Rational Human Behavior in a Social Setting. New York: Wiley.
Simon, Herbert. 1990. A Mechanism for Social Selection and Successful Altruism. Science 250 (4988): 1665–8.
Simon, Herbert. 1991. Bounded Rationality and Organizational Learning. Organization Science 2 (1): 125–134.
Slade, Margaret. E. 1996. Multitask Agency and Contract choice: an Empirical Exploration. International Economic Review. 37. 465-486.
Snelson, Edward, and Ghahramani, Zoubin. 2006. Sparse Gaussian Processes using Pseudo-Inputs. In Advances in Neural Information Processing Systems 18. MIT Press.
Spence, Michael. A, and Zeckhauser, Richard. J. 1971. Insurance, Information, and Individual Action. The American Economic Review, 61, 2, 380-387.
Spence, Michael. A. 1973. Job Market Signaling. The Quarterly Journal of Economics. 87. 3. 355-374.
Stiglitz, Joseph. E. 1975. Incentive, Risk and Information: Notes toward a Theory of Hierarchy. The Bell Journal of Economics, Vol. 6, No. 2, pp. 552-579.
Sufi, Amir. 2007. Information Asymmetry and Financing Arrangements: Evidence from Syndicated Loans. The Journal of Finance, Vol. 62, No. 2. pp. 629–668
Teh, Whye. Y, and Gorur, Dilan, and Ghahramani, Zoubin. 2007. Stick Breaking Construction for the Indian Buffet Process. Proceedings of the 11th Conference on Artificial Intelligence and Statistic.
Thomas, Hugh. 1999. A Preliminary Look at Gains from Asset Securitization. Journal of International Financial markets, Institutions and Money. 9. 321-333.
Titsias, Michalis. K. 2008. The Infinite Gamma-Poisson Feature Model. In J.C. Platt, D. Koller, Y. Singer, and S. Roweis, editors, Advances in Neural Information Processing Systems 20. MIT Press, Cambridge, MA.
Tirole, Jean. 1988. The Theory of Industrial Organization. Cambridge: MIT Press.
Tversky, Amos. 1972. Elimination by aspects: A theory of choice. Psychological Review, 79:281–299.
Ueda, Naonori, and Saito, Kazumi. 2003. Parametric Mixture Models for Multi-Labeled Text. In Advances in Neural Information Processing Systems 15. (S. Becker, S. Thrun and K. Obermayer, Eds.) Cambridge: MIT Press.
Wainwright. Martin. J andJordan, Michael. I. 2008. Graphical Models, Exponential Families, and Variational Inference. Foundations and Trends in Machine Learning, 1(1-2):1-305.
White, H. 1985. Agency as Control. In J. Pratt & R. Zeckhauser (Eds.). Principals and Agents: the Structure of Business (pp. 187-214). Boston: Harvard Business School Press.
Whitt, Ward. 1980. Uniform Conditional Stochastic Order. Journal of Applied Probability. 112-123.
Wiener, Norbert. 1948. Time Series. Cambridge: MIT Press.
Williamson, Oliver E. 1981. The Economics of Organization: the Transaction Cost Approach. American Journal of Sociology 87 (3):
Wilson, Robert. 1968. on the Theory of Syndicates. Econometrica, 119–132.
Winther, Ole. 2000. Gaussian Processes for Classification: Mean Field Algorithms. Neural Computation, 12.
Wood. Frank, and Griffiths, Thomas, and Ghahramani, Zoubin. 2006. A Non-Parametric Bayesian Method for Inferring Hidden Causes. In Proceedings of the 22nd Conference in Uncertainty in Artificial Intelligence (UAI’06).
Wood, Frank, and Griffiths, Thomas. L. 2007. Particle Filtering for Nonparametric Bayesian Matrix Factorization. In Advances in Neural Information Processing Systems, 19.
Yildirim, Llker, and Jacobs, Robert. A. 2012. A Rational Approach to the Acquisition of Multisensory Representations.Cognitive Science, Vol. 36, No. 2, 2012, pp. 305–332
Zeckhauser, Richard. J. 1970. Medical Insurance: A Case Study of the Tradeoff between Risk Spreading and Appropriate Incentives. Journal of Economic Theory, Vol. 2, No. 1, 1970, pp. 10-26.
Zellner, Arnold. 1971. An Introduction to Bayesian Inference in Econometrics. John Wiley, New York.
Zemel, Richard. S, and Hinton, Geoffrey. E. 1994. Developing Population Codes by Minimizing Description Length. Advances in Neural Information Processing Systems 6. (J. D. Cowan, G. Tesauro and J. Alspector, Eds.) San Francisco, CA: Morgan Kaufmann. 3–10.
