FU Berlin Digitale Dissertation
Thomas Schwerk : NELION Ein Nicht-Lineares Aktien-Prognose- und Portfolio-Management-System NELION
|Abstract| |Table of Contents| |More Information|

Abstract NELION is a database application running on MS SQL Server that automatically downloads stock data from the Internet and predicts future stock prices using auto-regressive as well as non-linear models: k-nearest neighbors, Hidden Markov Models and Artificial Neural Networks. Using the raw predictions, the software then suggests specific purchases for each investor, depending on the current portfolio and investor specific risk parameters. These include expected return, volatility and correlation aversity as well as volume and model error dependence. The output is done via Internet e-mail, mobile phone SMS or an application, which accesses the database directly. Investors can choose between daily, weekly and monthly purchase suggestions, as well as portfolio value updates. A "Test Investor" module allows potential investors to identify how a specific set of parameters would have traded in the past so that promising parameter combinations can be identified. An "Auto Investor" function simulated a real investor since May 15, 1999 in a "live" simulation of U.S. stocks. All trades were penalized with transaction costs, reflecting a realistic scenario.

Table of Contents Download the whole PhDthesis as a zip-tar file or as zip-File For download in PDF format click the chapter title Title and Contents Table of Contents Preface 3 1 Introduction 10 2Predicting Stock Prices 17 2.1 Efficient Market Hypothesis 17 2.2 Mathematical Modeling Techniques 21 3Portfolio Management 69 3.1 Return 70 3.2 Risk 71 3.3 The Optimal Portfolio 73 3.4 Applying the Theory 78 4 Methodology 82 4.1 Overview 82 4.2 The HTML Interface 82 4.3 The Administration Tool 83 4.4 The Database 84 4.5 The Task Agent 87 5 Implementation 105 5.1 Overview 105 5.2 The HTML Interface 106 5.3 The Administration Tool 110 5.4 The Database 115 5.5 The Task Agent 118 6Experimental Results 129 6.1 Test Investor Identification 129 6.2 Testing the Profiles 134 6.3 Model Distribution 138 6.4 Daily Operation 139 7 Conclusion 140 8 Appendix A: Investor Profiles 144 8.1 Conservative Investors 146 8.2 High Risk Investors 152 9 Appendix B: Portfolio History 158 9.1 Transactions by Conservative Investor 158 9.2 Transactions by High Risk Investor 160 10Appendix C: Screen Shots 161 11Appendix D: Conceptual Data Model 167 12Appendix E: Stocks Tracked in the Simulation Appendix E: 168 13 Appendix F: Bibliography 173 14 Appendix G: Curriculum Vitae for Thomas Schwerk 186

More Information:
Online available:	http://www.diss.fu-berlin.de/2001/85/indexe.html
Language of PhDThesis:	english
Keywords:	Non-linear Stock Prediction Portfolio
DNB-Sachgruppe:	28 Informatik, Datenverarbeitung
Classification ZDM:	R50
Date of disputation:	13-Feb-2001
PhDThesis from:	Fachbereich Mathematik u. Informatik, Freie Universität Berlin
First Referee:	Prof. Dr. Raul Rojas
Second Referee:	Prof. Dr. Volker Sperschneider
Contact (Author):	Thomas@Schwerk.com
Contact (Advisor):	rojas@inf.fu-berlin.de
Date created:	04-May-2001
Date available:	11-Jun-2001

 

---

|| DARWIN|| Digitale Dissertationen || Dissertation|| German Version|| FU Berlin|| Seitenanfang ||

---

	Fragen und Kommentare an: darwin@inf.fu-berlin.de
© Freie Universität Berlin 1999