臺灣博碩士論文加值系統

「資產配置」即是實踐了投資分散的原則，藉由將資金分散投資於不同的資本市場，來降低投資的風險。傳統上，以基於報酬 / 風險為基礎Markowitz E-V模式做為資產配置的方法。評價報酬 / 風險使用兩種方式：直接評價與多情境法。在使用多情境法時，必須面臨大量複雜的資料與各種不同的財務分析模式，增加了制訂投資決策的困難。智慧代理人系統藉由許多代理人合作完成任務的運作模式，產生很大的彈性，可解決使用多情境資產配置模式，所遭遇到大量財務資料與模式的困境。本研究基於智慧代理人系統架構，定義了Investor Agent、Asset Allocation Decision Support Agent、Scenario Define Agent、Scenario Probability Forecasting Agent、Asset Evaluation Agent、Financial Data Collection Agent等，模擬一個以多情境資產配置模式為基礎的資產配置決策環境。

Asset allocation is the choice of how much to invest among classes of assets to achieve the best portfolio given the investor’s objectives and investment constraints. The approach that explores the nature of risk-return trade-off and the principles of rational portfolio selection associated with it was first proposed by the Markowitz Model. In practice, the number of required data inputs for applying Markowitz model with multi-scenario analysis is extremely large. In addition, the sophisticated valuation models and computations complicate the situation. We therefore proposed an intelligent agent system for multi-scenario asset allocation decision support. By way of many intelligent agents’ co-work and coordination, the large amount of data computation and various jobs of analysis can be flexibly performed. In this thesis, we defined the roles and jobs of different agents, including: financial data collection agent, scenario-defined agent, scenario probability forecasting agent, investor agent, asset evaluation agent, and asset allocation decision support agent, to simulate multi-scenario asset allocation decisions.

書名頁 I
論文口試委員會審定書 II
授權書 III
中文摘要 V
英文摘要 VI
誌謝 VII
目錄 VIII
表目錄 XI
圖目錄 XIII
第一章 緒論 1
1.1 研究背景與動機 1
1.2 研究目的 4
1.3 研究架構 5
第二章 文獻探討 6
2.1 情境資產配置模式相關探討 6
2.1.1 資產配置之定義與源起 6
2.1.2 傳統資產配置模式 6
2.1.3 情境資產配置模式 12
2.2 建置多情境資產配置系統的挑戰 13
2.2.1 多情境資產配置系統流程 13
2.2.2 建構多情境資產配置系統的挑戰 15
2.3 智慧代理人系統相關探討 16
2.3.1 智慧代理人系統之源起與定義 16
2.3.2 代理人系統之分類 19
第三章 多情境資產配置之智慧代理人系統架構分析方法與系統需求 21
3.1 組織分析 21
3.1.1 任務分派模式 22
3.1.2 建置組織 24
3.2 代理人系統的行為與溝通行為分析 26
3.3 代理人系統的溝通語言 28
3.3.1 KQML 28
3.3.2 KIF 30
3.4 多情境資產配置之智慧代理人系統需求 31
第四章 多情境資產配置之智慧代理人系統架構 35
4.1 系統平台 35
4.2 系統組織結構 39
4.2.1 Top Organization 41
4.2.2 Asset Allocation Decision Support Organization 42
4.2.3 Scenario Define Organization 42
4.2.4 Scenario Probability Forecast Organization 43
4.2.5 Asset Evaluation Organization 44
4.2.6 Asset valuation under Scenario Evaluating Organization 45
4.2.7 Asset Correlations under Scenario Evaluating Organization 45
4.2.8 財務分析模式的組織 46
4.2.9 Financial Data Collection Organization 48
4.2.10 Math Organization 48
4.3 代理人的功能、行為與互動行為 49
4.3.1 Investor Agent 49
4.3.2 Asset Allocation Decision Support Agent 52
4.3.3 Scenario Define Agent 55
4.3.4 Scenario Probability Forecasting Agent 57
4.3.5 Asset Evaluation Agent 59
4.3.6 Asset valuation under Scenario Evaluating Agent 60
4.3.7 Asset Correlations under Scenario Evaluation Agent 62
4.3.8 財務分析之代理人系統 63
4.3.9 User Profile Agent 67
4.3.10 Math Agent 70
4.3.11 Computation Agent 71
4.3.12 Financial Data Collection Agent 72
4.3.13 Financial Data Gathering Agent 73
4.3.14 代理人系統的類型 74
4.4 代理人的溝通語言 76
4.4.1 Financial Data Collection Organization的溝通語言 77
4.4.2 User Profile Agent的溝通語言 80
4.4.3 Math Organization的溝通語言 81
4.4.4 Scenario Define Organization的溝通語言 84
4.4.5 Scenario Probability Forecasting Organization的溝通語言 87
4.4.6 AVSE Organization的溝通語言 89
4.4.7 ACSE Organization的溝通語言 92
4.4.8 Asset Evaluation Agent的溝通語言 95
4.4.9 Asset Allocation Decsion Suuport Agent的溝通語言 96
第五章 系統雛形建置 98
5.1 系統範圍 98
5-2 系統展示 98
第六章 結論與未來研究方向 103
6.1 研究結論 103
6.2 未來研究方向 103
中文參考資料 104
附錄 106
A.1 Investor Agent 106
A.2 Asset Allocation Decision Support Agent 108
A.3 Scenario Define Agent 109
A.4 Scenario Probability Forecasting Agent 110
A.5 Asset Evaluation Agent 111
A.6 Asset Valuation under Scenario Evaluating Agent 112
A.7 Asset Valuation under Scenario Evaluating Agent 113
A.8 財務分析的代理人 115
A.9 User Profile Agent 117
A.10 Math Agent 119
A.11 Computation Agent 119
A.12 Financial Data Collection Agent 120
A.13 Financial Data Gethering Agent 121

