學術產出-Theses

題名 最適資產配置-動態規劃問題之數值解
Optimal asset allocation-the numerical solution of dynamic programming
作者 黃迪揚
Huang, Di Yang
貢獻者 黃泓智
Huang, Hong Chih
黃迪揚
Huang, Di Yang
關鍵詞 資產配置
動態規劃
數值解
Asset Allocation
Dynamic Programming
Numerical Solution
日期 2008
上傳時間 8-Dec-2010 16:36:41 (UTC+8)
摘要 動態規劃是一種專門用來解決最適化的數學方法,其觀念源自於Bellman (1962),他提出了動態規劃的最佳原則,然而動態規劃問題不見得有封閉解(closed form solution),即使其存在,求解過程往往也相當困難且複雜。Vigna & Haberman (2001)用動態規劃方式找出最佳的投資策略並分析確定提撥制(defined contribution)下的財務風險;本研究擬以Vigna & Haberman (2001)的模型為基礎,提出解決動態規劃問題的數值方法。

Vigna & Haberman (2001)推導出確定提撥退休金制度下離散時間的最適投資策略封閉解,透過該模型,我們可以比較本研究所建議的方法與真正封閉解的差異,證實本研究所建議的方法的確可以提供動態規劃問題一個接近且有效率的數值解法。接著根據Yvonne C.(2002、2003)的抽樣方法,希望在進行模擬時,能找出模擬情境的特性並對這些情境進行抽樣,藉此減少情境數以增加電腦運算的效率。最後應用在Vigna & Haberman (2001)的修正模型以及Haberman & Vigna (2002)的模型上,說明了本研究所建議的數值方法也適用在各類型的動態規劃上,包含理論封閉解不存在以及求解非常複雜的問題。
參考文獻 1. Chang, S.C., (1999), "Optimal Pension Funding Through Dynamic Simulations: the Case of Taiwan Public Employees Retirement System." Insurance: Mathematics and Economics, 24, 187-199.
2. Chryssoverghi and Bacopoulos, Discrete approximation of relaxed optimal control problems. Journal of Optimization Theory and Applications, 1990, 395-407
3. C.-S. Huang, S. Wang and K.L. Teo, Solving Hamilton-Jacobi-Bellman equations by a modified method of characteristics. Nonlinear Analysis 40 (2000), 279-293.
4. Haberman, S., and Sung, J.H., (1994), "Dynamic Approaches to Pension Funding" Insurance: Mathematics and Economics, 15, p151-162.
5. Haberman, S., and Vigna, E., (2002), "Optimal Investment Strategies and risk measures in defined contribution pension schemes." Insurance mathematics and Economics, 31, p35-69.
6. M. A. H. Dempster, (1980), "Stochastic programming " International Conference on Stochastic Programming, Oxford, 1974
7. Markowitz, and Harry, (1952).“Portfolio Selection”. Journal of Finance ,pp.77-91.
8. M. G. Crandall and P.L. Lions, Two approximations of solutions of Hamilton-Jacobi equations. Mathematics of Computation 43 (1984), 1-19.
9. Sherris,(1992),”Portfolio Selection and Matching :A synthesis”. J.I.A.119,I,pp.87-105.
10. S. Wang, F. Gao and K.L. Teo, An upwind finite-difference method for the approximation of viscosity solutions to Hamilton-Jacobi-Bellman equations. IMA J. Math. Control 17 (2000), 167-178.
11. Vigna, E., and Haberman, S., (2001), "Optimal Investment Strategy for defined contribution pension schemes." Insurance mathematics and Economics, 28, p233-262.
12. Wilkie, A.D.,(1985).“Portfolio Selection in the Presence of Fixed Liabilities: A comment on The Matching of Assets to Liabilities” Journal of Institute of Actuaries,112, 229-277
13. Wise, A.J., (1984a)”A theoretical analysis of the matching of assets to liabilities.” Journal of Institute of Actuaries,111(Part II):375-402
14. Wise, A.J., (1984b)”The matching of assets to liabilities.” Journal of the Institute of Actuaries,111(Part II):445-501
15. Wise, A.J.,(1987a) “Matching and Portfolio Selection:Part 1 “Journal of Institute of Actuaries,114, 113-133
16. Wise, A.J.,(1987b) “Matching and Portfolio Selection:Part 2” Journal of Institute of Actuaries,114, 551-568
17. Yvonne, C., (2002), "Efficient Stochastic Modeling For Large and Consolidated Insurance Business:Interest Rate Sampling Algorithms." North American Actuarial Journal, Vol.6 Iss. 3, p88-103.
18. Yvonne, C., (2003), " Efficient Stochastic Modeling:From Scenario Sampling To Parametric Model Fitting Utilizing ASEM as an Exampling." International Professional Development Symposium Co-sponsored by Canadian Institute of Actuaries, Actuarial Foundation, and Society of Actuaries, Toronto, Canada.
