J. Ignacio Hidalgo

Technical market indicators optimization using evolutionary algorithms

Real world stock markets predictions such as stock prices, unpredictability, and stock selection for portfolios, are challenging problems. Technical indicators are applied to interpret stock market trending and investing decision. The main difficulty of an indicator usage is deciding its appropriate parameter values, as number of days of the periods or quantity and kind of indicators. Each stock index, price or volatility series is different among the rest. In this work, Evolutionary Algorithms are proposed to discover correct indicator parameters in trading. In order to check this proposal the Moving Average Convergence-Divergence (MACD) technical indicator has been selected. Preliminary results show that this technique could work well on stock index trending. Indexes are smoother and easier to predict than stock prices. Required future works should include several indicators and additional parameters.

Is the island model fault tolerant

In this paper, we present a study on the fault tolerance nature of the island model when applied to Genetic Algorithms. Parallel and distributed models have been extensively applied to GAs when researchers tackle hard problems. The idea is both to reduce computing time while also improving diversity of populations and therefore quality of solutions. Nevertheless, there are few works dealing with the problem of faults that are usually present when a distributed infrastructure is employed for running the parallel algorithm. This paper studies the behavior of the Island Model when faults appear on a parallel computer or a network of computers. Two benchmark problems have been employed, and good results obtained for each of them allow us to reliably consider Island Model as a fault tolerant parallel algorithm.

Multiobjective optimization of technical market indicators

This paper deals with the optimization of technical indicators for stock market investment. Price prediction is a problem of great complexity and usually some technical indicators are used to predict the markets trends. The main difficulty in the use of technical indicators lies in deciding the parameters values. We proposed the use of Evolutionary Algorithms (EAs) to obtain the best parameter values belonging to a collection of indicators that will help in the buying and selling of shares. This paper extends the work presented on previous works by including additional indicators and applying them to more complex problems. In this way the Moving Averages Convergence-Divergence (MACD) indicator and the Relative Strength Index (RSI) oscillator have been selected to obtain the buying/selling signals. The experimental results indicate that our EAs offer a solution to the problem obtaining results that improve those obtained through technical indicators with their standard parameters.

glUCModel: a monitoring and modeling system for chronic diseases applied to diabetes.

Chronic patients must carry out a rigorous control of diverse factors in their lives. Diet, sport activity, medical analysis or blood glucose levels are some of them. This is a hard task, because some of these controls are performed very often, for instance some diabetics measure their glucose levels several times every day, or patients with chronic renal disease, a progressive loss in renal function, should strictly control their blood pressure and diet. In order to facilitate this task to both the patient and the physician, we have developed a web application for chronic diseases control which we have particularized to diabetes. This system, called glUCModel, improves the communication and interaction between patients and doctors, and eventually the quality of life of the former. Through a web application, patients can upload their personal and medical data, which are stored in a centralized database. In this way, doctors can consult this information and have a better control over patient records. glUCModel also presents three novelties in the disease management: a recommender system, an e-learning course and a module for automatic generation of glucose levels model. The recommender system uses Case Based Reasoning. It provides automatic recommendations to the patient, based on the recorded data and physician preferences, to improve their habits and knowledge about the disease. The e-learning course provides patients a space to consult information about the illness, and also to assess their own knowledge about the disease. Blood glucose levels are modeled by means of evolutionary computation, allowing to predict glucose levels using particular features of each patient. glUCModel was developed as a system where a web layer allows the access of the users from any device connected to the Internet, like desktop computers, tablets or mobile phones.

Bivariate empirical and n-variate Archimedean copulas in estimation of distribution algorithms

This paper investigates the use of empirical and Archimedean copulas as probabilistic models of continuous estimation of distribution algorithms (EDAs). A method for learning and sampling empirical bivariate copulas to be used in the context of n-dimensional EDAs is first introduced. Then, by using Archimedean copulas instead of empirical makes possible to construct n-dimensional copulas with the same purpose. Both copula-based EDAs are compared to other known continuous EDAs on a set of 24 functions and different number of variables. Experimental results show that the proposed copula-based EDAs achieve a better behaviour than previous approaches in a 20% of the benchmark functions.

Parallel Architectures and Bioinspired Algorithms

This monograph presents examples of best practices when combining bioinspired algorithms with parallel architectures. The book includes recent work by leading researchers in the field and offers a map with the main paths already explored and new ways towards the future. Parallel Architectures and Bioinspired Algorithms will be of value to both specialists in Bioinspired Algorithms, Parallel and Distributed Computing, as well as computer science students trying to understand the present and the future of Parallel Architectures and Bioinspired Algorithms.

Optimization methodology of dynamic data structures based on genetic algorithms for multimedia embedded systems

Modern multimedia application exhibit high resource utilization. In order to efficiently run this kind of applications in embedded systems, the dynamic memory subsystem needs to be optimized. A key role in this optimization is played by the dynamic data structures that reside in every real-life application. This paper presents a novel and automated way to optimize dynamic data structures. The search space is pruned using genetic algorithms that converge to the best multilayered data structure implementation for the targeted applications.

A methodology to automatically optimize dynamic memory managers applying grammatical evolution

Modern consumer devices must execute multimedia applications that exhibit high resource utilization. In order to efficiently execute these applications, the dynamic memory subsystem needs to be optimized. This complex task can be tackled in two complementary ways: optimizing the application source code or designing custom dynamic memory management mechanisms. Currently, the first approach has been well established, and several automatic methodologies have been proposed. Regarding the second approach, software engineers often write custom dynamic memory managers from scratch, which is a difficult and error-prone work. This paper presents a novel way to automatically generate custom dynamic memory managers optimizing both performance and memory usage of the target application. The design space is pruned using grammatical evolution converging to the best dynamic memory manager implementation for the target application. Our methodology achieves important improvements (62.55% and 30.62% better on average in performance and memory usage, respectively) when its results are compared to five different general-purpose dynamic memory managers.

Matching island topologies to problem structure in parallel evolutionary algorithms

In the context of Parallel Evolutionary Algorithms, it has been shown that different population structures induce different search performances. Nevertheless, no work has shown a clear cut evidence that there is a correlation between the solver’s population structure and the problem’s network structure. In this work, we verify this correlation performing a clear and systematic analysis of a large set of population structures (based on the well known β-graphs and NK-landscape problems. Furthermore, we go beyond our findings in these idealised experiments by analysing the performance of variable-topology EAs on a dynamic real-world problem, the Multi-Skills Call Centre.

Using a GPU-CPU architecture to speed up a GA-based real-time system for trading the stock market

The use of mechanical trading systems allows managing a huge amount of data related to the factors affecting investment performance (macroeconomic variables, company information, industrial indicators, market variables, etc.) while avoiding the psychological reactions of traders when they invest in financial markets. When trading is executed in an intra-daily frequency instead a daily frequency, mechanical trading systems needs to be supported by very powerful engines since the amount of data to deal with grow while the response time required to support trades gets shorter. Numerous studies document the use of genetic algorithms (GAs) as the engine driving mechanical trading systems. The empirical insights provided in this paper demonstrate that the combine use of GA together with a GPU-CPU architecture speeds up enormously the power and search capacity of the GA for this kind of financial applications. Moreover, the parallelization allows us to implement and test previous GA approximations. Regarding the investment results, we can report 870% of profit for the S&P 500 companies in a 10-year time period (1996–2006), when the average profit of the S&P 500 in the same period was 273%.