Bespoke Portfolios

  • Published on
    30-Sep-2014

  • View
    91

  • Download
    4

Embed Size (px)

Transcript

<p> Journal ofAppliedMathematicsandDecisionSciencesHindawi Publishing Corporationhttp://www.hindawi.com Volume 2009Editor-in-ChiefMahyar A. AmouzegarSpecial IssueIntelligent Computational Methods for Financial EngineeringGuest EditorsLean Yu, Shouyang Wang, and K. K. LaiIntelligent Computational Methodsfor Financial EngineeringJournal ofApplied Mathematics and Decision SciencesIntelligent Computational Methodsfor Financial EngineeringGuest Editors: Lean Yu, Shouyang Wang, and K. K. LaiCopyright q 2009 Hindawi Publishing Corporation. All rights reserved.This is an issue published in volume 2009 of Journal of Applied Mathematics and Decision Sciences. All articlesare open access articles distributed under the Creative Commons Attribution License, which permits unrestricted use,distribution, and reproduction in any medium, provided the original work is properly cited.Editor-in-ChiefMahyar A. Amouzegar, California State University, USAAdvisory EditorsJames Moat, UK Graeme Wake, New ZealandAssociate EditorsMark Bebbington, New ZealandEric J. Beh, AustraliaJohn E. Bell, USAFernando Beltran, New ZealandOmer S. Benli, USADavid Bulger, AustraliaR. Honfu Chan, Hong KongWai Ki Ching, Hong KongS. Chukova, New ZealandStephan Dempe, GermanyWen-Tao Huang, TaiwanChin Diew Lai, New ZealandYan-Xia Lin, AustraliaChenghu Ma, ChinaRon McGarvey, USAKhosrow Moshirvaziri, USAShelton Peiris, AustraliaJack Penm, AustraliaJanos D. Pinter, TurkeyJohn C. W. Rayner, AustraliaRoger Z. Ros-Mercado, MexicoBhaba R. Sarker, USAHenry Schellhorn, USAManmohan S. Sodhi, UKAndreas Soteriou, CyprusOlivier Thas, BelgiumWing-Keung Wong, Hong KongG. Raymond Wood, AustraliaContentsIntelligent Computational Methods for Financial Engineering, Lean Yu, Shouyang Wang,and K. K. LaiVolume 2009, Article ID 394731, 2 pagesOptimal Bespoke CDO Design via NSGA-II, Diresh Jewan, Renkuan Guo,and Gareth WittenVolume 2009, Article ID 925169, 32 pagesModied Neural Network Algorithms for Predicting Trading Signals of Stock MarketIndices, C. D. Tilakaratne, M. A. Mammadov, and S. A. MorrisVolume 2009, Article ID 125308, 22 pagesSelecting the Best Forecasting-Implied Volatility Model Using Genetic Programming,Wafa Abdelmalek, Sana Ben Hamida, and Fathi AbidVolume 2009, Article ID 179230, 19 pagesDiscrete Analysis of Portfolio Selection with Optimal Stopping Time, Jianfeng LiangVolume 2009, Article ID 609196, 9 pagesA New Decision-Making Method for Stock Portfolio Selection Based on Computingwith Linguistic Assessment, Chen-Tung Chen and Wei-Zhan HungVolume 2009, Article ID 897024, 20 pagesA Fuzzy Pay-O Method for Real Option Valuation, Mikael Collan, Robert Full er,and J ozsef MezeiVolume 2009, Article ID 238196, 14 pagesValuation for an American Continuous-Installment Put Option on Bond under VasicekInterest Rate Model, Guoan Huang, Guohe Deng, and Lihong HuangVolume 2009, Article ID 215163, 11 pagesCallable Russian Options and Their Optimal Boundaries, Atsuo Suzukiand Katsushige SawakiVolume 2009, Article ID 593986, 13 pagesValuation of Game Options in Jump-Diusion Model and with Applications toConvertible Bonds, Lei Wang and Zhiming JinVolume 2009, Article ID 945923, 17 pagesFuzzy Real Options in Browneld Redevelopment Evaluation, Qian Wang, Keith W. Hipel,and D. Marc KilgourVolume 2009, Article ID 817137, 16 pagesDiscriminant Analysis of Zero Recovery for Chinas NPL, Yue Tang, Hao Chen, Bo Wang,Muzi Chen, Min Chen, and Xiaoguang YangVolume 2009, Article ID 594793, 16 pagesCumulative Gains Model Quality Metric, Thomas Brandenburger and Alfred FurthVolume 2009, Article ID 868215, 14 pagesHindawi Publishing CorporationJournal of Applied Mathematics and Decision SciencesVolume 2009, Article ID 394731, 2 pagesdoi:10.1155/2009/394731EditorialIntelligent Computational Methods forFinancial EngineeringLean Yu,1Shouyang Wang,1and K. K. Lai21Institute of Systems Science, Academy of Mathematics and Systems Science,Chinese Academy of Sciences, Beijing 100190, China2Department of Management Sciences, City University of Hong Kong,Tat Chee Avenue, Kowloon, Hong KongCorrespondence should be addressed to Lean Yu, yulean@amss.ac.cnReceived 17 June 2009; Accepted 17 June 2009Copyright q 2009 Lean Yu et al. This is an open access article distributed under the CreativeCommons Attribution License, which permits unrestricted use, distribution, and reproduction inany medium, provided the original work is properly cited.As a multidisciplinary eld, nancial engineering is becoming increasingly important intodays economic and nancial world, especially in areas such as portfolio management,asset valuation and prediction, fraud detection, and credit risk management. For example,in a credit risk context, the recently approved Basel II guidelines advise nancial institutionsto build