中文參考資料
李青憲，〈多情境資產配置系統建置與實現〉，《元智大學資管所碩士論文》，民國91年。
閔志清，〈台灣基金資產配置之研究〉，《台大財務金融研究所碩士論文》，民國87年。
楊之宜譯，Charles P.Jones原著，《投資學分析與管理》第七版，台灣西書出版社，民國89年。
英文參考資料
ARPA Knowledge Sharing Initiative,” Specification of the KQML agent communication language”, ARPA Knowledge Sharing Initiative, External Interface Working Group working paper, July, 1993.
Brinson, Gary P., Brian D. Singer and Gilbert L. Beebower, “Determinants of Portfolio Performance Ⅱ: An Update”, Financial Analysts Journal, and May-June 1997.
Edesess, M. and G. A. Hambrecht, “Scenario Forecasting: Necessity, Not Choice”, Journal of Portfolio Management, 1980.
Elton, E.J.and M.J.Gruber, “Risk Reduction and Portfolio Size: An Analytical Solution”, Journal of Business, October, 1997.
Etzioni, Lesh, N., Segal, R.,”Building softbots for UNIX”, Software Agents, 1994.
Etzioni, O, and Weld, D.S.,”Intelligent Agents on Internet: Fact, Fiction, and Forecast”, IEEE Expert, August, 1995.
Fitzmaurice G.., Form-Countered Workflow Automation Using an Agent Framework”, Brown University, 1991.
FIPA Specification, http://www.fipa.org/.
Genesereth, M.R., and Ketchpel, S.P., “Software agents”, Communications of the ACM, 1994.
Hewitt, C., “Viewing Control Structures as Pattern of Passing Messages”, Artificial Intelligence, 1977.
Jacques Ferber,”Multi-Agent Systems: An Introduction to Distributed Artificial Intelligent”, ADDISON-WESLEY, 1999.
KIF Specification, http://logic.stanford.edu/kif/specification.html
Koskosidis, Y.A. and Duarte, A.M., “A Scenario-Based Approach to Active Asset Allocation”, Journal of Portfolio Management, 1997.
Markowitz, Harry M, “Portfolio Selection”, Journal of Finance, March, 1952.
Morin, E,”La Methode (1): la Nature de la Nature. Le Seuil”, 1977.
Newell, A., Shaw, J. and Simon, H.,”Empirical Exploration of Logic Theory Machine: A Case Study in Heuristics’ ”, Computers and Thought, 1963.
Nwana H.S.,”Software agent: an overview”, The Knowledge Engineering Review, 1996.
Wooldridge M., Jennings N.R.,”Intelligent agent: theory and practice”, The Knowledge Engineering Review, 1996.
Yannis Labrou, Tim Finin,”A Proposal for a new KQML Specification”, ARPA Knowledge Sharing Initiative, External Interface Working Group working paper, February, 1997.