Skip to main content
Fachgebiete
Automobil + Motoren Bauwesen + Immobilien Business IT + Informatik Elektrotechnik + Elektronik Energie + Nachhaltigkeit Finance + Banking Management + Führung Marketing + Vertrieb Maschinenbau + Werkstoffe Versicherung + Risiko
DE
EN
Themenseiten
Organisationspsychologie Projektmanagement Marketing Smart Manufacturing
Bücher
Zeitschriften
Weitere Formate
Podcasts Webinare Technik Webinare Wirtschaft Kongresse Veranstaltungskalender Awards
Jetzt Einzelzugang starten
Zugang für Unternehmen
Referenzkunden
ATZ-Fachkongress

Chassis.tech plus 2024


4 Kongresse in einer Veranstaltung

Treffen Sie in München die Fachleute von Chassis, Lenkung, Bremsen sowie Reifen/Räder.
Erweiterte Suche
Anmelden
nach oben

2010 | Buch

Natural Computing in Computational Finance (Volume 3): Introduction Kapitel lesen Erstes Kapitel lesen

Natural Computing in Computational Finance

herausgegeben von: Anthony Brabazon, Michael O’Neill, Dietmar G. Maringer

Verlag: Springer Berlin Heidelberg

Buchreihe : Studies in Computational Intelligence

Enthalten in: Springer Professional "Wirtschaft+Technik" , Springer Professional "Technik" , Springer Professional "Wirtschaft"

Einloggen, um Zugang zu erhalten
insite
SUCHEN

Inhaltsverzeichnis

Frontmatter

Natural Computing in Computational Finance (Volume 3): Introduction

Natural Computing in Computational Finance (Volume 3): Introduction
Abstract
Computational Finance covers a wide and still growing array of topics and methods within quantitative economics. The core focus has long been on efficient methods, models and algorithms for numerically demanding problems. The advent of new computational methods, together with the advances in available hardware, has pushed the boundaries of this field outwards. Not only can the complexity of investigated problems be increased, one can even approach problems that defy traditional analytical examination all together. One major contributor of such methods is natural computing.
Anthony Brabazon, Michael O’Neill, Dietmar Maringer

Part I: Financial and Agent-Based Models

Frontmatter

Open Access

Robust Regression with Optimisation Heuristics
Summary
Linear regression is widely-used in finance. While the standard method to obtain parameter estimates, Least Squares, has very appealing theoretical and numerical properties, obtained estimates are often unstable in the presence of extreme observations which are rather common in financial time series. One approach to deal with such extreme observations is the application of robust or resistant estimators, like Least Quantile of Squares estimators. Unfortunately, for many such alternative approaches, the estimation is much more difficult than in the Least Squares case, as the objective function is not convex and often has many local optima. We apply different heuristic methods like Differential Evolution, Particle Swarm and Threshold Accepting to obtain parameter estimates. Particular emphasis is put on the convergence properties of these techniques for fixed computational resources, and the techniques’ sensitivity for different parameter settings.
Manfred Gilli, Enrico Schumann
PDF
Evolutionary Estimation of a Coupled Markov Chain Credit Risk Model
Summary
There exists a range of different models for estimating and simulating credit risk transitions to optimally manage credit risk portfolios and products. In this chapter we present a Coupled Markov Chain approach to model rating transitions and thereby default probabilities of companies. As the likelihood of the model turns out to be a non-convex function of the parameters to be estimated, we apply heuristics to find the ML estimators. To this end, we outline the model and its likelihood function, and present both a Particle Swarm Optimization algorithm, as well as an Evolutionary Optimization algorithm to maximize the likelihood function. Numerical results are shown which suggest a further application of evolutionary optimization techniques for credit risk management.
Ronald Hochreiter, David Wozabal
Evolutionary Computation and Trade Execution
Summary
Although there is a plentiful literature on the use of evolutionary methodologies for the trading of financial assets, little attention has been paid to the issue of efficient trade execution. Trade execution is concerned with the actual mechanics of buying or selling the desired amount of a financial instrument of interest. This chapter introduces the concept of trade execution and outlines the limited prior work applying evolutionary computing methods for this task. Furthermore, we build an Agent-based Artificial Stock Market and apply a Genetic Algorithm to evolve an efficient trade execution strategy. Finally, we suggest a number of opportunities for future research.
Wei Cui, Anthony Brabazon, Michael O’Neill
Agent-Based Co-operative Co-evolutionary Algorithms for Multi-objective Portfolio Optimization
Summary
Co-evolutionary techniques makes it possible to apply evolutionary algorithms in the cases when it is not possible to formulate explicit fitness function. In the case of social and economic simulations such techniques provide us tools for modeling interactions between social and economic agents-especially when agent-based models of co-evolution are used. In this chapter agent-based versions of multi-objective co-operative co-evolutionary algorithms are presented and applied to portfolio optimization problem. The agent-based algorithms are compared with classical versions of SPEA2 and NSGA2 multi-objective evolutionary algorithms with the use of multi-objective test problems and multi-objective portfolio optimization problem. Presented results show that agent-based algorithms obtain better results in the case of multi-objective test problems, while in the case of portfolio optimization problem results are mixed.
Rafał Dreżewski, Krystian Obrocki, Leszek Siwik
Inferring Trader’s Behavior from Prices
Summary
We propose a representation of the stock market as a group of rule-based trading agents, with the agents evolved using past prices. We encode each rule-based agent as a genome, and then describe how a steady-state genetic algorithm can evolve a group of these genomes (i.e. an inverted market) using past stock prices. This market is then used to generate forecasts of future stock prices, which are compared to actual future stock prices. We show how our method outperforms standard financial time-series forecasting models, such as ARIMA and Lognormal, on actual stock price data taken from real-world archives.
Louis Charbonneau, Nawwaf Kharma