comprehensible credit risk models in order to optimize their capital allocation policy.Computational methods are being intensively studied and applied to improve the quality ofthe nancial decisions that need to be made. Until now, computational methods and modelsare central to the analysis of economic and nancial decisions.However, more and more researchers have found that the nancial environmentis not ruled by mathematical distributions or statistical models. In such situations, someattempts have also been made to develop nancial engineering models using some emergingintelligent computing approaches. For example, an articial neural network ANN is anonparametric estimation technique which does not make any distributional assumptionsregarding the underlying asset. Instead, ANN approach develops a model using sets ofunknown parameters and lets the optimization routine seek the best tting parameters toobtain the desired results. That is, these emerging intelligent solutions can eciently improvethe decisions for nancial engineering problems. Having agreed on this basic fact, the guesteditors determined that the main purpose of this special issue is not to merely illustrate thesuperior performance of a new intelligent computational method, but also to demonstratehowit can be used eectively in a nancial engineering environment to improve and facilitatenancial decision making.For this purpose, this special issue presents some new progress in intelligentcomputational methods for nancial engineering. In particular, the special issue addresses2 Journal of Applied Mathematics and Decision Scienceshow the emerging intelligent computational methods e.g., ANN, support vector machines,evolutionary algorithm, and fuzzy models, etc. can be used to develop intelligent, easy-to-use and/or comprehensible computational systems e.g., decision support systems, agent-based system, and web-based systems, etc., which is expected to trigger some thoughts anddeepen further research.In this special issue, 12 papers were selected from 26 submissions related to intelligentcomputational methods for nancial engineering from dierent countries and regions. Theauthors of the selected papers are from USA, Canada, Australia, Japan, Finland, Tunisia, SriLanka, Taiwan, South Africa, and China, respectively. In addition, all the selected papers wentthrough a standard peer review process of the journal and the authors of some papers madenecessary revision in terms of reviewing comments. The selected papers include OptimalBespoke CDO Design via NSGA-II by Diresh Jewan, Renkuan Guo, and Gareth Witten,Modied neural network algorithms for predicting trading signals of stock market indicesby C. D. Tilakaratne, M. A. Mammadov, S. A. Morris, Selecting the best forecasting impliedvolatility model using genetic programming by Wafa Abdelmalek, Sana Ben Hamida, FathiAbid, Discrete analysis of portfolio selection with optimal stopping time by Jianfeng Liang,A New decision-making method for stock portfolio selection based on computing withlinguistic assessment by Chen Tung Chen, Wei Zhan Hung, Afuzzy pay-o method for realoption valuation by Mikael Collan, Robert Fuller, Jozsef Mezei, Valuation for an Americancontinuous-installment put option on bond under vasicek interest rate model by GuoheDeng, Lihong Huang, Callable Russian options and their optimal boundaries by AtsuoSuzuki, Katsushige Sawaki, Valuation of game options in jump diusion model and withapplications to convertible bonds by Lei Wang and Zhiming Jin, Fuzzy real options inbrowneld redevelopment evaluation by Qian Wang, Keith W. Hipel, D. Marc Kilgour,Discriminant analysis of zero recovery for Chinas NPL by Yue Tang, Xiaoguang Yang,Hao Chen, Bo Wang, Muzi Chen, Min Chen, and Cumulative gains model quality metricby Thomas Brandenburger, Alfred Furth. The guest editors hope that the papers published inthis special issue would be of value to academic researchers and business practitioners andwould provide a clearer sense of direction for further research, as well as facilitating use ofexisting methodologies in a more productive manner.The guest editors would like to place on record their sincere thanks to ProfessorMahyar A. Amouzegar, the Editor-in-Chief of Journal of Applied Mathematics and DecisionSciences, for this very special opportunity provided to us for contributing to this special issue.The guest editors have to thank all the referees for their kind support and help, which hasguaranteed that this special issue is of high standard. Finally, the guest editors would like tothank the authors of all the submissions to this special issue for their contribution. Withoutthe support of the authors and the referees, it would have been impossible to make this specialissue for our readers. It is hoped that readers can nd some topics of interest and benet tothem. The guest editors also hope that this