Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
173 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
46 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Analysis of an aggregate loss model in a Markov renewal regime (2401.14553v2)

Published 25 Jan 2024 in q-fin.RM and stat.AP

Abstract: In this article we consider an aggregate loss model with dependent losses. The losses occurrence process is governed by a two-state Markovian arrival process (MAP2), a Markov renewal process process that allows for (1) correlated inter-losses times, (2) non-exponentially distributed inter-losses times and, (3) overdisperse losses counts. Some quantities of interest to measure persistence in the loss occurrence process are obtained. Given a real operational risk database, the aggregate loss model is estimated by fitting separately the inter-losses times and severities. The MAP2 is estimated via direct maximization of the likelihood function, and severities are modeled by the heavy-tailed, double-Pareto Lognormal distribution. In comparison with the fit provided by the Poisson process, the results point out that taking into account the dependence and overdispersion in the inter-losses times distribution leads to higher capital charges.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (83)
  1. On the analysis of the Gerber–Shiu discounted penalty function for risk processes with Markovian arrivals. Insurance: Mathematics and Economics, 41(2):234–249.
  2. Bayesian analysis of aggregate loss models. Mathematical Finance, 21(2):257–279.
  3. A micro-level claim count model with overdispersion and reporting delays. Insurance: Mathematics and Economics, 71:1 – 14.
  4. On the analysis of a multi-threshold Markovian risk model. Scandinavian Actuarial Journal, 2007(4):248–260.
  5. A Markovian canonical form of second-order matrix-exponential processes. European Journal of Operational Research, 190:459–477.
  6. Quantitative Operational Risk Models. Chapmal & Hall, CRC Press.
  7. Flexible dependence modeling of operational risk losses and its impact on total capital requirements. Journal of Banking & Finance, 40:271–285.
  8. Breuer, L. (2002). An EM algorithm for batch Markovian arrival processes and its comparison to a simpler estimation procedure. Annals of Operations Research, 112:123–138.
  9. Fat tails, expected shortfall and the Monte Carlo method: a note. The Journal of Operational Risk, 4(1):81–88.
  10. A global optimization approach for parameter estimation of a mixture of double pareto lognormal and lognormal distributions. Computers & Operations Research, 52:231–240.
  11. Maximum likelihood estimation in the two-state Markovian arrival process.
  12. Trace data characterization and fitting for Markov modeling. Performance Evaluation, 67:61–79.
  13. Çinlar, E. (1975). Introduction to stochastic processes. Prentice-Hall, Usa.
  14. Chakravarthy, S. (2001). The Batch Markovian arrival process: a review and future work. In et al., A. K., editor, Advances in probability and stochastic processes, pages 21–49.
  15. Chakravarthy, S. (2009). A disaster queue with Markovian arrivals and impatient customers. Applied Mathematics and Computation, 214:48–59.
  16. Basel II and operational risk: Implications for risk measurement and management in the financial sector. National Bank of Belgium Working Paper, No. 51.
  17. An extreme value approach for modeling operational risk losses depending on covariates. Journal of Risk and Insurance.
  18. Quantitative models for operational risk: extremes, dependence and aggregation. Journal of Banking & Finance, 30(10):2635–2658.
  19. Operational risk: a guide to Basel II capital requirements, models, and analysis, volume 180. John Wiley & Sons.
  20. A generalized penalty function with the maximum surplus prior to ruin in a MAP risk model. Insurance: Mathematics and Economics, 46:127–134.
  21. Joint moments of the total discounted gains and losses in the renewal risk model with two-sided jumps. Applied Mathematics and Computation, 331:358–377.
  22. Perturbed MAP risk models with dividend barrier strategies. Journal of Applied Probability, 46(2):521–541.
  23. Observed correlations and dependencies among operational losses in the ORX consortium database. Journal of Operational Risk, 3(4):47–74.
  24. Cruz, M. (2002). Modeling, Measuring and Hedging Operational Risk. John Wiley & Sons.
  25. On the evaluation of finite-time ruin probabilities in a dependent risk model. Applied Mathematics and Computation, 275:268–286.