描述 碩士
國立政治大學
風險管理與保險研究所
96358021
97
資料來源 http://thesis.lib.nccu.edu.tw/record/#G0096358021
資料類型 thesis
dc.contributor.advisor 黃泓智zh_TW
dc.contributor.advisor Huang, Hong Chihen_US
dc.contributor.author (Authors) 黃迪揚zh_TW
dc.contributor.author (Authors) Huang, Di Yangen_US
dc.creator (作者) 黃迪揚zh_TW
dc.creator (作者) Huang, Di Yangen_US
dc.date (日期) 2008en_US
dc.date.accessioned 8-Dec-2010 16:36:41 (UTC+8)-
dc.date.available 8-Dec-2010 16:36:41 (UTC+8)-
dc.date.issued (上傳時間) 8-Dec-2010 16:36:41 (UTC+8)-
dc.identifier (Other Identifiers) G0096358021en_US
dc.identifier.uri (URI) http://nccur.lib.nccu.edu.tw/handle/140.119/49681-
dc.description (描述) 碩士zh_TW
dc.description (描述) 國立政治大學zh_TW
dc.description (描述) 風險管理與保險研究所zh_TW
dc.description (描述) 96358021zh_TW
dc.description (描述) 97zh_TW
dc.description.abstract (摘要) 動態規劃是一種專門用來解決最適化的數學方法,其觀念源自於Bellman (1962),他提出了動態規劃的最佳原則,然而動態規劃問題不見得有封閉解(closed form solution),即使其存在,求解過程往往也相當困難且複雜。Vigna & Haberman (2001)用動態規劃方式找出最佳的投資策略並分析確定提撥制(defined contribution)下的財務風險;本研究擬以Vigna & Haberman (2001)的模型為基礎,提出解決動態規劃問題的數值方法。

Vigna & Haberman (2001)推導出確定提撥退休金制度下離散時間的最適投資策略封閉解,透過該模型,我們可以比較本研究所建議的方法與真正封閉解的差異,證實本研究所建議的方法的確可以提供動態規劃問題一個接近且有效率的數值解法。接著根據Yvonne C.(2002、2003)的抽樣方法,希望在進行模擬時,能找出模擬情境的特性並對這些情境進行抽樣,藉此減少情境數以增加電腦運算的效率。最後應用在Vigna & Haberman (2001)的修正模型以及Haberman & Vigna (2002)的模型上,說明了本研究所建議的數值方法也適用在各類型的動態規劃上,包含理論封閉解不存在以及求解非常複雜的問題。
zh_TW
dc.description.tableofcontents 第壹章 緒論 1
第一節、 研究動機及目的 1
第二節、 研究架構 2
第貳章 文獻回顧 4
第一節、 傳統模型探討 4
第二節、 動態規劃介紹 4
第三節、 動態規劃數值解 6
第四節、 情境抽樣 6
第參章 資產累積模型與目標函數 7
第一節、 帳戶價值的累積 7
1. 各期帳戶目標價值 8
2. 投資決策的最適化 8
第二節、 最適動態策略 9
第肆章 動態規劃數值解 11
第一節、 數值解方法-利用決策表 11
第二節、 決策表的建構 12
1. 建構第T期投資決策表 13
2. 建構第T-1期投資決策表 14
3. 建構第T-2期、第T-3期…投資決策表 15
第伍章 數值解與理論解之比較 16
第一節、 理論解與數值解 16
第二節、 結果分析 19
第三節、 重複模擬 21
第陸章 情境抽樣 23
第一節、 均勻抽樣法 23
1. 定義顯著測度 23
2. 系統抽樣 23
3. 顯著測度的修正 24
第二節、 數值結果 24
1. 顯著測度的機率密度函數 25
2. 抽樣結果 25
3. 均勻抽樣法有效性之驗證 26
第柒章 數值解方法的應用 29
第一節、 Vigna & Haberman (2001)的修正 29
1. 資產投資模型 29
2. 數值結果 29
第二節、 Haberman & Vigna (2002) 30
1. 資產投資模型 31
2. 理論封閉解 32
3. 數值結果 34
第捌章 結論與建議 36
參考文獻 38
附錄一 10000組情境的數值結果 40
附錄二 均勻抽樣法的數值結果 41
附錄三 1000組情境的數值結果 42
附錄四 有買空和賣空限制下的投資決策表 43
附錄五 三種資產下的投資決策表 46
zh_TW
dc.format.extent 113689 bytes-
dc.format.extent 207816 bytes-
dc.format.extent 162284 bytes-
dc.format.extent 234777 bytes-
dc.format.extent 221720 bytes-
dc.format.extent 234526 bytes-
dc.format.extent 450685 bytes-
dc.format.extent 552118 bytes-
dc.format.extent 499664 bytes-
dc.format.extent 420629 bytes-
dc.format.extent 485494 bytes-
dc.format.extent 220581 bytes-
dc.format.extent 210223 bytes-
dc.format.extent 437676 bytes-
dc.format.mimetype application/pdf-
dc.format.mimetype application/pdf-
dc.format.mimetype application/pdf-
dc.format.mimetype application/pdf-
dc.format.mimetype application/pdf-
dc.format.mimetype application/pdf-
dc.format.mimetype application/pdf-
dc.format.mimetype application/pdf-
dc.format.mimetype application/pdf-
dc.format.mimetype application/pdf-
dc.format.mimetype application/pdf-
dc.format.mimetype application/pdf-
dc.format.mimetype application/pdf-
dc.format.mimetype application/pdf-
dc.language.iso en_US-
dc.source.uri (資料來源) http://thesis.lib.nccu.edu.tw/record/#G0096358021en_US
dc.subject (關鍵詞) 資產配置zh_TW
dc.subject (關鍵詞) 動態規劃zh_TW
dc.subject (關鍵詞) 數值解zh_TW
dc.subject (關鍵詞) Asset Allocationen_US
dc.subject (關鍵詞) Dynamic Programmingen_US
dc.subject (關鍵詞) Numerical Solutionen_US
dc.title (題名) 最適資產配置-動態規劃問題之數值解zh_TW