special issue would inspire researchers in the eldsof intelligent nancial engineering to explore more creative contributions in their researchelds.Lean YuShouyang WangK. K. LaiHindawi Publishing CorporationJournal of Applied Mathematics and Decision SciencesVolume 2009, Article ID 925169, 32 pagesdoi:10.1155/2009/925169Research ArticleOptimal Bespoke CDO Design via NSGA-IIDiresh Jewan,1Renkuan Guo,1and Gareth Witten21Department of Statistical Sciences, University of Cape Town, Private Bag, Rhodes Gift, Rondebosch 7701,Cape Town, South Africa2Peregrine Quant, PO Box 44586, Claremont, Cape Town, 7735, South AfricaCorrespondence should be addressed to Renkuan Guo, renkuan.guo@uct.ac.zaReceived 28 November 2008; Accepted 9 January 2009Recommended by Lean YuThis research work investigates the theoretical foundations and computational aspects ofconstructing optimal bespoke CDO structures. Due to the evolutionary nature of the CDO designprocess, stochastic search methods that mimic the metaphor of natural biological evolution areapplied. For ecient searching the optimal solution, the nondominating sort genetic algorithmNSGA-II is used, which places emphasis on moving towards the true Paretooptimal region. Thisis an essential part of real-world credit structuring problems. The algorithm further demonstratesattractive constraint handling features among others, which is suitable for successfully solvingthe constrained portfolio optimisation problem. Numerical analysis is conducted on a bespokeCDO collateral portfolio constructed from constituents of the iTraxx Europe IG S5 CDS index. Forcomparative purposes, the default dependence structure is modelled via Gaussian and Claytoncopula assumptions. This research concludes that CDO tranche returns at all levels of risk underthe Clayton copula assumption performed better than the sub-optimal Gaussian assumption.It is evident that our research has provided meaningful guidance to CDO traders, for seekingsignicant improvement of returns over standardised CDOs tranches of similar rating.Copyright q 2009 Diresh Jewan et al. This is an open access article distributed under the CreativeCommons Attribution License, which permits unrestricted use, distribution, and reproduction inany medium, provided the original work is properly cited.1. IntroductionBespoke CDOs provides tailored credit solutions to market participants. They provide bothlong-term strategic and tactical investors with the ability to capitalise on views at the market,sector and name levels. Investors can use these structures in various investment strategies totarget the risk/return prole or hedging needs. These strategies can vary from leverage andcorrelation strategies to macro and relative value plays 1.Understanding the risk/return trade-o dynamics underlying the bespoke CDOcollateral portfolios is crucial when maximising the utility provided by these instruments. Thesingle-tranche deal can be put together in a relatively short period of time. This is aided bythe development of numerous advance pricing, risk management and portfolio optimisationtechniques.2 Journal of Applied Mathematics and Decision SciencesThe most crucial tasks in putting together the bespoke CDOis choosing the underlyingcredits that will be included in the portfolio. Investors often express preferences on individualnames, and there is likely to be credit rating constraint and industry concentration limitsimposed by the investors and rating agencies 2.Given these various investor dened requirements, the structurer is required tooptimise the portfolio to achieve the best possible tranche spreads for investors. This wasa complicated task, however, with the advent of faster computational pricing and portfoliooptimisation algorithms, aid structurers in presenting bespoke CDO which conform to theinvestment parameters.The proper implementation of the decision steps lies in the solution of themultiobjective, multiconstrained optimisation problem, where investors can choose anoptimal structure that matches their risk/return prole. Optimal structures are dened byportfolios that lie on the Pareto frontier on the CDO tranche yield/portfolio risk plane.Davidson 2 provides an interesting analogy between CDO portfolio optimisationprocesses and evolutionary cycles espoused by Charles Darwin. In the natural world, lifeadapts to suit the particulars of its environment. To adapt to a specic environment, a simplebut extraordinarily powerful set of evolutionary techniques are employedreproduction,mutation and survival of the ttest. In this way, nature explores the full range of possiblestructures to hone in on those that are most perfectly suited to the surrounding environment.The creation of the CDO collateral portfolio can broadly be seen in similar ways.Given a certain set of investor and/or market constraints, such as the number of underlyingcredits, the...</p>