  26. A tale of tails: an empirical analysis of loss distribution models for estimating operational risk capital. Working paper 06-13, Federal Reserve Bank of Boston.
  27. Using copulae to bound the Value-at-Risk for functions of dependent risks. Finance and Stochastics, 7:145–167.
  28. Modelling extremal events: for insurance and finance, volume 33. Springer Science & Business Media.
  29. A matching model for MAP-2 using moments of the counting process. In Proceedings of the International Network Optimization Conference, INOC 2007, Spa, Belgium.
  30. An exact Gibbs sampler for the Markov-modulated Poisson process. Journal of the Royal Statistical Society: Series B (Statistical Methodology), 68(5):767–784.
  31. Tackling the over-dispersion of operational risk: implications on capital adequacy requirements. The North American Journal of Economics and Finance, 31:206–221.
  32. High frequency trading and asymptotics for small risk aversion in a markov renewal model. SIAM Journal on Financial Mathematics, 6(1):656–684.
  33. Loss distribution approach for operational risk. Available at http://dx.doi.org/10.2139/ssrn.1032523.
  34. Frostig, E. (2008). On ruin probability for a risk process perturbed by a Lévy process with no negative jumps. Stochastic Models, 24(2):288–313.
  35. Multivariate Cox hidden Markov models with an application to operational risk. Scandinavian Actuarial Journal, 2019(8):686–710.
  36. A generalization of Panger’s recursion and numerically stable risk aggregation. Finance and Stochastics, 14:81–128.
  37. Groupe Consultatif Actuariel Européen (2007). Solvency II Glossary: European Commission. Technical report.
  38. A Markov modulated characterization of packetized voice and data traffic and related statistical multiplexer performance. IEEE Journal on Selected Areas in Communications, 4:856–868.
  39. Applied Semi-Markov Processes. Springer.
  40. Analysis of unreliable BMAP/PH/N type queue with Markovian flow of breakdowns. Applied Mathematics and Computation, 314:154–172.
  41. Modeling IP traffic using Batch Markovian Arrival Process. Performance Evaluation, 54(2):149–173.
  42. Loss models: from data to decisions. John Wiley & Sons.
  43. Lindsey, J. (1995). Modelling frequency and count data, volume 15. Oxford University Press.
  44. Lucantoni, D. (1991). New results for the single server queue with a Batch Markovian Arrival Process. Stochastic Models, 7:1–46.
  45. Lucantoni, D. (1993). The B⁢M⁢A⁢P/G/1𝐵𝑀𝐴𝑃𝐺1BMAP/G/1italic_B italic_M italic_A italic_P / italic_G / 1 queue: A tutorial. In Donatiello, L. and Nelson, R., editors, Models and Techniques for Performance Evaluation of Computer and Communication Systems, pages 330–358. Springer, New York.
  46. A single-server queue with server vacations and a class of nonrenewal arrival processes. Advances in Applied Probability, 22:676–705.
  47. Maegebier, A. (2013). Valuation and risk assessment of disability insurance using a discrete time trivariate Markov renewal reward process. Insurance: Mathematics and Economics, 53(3):802–811.
  48. Quantitative Risk Management: Concepts, Techniques and Tools. Princeton university press.
  49. Estimating operational risk capital for correlated, rare events. Journal of Operational Risk, 4(4):1–23.
  50. The first two moment matrices of the counts for the Markovian arrival process. Communications in statistics. Stochastic models, 8(3):459–477.
  51. MAP fitting by count and inter-arrival moment matching. Stochastic Models (in Press).
  52. An algorithm for the P⁢(n,t)𝑃𝑛𝑡P(n,t)italic_P ( italic_n , italic_t ) matrices of a continuous BMAP, volume 183 of Lectures notes in Pure and Applied Mathematics, pages 7–19. Srinivas R. Chakravarthy and Attahiru, S. Alfa, editors. NY: Marcel Dekker, Inc.
  53. Neuts, M. F. (1979). A versatile Markovian point process. Journal of Applied Probability, 16:764–779.
  54. On the joint distribution of surplus before and after ruin under a Markovian regime switching model. Stochastic Processes and their Applications, 116(2):244–266.
