+612 9045 4394
$7.95 Delivery per order to Australia and New Zealand
100% Australian owned
Over a hundred thousand in-stock titles ready to ship
Artificial Intelligence in Finance and Investing : Theory and Application in Portfolio Management - Robert R. Trippi

Artificial Intelligence in Finance and Investing

Theory and Application in Portfolio Management

Hardcover Published: 19th November 1995
ISBN: 9781557388681
Number Of Pages: 246

Share This Book:


RRP $168.99
or 4 easy payments of $30.45 with Learn more
Ships in 7 to 10 business days

Earn 244 Qantas Points
on this Book

In Artificial Intelligence in Finance and Investing, authors Robert Trippi and Jae Lee explain this fascinating new technology in terms that portfolio managers, institutional investors, investment analysis, and information systems professionals can understand. Using real-life examples and a practical approach, this rare and readable volume discusses the entire field of artificial intelligence of relevance to investing, so that readers can realize the benefits and evaluate the features of existing or proposed systems, and ultimately construct their own systems. Topics include using Expert Systems for Asset Allocation, Timing Decisions, Pattern Recognition, and Risk Assessment; overview of Popular Knowledge-Based Systems; construction of Synergistic Rule Bases for Securities Selection; incorporating the Markowitz Portfolio Optimization Model into Knowledge-Based Systems; Bayesian Theory and Fuzzy Logic System Components; Machine Learning in Portfolio Selection and Investment Timing, including Pattern-Based Learning and Fenetic Algorithms; and Neural Network-Based Systems.
To illustrate the concepts presented in the book, the authors conclude with a valuable practice session and analysis of a typical knowledge-based system for investment management, K-FOLIO. For those who want to stay on the cutting edge of the "application" revolution, Artificial Intelligence in Finance and Investing offers a pragmatic introduction to the use of knowledge-based systems in securities selection and portfolio management.

