
Markov Chain ◽  
Markov Chain Model ◽  
Sufficient Conditions ◽  
Necessary And Sufficient Conditions ◽  
Homogeneous Markov Chain ◽  
Initial Structure ◽  
Chain Model ◽  
Limiting Behaviour ◽  
Necessary And Sufficient

Necessary and sufficient conditions for stability, imposed firstly on the initial structure and the sequence of recruitment, and secondly on the initial structure and the sequence of expansion are provided in forms of two theorems. Also the limiting behaviour of the expected relative grade sizes is studied if we drop the conditions for stability imposed on the initial structure and keep the same sequence of expansion. Finally we examine the limiting behaviour of the expected grade sizes if we drop the assumption of a continuously expanding system.

Markov chain based modelling and prediction of natural gas allocation structure in Pakistan

2020 ◽  
Vol 14 (5) ◽  
pp. 911-933
Author(s):  
Hussaan Ahmad ◽  
Nasir Hayat
Keyword(s):  
Markov Chain ◽  
Natural Gas ◽  
Polynomial Regression ◽  
Markov Chain Model ◽  
Chain Model ◽  
Transition Matrices ◽  
Allocation Pattern ◽  
Content Type ◽  
Structural Prediction ◽  
Order Polynomial

Purpose The purpose of this paper is to analyze the historical gas allocation pattern for seeking appropriate arrangement and utilization of potentially insufficient natural gas supply available in Pakistan up to 2030. Design/methodology/approach This study presents Markov chain-based modeling of historical gas allocation data followed by its validation through error evaluation. Structural prediction using classical Chapman–Kolmogorov method and varying-order polynomial regression in the historical transition matrices are presented. Findings Markov chain model reproduces the terminal state vector with 99.8 per cent accuracy, thus demonstrating its validity for capturing the history. Lower order polynomial regression results in better structural prediction compared with higher order ones in terms of closeness with Markov approach-based prediction. Research limitations/implications The data belongs to a certain geographic region with specific gas demand and supply profile. The proposition may be tested further by researchers to check the validity for other comparable structural predictions/analyses. Practical implications This study can facilitate policy-making in the field of natural gas allocation and management in Pakistan specifically and other comparable countries generally. Originality/value Two major literature gaps filled through this study are: first, Markov chain model becomes stationary when projected using Chapman–Kolmogorov relation in terms of a fixed, average transition matrix resulting in an equilibrium state after a finite number of future steps. Second, most of the previous studies analyze various gas consumption sectors individually, thus lacking integrated gas allocation policy.

The forecast of cultivate land quantity based on Grey-Markov model

2015 ◽  
Vol 5 (1) ◽  
pp. 127-136 ◽  
Author(s):  
Hongyan Huan ◽  
Qing-mei Tan
Keyword(s):  
Markov Chain ◽  
Markov Model ◽  
Land Use Planning ◽  
Markov Chain Model ◽  
Arable Land ◽  
Jiangsu Province ◽  
Chain Model ◽  
Cultivated Land ◽  
Content Type ◽  
Investigation Methods

Purpose – The purpose of this paper is to employ the Grey-Markov Chain Model for the scale prediction of cultivated land and took an empirical research with the case of Jiangsu province. Design/methodology/approach – Along with China’s industrialization and urbanization accelerated, a large number of cultivated land converse into construction land. The change of utilization of cultivated land concerns national food security and sustainable development of economy and society. Due to the fact that the different investigation methods of arable land usually cause a uncertain. The Grey-Markov model combines the Grey GM(1,1) and Markov chain, with two advantages of dealing with poor information and long-term and volatile series. A numeric example of scale prediction of cultivated land in Jiangsu province is also computed in the third part of the paper. Findings – The results show that the Grey-Markov Chain Model has a higher prediction accuracy compared with GM (1,1), which is a reliable guarantee for the change of cultivated land resources. Practical implications – The forecast of cultivated land can provide useful information for the general land use planning. Originality/value – The paper confirmed the feasibility of the Grey-Markov model in scale prediction of cultivated land.

Sign in / Sign up

Export Citation Format

Share Document