  55. Quantitative operational risk management. Working paper, Swedbank, Group Financial Risk Control.
  56. Fitting phase-type distributions and Markovian arrival processes: Algorithms and tools. In Principles of performance and reliability modeling and evaluation, pages 49–75.
  57. Panjer, H. H. (2006a). Aggregate Loss Modeling. John Wiley & Sons, Ltd.
  58. Panjer, H. H. (2006b). Operational risk: modeling analytics. John Wiley & Sons.
  59. Advances in Heavy Tailed Risk Modeling: A Handbook of Operational Risk. John Wiley & Sons.
  60. Analytic loss distributional approach models for operational risk from the α𝛼\alphaitalic_α-stable doubly stochastic compound processes and implications for capital allocation. Insurance: Mathematics and Economics, 49(3):565–579.
  61. Modeling and generating dependent risk processes for IRM and DFA. Astin Bulletin, 34(02):333–360.
  62. Ramaswami, V. (1990). From the matrix-geometric to the matrix-exponential. Queueing Systems, 6:229–260.
  63. Nonidentifiability of the two-state Markovian arrival process. Journal of Applied Probability, 47(3):630–649.
  64. Bayesian analysis of the stationary MAP22{}_{2}start_FLOATSUBSCRIPT 2 end_FLOATSUBSCRIPT. Bayesian Analysis, 12(4):1163–1194.
  65. Bayesian inference for Double Pareto lognormal queues. Annals of Applied Statistics, 4(3):1533–1557.
  66. The Markovian arrival process: A statistical model for daily precipitation amounts. Journal of Hydrology, 510(0):459 – 471.
  67. The Double Pareto-lognormal distribution - a new parametric model for size distributions. Communications in Statistics, Theory and Methods, 33(8):1733–1753.
  68. Ren, J. (2012). A multivariate aggregate loss model. Insurance: Mathematics and Economics, 51(2):402–408.
  69. Reshetar, G. (2008). Dependence of operational losses and the capital at risk. Available at http://dx.doi.org/10.2139/ssrn.1081256.
  70. Failure modeling of an electrical N-component framework by the non-stationary Markovian arrival process. Reliability Engineering and System Safety, 134:126–133.
  71. Rydén, T. (1996). An EM algorithm for estimation in Markov-modulated Poisson processes. Computational Statistics and Data Analysis, 21:431–447.
  72. Scott, S. (1999). Bayesian analysis of a two-state Markov modulated Poisson process. Journal of Computational and Graphical Statistics, 8(3):662–670.
  73. Pricing and simulating catastrophe risk bonds in a markov-dependent environment. Applied Mathematics and Computation, 309:68–84.
  74. Sharma, S. (2020). Operational risk modeling - Approaches and responses. Bimaquest, 20(1):15–31.
  75. Shevchenko, P. V. (2010a). Calculation of aggregate loss distribution. The journal of Operational Risk, 5(2):3–40.
  76. Shevchenko, P. V. (2010b). Implementing loss distribution approach for operational risk. Applied Stochastic Models in Business and Industry, 26(3):277–307.
  77. Stutzer, M. (2020). Persistence of averages in financial Markov Switching models: A large deviations approach. Physica A: Statistical Mechanics and its Applications, page 124237.
  78. A minimal representation of Markov arrival processes and a moments matching method. Performance evaluation, 64:1153–1168.
  79. A Bayesian approach to estimate the marginal loss distributions in operational risk management. Computational Statistics &\&& Data Analysis, 52:3107–3127.
  80. A claims persistence process and insurance. Insurance: Mathematics and Economics, 44(3):367–373.
  81. Double correlation model for operational risk: evidence from Chinese commerical banks. Physica A: Statistical mechanics and its applications, 516:327–339.
  82. Fitting procedure for the two-state Batch Markov modulated Poisson process. European Journal of Operational Research, (279(1)):79–92.
  83. On the absolute ruin in a MAP risk model with debit interest. Advances in Applied Probability, pages 77–96.
Citations (2)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now