Part II: Dynamic Strategies and Algorithmic Trading

Frontmatter
Index Mutual Fund Replication
Summary
This chapter discusses the application of an index tracking technique to mutual fund replication problems. By using a tracking error (TE) minimization method and two tactical rebalancing strategies (i.e. the calendar based strategy and the tolerance triggered strategy), a multiperiod fund tracking model is developed that replicates S&P 500 mutual fund returns. The impact of excess returns and loss aversion on overall tracking performance is also discussed in two extended cases of the original TE optimization. An evolutionary method, Differential Evolution, is used for optimizing the asset weights. According to the experiment results, it is found that the proposed model replicates the first two moments of the fund returns by using only five equities. The TE optimization strategy under loss aversion with tolerance triggered rebalancing dominates other combinations studied with regard to tracking ability and cost efficiency.
Jin Zhang, Dietmar Maringer
Frequent Knowledge Patterns in Evolutionary Decision Support Systems for Financial Time Series Analysis
Summary
This chapter discusses extracting and reusing frequent knowledge patterns in building trading experts in an evolutionary decision support system for financial time series analysis. It focuses on trading experts built by an evolutionary algorithm as binary sequences representing subsets of a specific set of trading rules, where frequent knowledge patterns correspond to common building blocks of trading rules occurring in previous trading experts. Reusing frequent knowledge patterns leads to a significant reduction of the search space, due to fixing a part of chromosome and running the evolution process to set only the remaining genes, without significant decreases of results.
This chapter presents a number of experiments carried out on financial time series from the Paris Stock Exchange, discusses some examples of the frequent knowledge patterns as well as analyses the results obtained in terms of their financial relevance and compares them with some popular benchmarks.
Piotr Lipinski
Modeling Turning Points in Financial Markets with Soft Computing Techniques
Summary
Two independent evolutionary modeling methods, based on fuzzy logic and neural networks respectively, are applied to predicting trend reversals in financial time series of the financial instruments S&P 500, crude oil and gold, and their performances are compared. Both methods are found to give essentially the same results, indicating that trend reversals are partially predictable.
Antonia Azzini, Célia da Costa Pereira, Andrea G. B. Tettamanzi
Evolutionary Money Management
Summary
This paper evolves trading strategies using genetic programming on high-frequency tick data of the USD/EUR exchange rate covering the calendar year 2006. This paper proposes a novel quad tree structure for trading system design. The architecture consists of four trees each solving a separate task, but mutually dependent for overall performance. Specifically, the functions of the trees are related to initiating (“entry”) and terminating (“exit”) long and short positions. Thus, evaluation is contingent on the current market position. Using this architecture the paper investigates the effects of money management. Money management refers to certain measures that traders use to control risk and take profits, but the findings in this paper suggest that it has detrimental effects on performance.
Philip Saks, Dietmar Maringer
Interday and Intraday Stock Trading Using Probabilistic Adaptive Mapping Developmental Genetic Programming and Linear Genetic Programming
Summary
A developmental co-evolutionary genetic programming approach (PAM DGP) is compared to a standard linear genetic programming (LGP) implementation for trading of stocks in the technology sector. Both interday and intraday data for these stocks were analyzed, where both implementations were found to be impressively robust to market fluctuations while reacting efficiently to opportunities for profit. PAM DGP proved slightly more reactive to market changes compared to LGP for intraday data, where the converse held true for interday data. Both implementations had very impressive accuracy in choosing both profitable buy trades and sells that prevented losses for both interday and intraday stock data. These successful trades occurred in the context of moderately active trading for interday prices and lower levels of trading for intraday prices.
Garnett Wilson, Wolfgang Banzhaf
Backmatter
Metadaten
Titel
Natural Computing in Computational Finance
herausgegeben von
Anthony Brabazon
Michael O’Neill
Dietmar G. Maringer
Copyright-Jahr
2010
Verlag
Springer Berlin Heidelberg
Electronic ISBN
978-3-642-13950-5
Print ISBN
978-3-642-13949-9
DOI
https://doi.org/10.1007/978-3-642-13950-5

Premium Partner

    Bildnachweise