dc.title (題名) Optimal asset allocation-the numerical solution of dynamic programmingen_US
dc.type (資料類型) thesisen
dc.relation.reference (參考文獻) 1. Chang, S.C., (1999), "Optimal Pension Funding Through Dynamic Simulations: the Case of Taiwan Public Employees Retirement System." Insurance: Mathematics and Economics, 24, 187-199.zh_TW
dc.relation.reference (參考文獻) 2. Chryssoverghi and Bacopoulos, Discrete approximation of relaxed optimal control problems. Journal of Optimization Theory and Applications, 1990, 395-407zh_TW
dc.relation.reference (參考文獻) 3. C.-S. Huang, S. Wang and K.L. Teo, Solving Hamilton-Jacobi-Bellman equations by a modified method of characteristics. Nonlinear Analysis 40 (2000), 279-293.zh_TW
dc.relation.reference (參考文獻) 4. Haberman, S., and Sung, J.H., (1994), "Dynamic Approaches to Pension Funding" Insurance: Mathematics and Economics, 15, p151-162.zh_TW
dc.relation.reference (參考文獻) 5. Haberman, S., and Vigna, E., (2002), "Optimal Investment Strategies and risk measures in defined contribution pension schemes." Insurance mathematics and Economics, 31, p35-69.zh_TW
dc.relation.reference (參考文獻) 6. M. A. H. Dempster, (1980), "Stochastic programming " International Conference on Stochastic Programming, Oxford, 1974zh_TW
dc.relation.reference (參考文獻) 7. Markowitz, and Harry, (1952).“Portfolio Selection”. Journal of Finance ,pp.77-91.zh_TW
dc.relation.reference (參考文獻) 8. M. G. Crandall and P.L. Lions, Two approximations of solutions of Hamilton-Jacobi equations. Mathematics of Computation 43 (1984), 1-19.zh_TW
dc.relation.reference (參考文獻) 9. Sherris,(1992),”Portfolio Selection and Matching :A synthesis”. J.I.A.119,I,pp.87-105.zh_TW
dc.relation.reference (參考文獻) 10. S. Wang, F. Gao and K.L. Teo, An upwind finite-difference method for the approximation of viscosity solutions to Hamilton-Jacobi-Bellman equations. IMA J. Math. Control 17 (2000), 167-178.zh_TW
dc.relation.reference (參考文獻) 11. Vigna, E., and Haberman, S., (2001), "Optimal Investment Strategy for defined contribution pension schemes." Insurance mathematics and Economics, 28, p233-262.zh_TW
dc.relation.reference (參考文獻) 12. Wilkie, A.D.,(1985).“Portfolio Selection in the Presence of Fixed Liabilities: A comment on The Matching of Assets to Liabilities” Journal of Institute of Actuaries,112, 229-277zh_TW
dc.relation.reference (參考文獻) 13. Wise, A.J., (1984a)”A theoretical analysis of the matching of assets to liabilities.” Journal of Institute of Actuaries,111(Part II):375-402zh_TW
dc.relation.reference (參考文獻) 14. Wise, A.J., (1984b)”The matching of assets to liabilities.” Journal of the Institute of Actuaries,111(Part II):445-501zh_TW
dc.relation.reference (參考文獻) 15. Wise, A.J.,(1987a) “Matching and Portfolio Selection:Part 1 “Journal of Institute of Actuaries,114, 113-133zh_TW
dc.relation.reference (參考文獻) 16. Wise, A.J.,(1987b) “Matching and Portfolio Selection:Part 2” Journal of Institute of Actuaries,114, 551-568zh_TW
dc.relation.reference (參考文獻) 17. Yvonne, C., (2002), "Efficient Stochastic Modeling For Large and Consolidated Insurance Business:Interest Rate Sampling Algorithms." North American Actuarial Journal, Vol.6 Iss. 3, p88-103.zh_TW
dc.relation.reference (參考文獻) 18. Yvonne, C., (2003), " Efficient Stochastic Modeling:From Scenario Sampling To Parametric Model Fitting Utilizing ASEM as an Exampling." International Professional Development Symposium Co-sponsored by Canadian Institute of Actuaries, Actuarial Foundation, and Society of Actuaries, Toronto, Canada.zh_TW