List of Figuresp. xv
List of Tablesp. xix
Prefacep. xxi
Introductionp. 1
Artificial Intelligence and Investingp. 1
The Organization of This Bookp. 3
Nature of the Security Investment Domainp. 7
Characteristics of Investment Assetsp. 8
Theories of Stock Price Determinationp. 9
Random, Ordered, and Complex Systemsp. 10
Value-Based Investingp. 10
The Efficient Market Hypothesisp. 11
Beyond the EMHp. 12
Risk Issuesp. 14
What Is Risk?p. 14
Cognitive Error and Stochastic Risk Modelingp. 14
Market Psychology and Noisep. 15
Institutional Trading and Market Behaviorp. 15
Agency and Database Commonality Effectsp. 15
Trading Dynamics and Instabilityp. 16
The Exploitation of Anomaliesp. 17
The Cost and Value of Informationp. 17
Implied Probability Distributionsp. 17
Decision Rules and Black Box Investingp. 19
Conclusionsp. 20
Endnotesp. 20
Referencesp. 21
Modern Approaches to Portfolio Selectionp. 23
Introductionp. 23
Goal Programmingp. 25
Mean-Variance Optimizationp. 27
The Markowitz Modelp. 27
The Efficient Frontierp. 29
Model Enhancementp. 30
Beta and Index Modelsp. 31
Security Risk and Portfolio Riskp. 35
The Role of Riskless Assetsp. 36
Mean Absolute Deviation Optimizationp. 37
Markowitz and Capital-Asset Pricing Model Limitationsp. 38
CAPM Extensions and Program Tradingp. 40
Endnotesp. 41
Referencesp. 43
Artificial Intelligence in Investment Management: An Overviewp. 45
Knowledge-Based Systems, Auto-Learning Systems, and Intelligent Systemsp. 45
Introduction to Knowledge Representationp. 46
Expert Systems and Financial Servicesp. 51
An Early ES for Portfolio Selectionp. 52
Contemporary Systemsp. 53
Emerging Artificial Intelligence Technologiesp. 57
Conclusionsp. 61
Endnotesp. 62
Referencesp. 62
Portfolio-Selection System Issuesp. 67
Expert System Componentsp. 67
Rule-Based Systemsp. 70
Representation in Rule-Based Systemsp. 70
Inference Strategiesp. 71
Frame-Based Systemsp. 73
Investment Support Featuresp. 75
Knowledge Representationp. 75
Inference and Explanationp. 77
Knowledge Acquisition and Maintenancep. 78
System Architecturep. 79
Referencesp. 79
Knowledge Representation and Inferencep. 81
Introductionp. 82
The Rule Basep. 82
Syntax of Rulesp. 82
Example Rulesp. 82
The Databasep. 84
Relational Database Examplesp. 84
Inheritance, Average-up, and Sum-upp. 85
Working Memoryp. 87
Security Inferencep. 89
Conflict-Set Generationp. 90
Composite-Grade Generationp. 90
Explanation Synthesisp. 93
Dialoguesp. 93
Company-Based Dialoguep. 95
Industry-Based Dialoguep. 96
Criteria-Based Dialoguep. 97
Grade-Based Dialoguep. 98
Conclusionsp. 98
Referencesp. 99
Handling Investment Uncertaintiesp. 101
Introductionp. 102
The Bayesian Approachp. 102
Definitions and Formulasp. 102
An Illustrative Examplep. 104
Handling Uncertain Evidencep. 106
Handling More Than Two Levels of Hypothesesp. 108
Inference Strategy in the Bayesian Approachp. 108
The Sequence of Applying Evidencep. 109
Stopping Rulesp. 110
Discussionp. 111
The Certainty Factor Approachp. 111
The Fuzzy Logic Approachp. 112
Possibility Theoryp. 112
Fuzzy Logicp. 112
A Fuzzy Logic-Based Expert Systemp. 113
A Compensatory Fuzzy-Logic Approachp. 114
Attenuation by the Credibility of Rulesp. 115
Discussionp. 115
Nonmonotonic Reasoningp. 116
Conclusionsp. 116
Referencesp. 116
Knowledge Acquisition, Integration, and Maintenancep. 119
Introductionp. 119
The Representation and Integration of Investor Preferencesp. 120
The Organization of Investor Preference Basesp. 120
The Representation of Investor Preferencesp. 120
The Integration and Interpretation of Preferencesp. 123
Sources for Knowledge Acquisitionp. 124
Knowledge Structure and Maintenancep. 125
Structuring Knowledgep. 125
Maintenance Aidsp. 127
The Selective Integration of Relevant Knowledgep. 128
Conclusionsp. 130
Referencesp. 130
Machine Learningp. 131
Introductionp. 131
Why Machine Learning?p. 131
Machine-Learning Systemsp. 132
Learning Strategiesp. 133
Implied Distribution Surrogatesp. 133
Inductive Learningp. 134
ID3p. 135
The Concept-Learning Algorithmp. 135
Application of Inductive Learning to Investment Decisionsp. 139
The Potential of Inductive Learning in Investmentp. 139
Syntactic Pattern-Based Learningp. 143
The SYNPLE Frameworkp. 144
Performancep. 149
Genetic Adaptive Algorithmsp. 152
The Genetic Algorithm Approach to Learningp. 152
Problem Representation Issuesp. 153
A Genetic Algorithm for Trading Rule Generationp. 154
Conclusionsp. 156
Referencesp. 156
Neural Networksp. 159
Introductionp. 159
Architecture of Neural Networksp. 160
Learning in Neural Networksp. 162
Strengths and Weaknessesp. 164
Neural Network Applicationsp. 166
Neural Networks for Stock Price Predictionp. 167
Other Neural Network Applicationsp. 170
Example of Integrating Neural Networks and Rulesp. 173
Conclusionsp. 177
Referencesp. 178
Integrating Knowledge with Portfolio Optimizationp. 183
Introductionp. 183
An Unenhanced Markowitz Model Examplep. 184
The Interpretation of Knowledgep. 185
Quadratic Programming with Prioritized Decision Variablesp. 188
Performance Evaluationp. 192
Conclusionsp. 194
Referencesp. 195
Integrating Knowledge with Databasesp. 197
Introductionp. 198
Database Evolutionp. 198
Relational Databasesp. 198
The Advent of Knowledge Basesp. 199
Object-Oriented Databasesp. 200
The Management of Financial Datap. 201
The Organization of Financial Datap. 201
The Use of Financial Datap. 204
The Management of Price and Trading Volume Datap. 204
The Organization of Price and Volume Datap. 204
The Uses of Price and Volume Datap. 205
Management of the Function Basep. 205
Functionsp. 205
Reserved Wordsp. 206
Conclusionsp. 207
Referencesp. 207
An Illustrative Session with K-FOLIOp. 209
Introductionp. 209
Selecting Investment Characteristics, Environmental Assumptions, and Knowledge Sourcesp. 210
Individual Stock Evaluationp. 212
Industry Evaluationp. 212
Criteria-Based Dialoguep. 213
Grade-Based Listingp. 214
Portfolio Selectionp. 215
Conclusionsp. 217
Referencesp. 227
Concluding Remarksp. 229
System Design Criteria: A Summaryp. 229
Directions for Future Researchp. 231
Name Indexp. 233
Subject Indexp. 237
Table of Contents provided by Syndetics. All Rights Reserved.

ISBN: 9781557388681
ISBN-10: 1557388687
Audience: Professional
Format: Hardcover
Language: English
Number Of Pages: 246
Published: 19th November 1995
Country of Publication: US
Dimensions (cm): 23.77 x 15.8  x 2.24
Weight (kg): 0.6
Edition Number: 2
Edition Type: Revised

Earn 244 Qantas Points
on this Book