Claus de Castro Aranha

Optimization of the trading rule in foreign exchange using genetic algorithm

The generation of profitable trading rules for Foreign Exchange (FX) investments is a difficult but popular problem. The use of Machine Learning in this problem allows us to obtain objective results by using information of the past market behavior. In this paper, we propose a Genetic Algorithm (GA) system to automatically generate trading rules based on Technical Indexes. Unlike related researches in the area, our work focuses on calculating the most appropriate trade timing, instead of predicting the trading prices.

The Memetic Tree-based Genetic Algorithm and its application to Portfolio Optimization

We introduce a Memetic system to solve the application problem of Financial Portfolio Optimization. This problem consists of selecting a number of assets from a market and their relative weights to form an investment strategy. These weights must be optimized against a utility function that considers the expected return of each asset, and their co-variance; which means that as the number of available assets increases, the search space increases exponentially. Our method introduces two new concepts that set it apart from previous evolutionary based approaches. The first is the Tree-based Genetic Algorithm (GA), a recursive representation for individuals which allows the genome to learn information regarding relationships between the assets, and the evaluation of intermediate nodes. The second is the hybridization with local search, which allows the system to fine-tune the weights of assets after the tree structure has been decided. These two innovations make our system superior than other representations used for multi-weight assignment of portfolios.

A tree-based GA representation for the portfolio optimization problem

Recently, a number of works have been done on how to use Genetic Algorithms to solve the Portfolio Optimization problem, which is an instance of the Resource Allocation problem class. Almost all these works use a similar genomic representation of the portfolio: An array, either real, where each element represents the weight of an asset in the portfolio, or binary, where each element represents the presence or absence of an asset in the portfolio. In this work, we explore a novel representation for this problem. We use a tree structure to represent a portfolio for the Genetic Algorithm. Intermediate nodes represent the weights, and the leaves represent the assets. We argue that while the Array representation has no internal structure, the Tree approach allows for the preservation of building blocks, and accelerates the evolution of a good solution. The initial experimental results support our opinions regarding this new genome representation. We believe that this approach can be used for other instances of Resource Allocation problems.

Using memetic algorithms to improve portfolio performance in static and dynamic trading scenarios

The Portfolio Optimization problem consists of the selection of a group of assets to a long-term fund in order to minimize the risk and maximize the return of the investment. This is a multi-objective (risk, return) resource allocation problem, where the aim is to correctly assign weights to the set of available assets, which determines the amount of capital to be invested in each asset. In this work, we introduce a Memetic Algorithm for portfolio optimization. Our system is based on a tree-structured genome representation which selects assets from the market and establish relationships between them, and a local hill climbing function which uses the information available from the tree-structure to calculate the weights of the selected assets. We use simulations based on historical data to test our system and compare it to previous approaches. In these experiments, our system shows that it is able to adapt to aggressive changes in the market, like the crash of 2008, with reduced trading cost.

Practical Applications of Evolutionary Computation to Financial Engineering

Practical Applications of Evolutionary Computation to Financial Engineering presents the state of the art techniques in Financial Engineering using recent results in Machine Learning and Evolutionary Computation. This book bridges the gap between academics in computer science and traders and explains the basic ideas of the proposed systems and the financial problems in ways that can be understood by readers without previous knowledge on either of the fields. To cement the ideas discussed in the book, software packages are offered that implement the systems described within. The book is structured so that each chapter can be read independently from the others. Chapters 1 and 2 describe evolutionary computation. The third chapter is an introduction to financial engineering problems for readers who are unfamiliar with this area. The following chapters each deal, in turn, with a different problem in the financial engineering field describing each problem in detail and focusing on solutions based on evolutionary computation. Finally, the two appendixes describe software packages that implement the solutions discussed in this book, including installation manuals and parameter explanations.

Money in trees: How memes, trees, and isolation can optimize financial portfolios

In this paper, we propose the hybrid application of two nature inspired approaches to the problem of Portfolio Optimization. This problem consists of the selection and weighting of financial assets. Its goal is to form an investment strategy which maximizes a return measure and minimizes a risk measure. We perform a series of simulation experiments with historical data in the NASDAQ and S&P500 markets between 2006 and 2008. The results show that adding a terrain strategy to a previously successful Memetic Algorithm promoted niching and speciation of the population, which led to a significant improvement in the performance when compared to previous evolutionary methods. We also show that the use of Memetic Algorithms gives the evolved solutions a degree of adaptability to changes in a dynamic market.

PSO Algorithm with Transition Probability Based on Hamming Distance for Graph Coloring Problem

In this paper, we propose a PSO algorithm with transition probability based on Hamming distance for solving planar graph coloring problems. PSO was originally intended to handle only continuous optimization problems. To apply PSO to discrete problems, the standard arithmetic operators of PSO need to be redefined over discrete space. In this work, we propose a new algorithm that uses transition probability based on Hamming distance into PSO. The experimental results show that the new algorithm can get higher success rate and smaller average iterations than a Genetic Algorithm and the conventional PSO.

Optimization of oil reservoir models using tuned evolutionary algorithms and adaptive differential evolution

In the petroleum industry, accurate oil reservoir models are crucial in the decision making process. One critical step in reservoir modeling is History Matching (HM), where the parameters of a reservoir model are adjusted in order to improve its accuracy and enhance future prediction. Recent works applied evolutionary algorithms (EAs) such as GA, DE and PSO for the HM problem, but they have been limited to classical versions of these algorithms. A significant obstacle to applying EAs to HM is that each call to the fitness function requires an expensive simulation, making it difficult to tune the control parameters for EAs in order to obtain the best performance. We apply and evaluate state-of-the-art, adaptive differential algorithms (SHADE and jDE), as well as non-adaptive evolutionary algorithms (standard DE, PSO) that have been tuned using standard black-box benchmark functions as training instances. Both of these approaches result in significant improvements compared to standard methods in the HM literature. We also apply fitness distance correlation analysis to the search space explored by our algorithms in order to better understand the landscape of the HM problem.

Introduction to Genetic Algorithms

We can take from the above expert that a large part of technological and social innovations come from improvements on already existing ideas. It could not be in any other way: the human being has an irresistible urge to explore the world around it and modify it, and this includes both the natural world, and that created by his ancestors.

Application of a Memetic Algorithm to the Portfolio Optimization Problem

We use local search to improve the performance of Genetic Algorithms applied the problem of Financial Portfolio Selection and Optimization. Our work describes the Tree based Genetic Algorithm for Portfolio Optimization. To improve this evolutionary system, we introduce a new guided crossover operator, which we call the BWS, and add a local optimization step. The performance of the system increases noticeably on simulated experiments with historical data.