Zhu, Wei-Qiu, and Lin, Yu-Kweng, and Cai, G. Q. 2001. UTAM Symposium on Nonlinear Stochastic Dynamics and Control. Proceedings of the IUTAM Symposium held in Hangzhou, China. Springer Science Business Media. 10–14. 2010.
Zou, Hui, and Hastie, Trevor, and Tibshirani, Robert. 2006. Sparse Principal Component Analysis. Journal of Computer Graphical Statistics. 15. 2. 265–286.
جدول 1: ماتریس پارامتر توزیع برنولی برای متغیر تصادفی z_nk (ν_nk, ∀n=1,…20, ∀k=1,…,6)
جدول 2: ماتریس پارامتر میانگین توزیع نرمال برای ماتریس وزنهایA (ϕ ̅_k, k=1,…6)
جدول 3: ماتریس پارامتر کواریانس توزیع نرمال برای ماتریس وزنهای A (Φ_k, k=1,…,6)
Asset securitization is one of the most important innovations in the financial markets. Securitization process is a financial technique that pools a wide variety of financial assets (mainly illiquid ones) which are capable of generating cash flows. Then created securities, guaranteed against the pools of those assets and their associated cash flows, eventually offer to the various different investors in the financial markets.
In its simplest form, in addition to the investors, securitization has another two major players. The Originator, firstly originates the assets (e.g. loans) which, during to the securitization process, finally transform to the marketable securities. Therefore, originator is original owner of the assets involved in the deal .This paper focuses on mortgage loans which during the securitization process, can transform to the marketable securities.
The second player in the securitization process is Special Purpose Vehicle (SPV) which is issuer of these securities and is bankruptcy remote. In fact, the originator pools a suitably large portfolio of the assets and transfers them to the issuer (SPV). The issuer, which is a limited liability company, and created for the specific purposes of financing the purchase of the asset pool, issues the securities backed by these pools (in the form of debt instrument), and acts as a channel for the payment flows.
It is important to notice that in the securitization process, transferring assets pool to issuer is a true sale (vs. a secured loan). According to accounting standards, the true sale is accomplished with transferring ownership of pool asset to the buyer (issuer). Thus, originator can remove these illiquid assets from his balance sheets, and can improve its liquidity. Therefore, originator and issuer are legally separated. So, if the originator goes in to bankruptcy, these assets, owning by issuer, will not be distributed among the originator’s creditors. All these things demonstrate the off-balance-sheet (OBS) feature of securitization process.
The issuance structure in the securitization process is such that issuer, in order to fund the purchase of pool assets from originator, structures and issues the tradable securities in the form of debt instrument. These securities are issued backed by cash flows generated from underlying asset pool (loans), and through selling networks are offered to the public, or only to the institutional investors, in the secondary markets.
It should be noted that periodic income payments of these securities are collected only from the assets pool rather than the originator. The securities, which represent claims to the cash flows from pools of the mortgage loans, are called mortgage-backed-securities (MBS).
Investors are third major player in this process. Investors are Mortgage-Backed securities (MBS) purchasers. Cash flows, from underlying assets, from issuer passed through to the investors. In fact, in the securitization process, all of these steps simultaneously occur.
In the securitization, by separating assets (mortgage loans) from balance sheet and using them as guarantee for issued securities to the investors, credit quality of these securities will be legally insulated from originator’s credit risk. In fact, originator does not live with credit outcomes of his originated loans. Thus, performance of the created securities is directly related to the borrowers’ quality in generating cash flows. But the matter is that the underlying asset performance and therefore securities’ performance, created and issued backed by them, is determined by the number of efforts performed by originator during the loans lending. It is clear that attempting to implement underwriting standards and qualifying clients, is costly. On the contrary, one can gather any information, and makes loans to every kind of mortgage applicants. Although second approach in favor of lender is less costly, this will lead to underwritten mortgages with high default risk which has detriment to the other party, namely investor; in fact risks now transfer to the investor rather than lenders.
On the other hand, for the investors, the other side of the market, complete observation of originator’s effort, in practice is impossible, or even if possible, it can be very costly. All of these things, along with OBS feature of securitization, can potentially distort incentive for carefully assessing creditworthiness of borrowers, which, in return, can reduce underwriting standards. In the securitization, what matters is the ability of assets to generate cash flows, but existence of informational related problems, which is inherent in this process, can strongly affect benefits of these investors. Hence, controlling over transparency of the flow of information, regarding implementing underwriting standards, is needed more analysis by investors, who are only bearing the credit risk of the assets (loan pools), underlying the mortgage-backed securities.