Forecasting and trading the EUR/USD exchange rate with Gene Expression and Psi Sigma Neural Networks

The motivation for this paper is to investigate the use of two promising classes of artificial intelligence models, the Psi Sigma Neural Network (PSI) and the Gene Expression algorithm (GEP), when applied to the task of forecasting and trading the EUR/USD exchange rate. This is done by benchmarking their results with a Multi-Layer Perceptron (MLP), a Recurrent Neural Network (RNN), a genetic programming algorithm (GP), an autoregressive moving average model (ARMA) plus a naïve strategy. We also examine if the introduction of a time-varying leverage strategy can improve the trading performance of our models.     

Evolving trading strategies using directional changes

The majority of forecasting methods use a physical time scale for studying price fluctuations of financial markets, making the flow of physical time discontinuous. Therefore, using a physical time scale may expose companies to risks, due to ignorance of some significant activities. In this paper, an alternative and original approach is explored to capture important activities in the market. The main idea is to use an event-based time scale based on a new way of summarising data, called Directional Changes. Combined with a genetic algorithm, the proposed approach aims to find a trading strategy that maximises profitability in foreign exchange markets. In order to evaluate its efficiency and robustness, we run rigorous experiments on 255 datasets from six different currency pairs, consisting of intra-day data from the foreign exchange spot market. The results from these experiments indicate that our proposed approach is able to generate new and profitable trading strategies, significantly outperforming other traditional types of trading strategies, such as technical analysis and buy and hold.     

Static and dynamic SABR stochastic volatility models: Calibration and option pricing using GPUs

For the calibration of the parameters in static and dynamic SABR stochastic volatility models, we propose the application of the GPU technology to the Simulated Annealing global optimization algorithm and to the Monte Carlo simulation. This calibration has been performed for EURO STOXX 50 index and EUR/USD exchange rate with an asymptotic formula for volatility or Monte Carlo simulation. Moreover, in the dynamic model we propose an original more general expression for the functional parameters, specially well suited for the EUR/USD exchange rate case. Numerical results illustrate the expected behavior of both SABR models and the accuracy of the calibration. In terms of computational time, when the asymptotic formula for volatility is used the speedup with respect to CPU computation is around 200 with one GPU. Furthermore, GPU technology allows the use of Monte Carlo simulation for calibration purposes, the computational time with CPU being prohibitive.     

Building Technical Trading System with Genetic Programming: A New Method to Test the Efficiency of Chinese Stock Markets

Testing whether technical trading rules can beat buy-and-hold strategy is a common approach to study the efficiency of stock markets. Noticing that the common approach of evaluating popular technical trading rules’ profitability would result in the biases of data snooping and incomplete test, we build a technical trading system with genetic programming to test the efficiency of Chinese stock markets. This system takes historical prices and volumes as inputs, randomly generates treelike structured technical trading rules composed of basic functions, and optimizes the rules using genetic programming according to the inputs. Using daily prices and volumes of Shenzhen Stock Exchange 100 index from January 2, 2004 to March 12, 2010, we find out that the optimal technical trading rules generated by our technical trading system have statistically significant out-of-sample excess returns compared with buy-and-hold strategy considering realistic transaction costs. Therefore, we conclude that Chinese stock markets have not achieved weak-form efficiency.     

Level estimation, classification and probability distribution architectures for trading the EUR/USD exchange rate

Dunis and Williams (Derivatives: use, trading and regulation 8(3):211–239, 2002; Applied quantitative methods for trading and investment. Wiley, Chichester, 2003) have shown the superiority of a Multi-layer perceptron network (MLP), outperforming its benchmark models such as a moving average convergence divergence technical model (MACD), an autoregressive moving average model (ARMA) and a logistic regression model (LOGIT) on a Euro/Dollar (EUR/USD) time series. The motivation for this paper is to investigate the use of different neural network architectures. This is done by benchmarking three different neural network designs representing a level estimator, a classification model and a probability distribution predictor. More specifically, we present the Mulit-layer perceptron network, the Softmax cross entropy model and the Gaussian mixture model and benchmark their respective performance on the Euro/Dollar (EUR/USD) time series as reported by Dunis and Williams. As it turns out, the Multi-layer perceptron does best when used without confirmation filters and leverage, while the Softmax cross entropy model and the Gaussian mixture model outperforms the Multi-layer perceptron when using more sophisticated trading strategies and leverage. This might be due to the ability of both models using probability distributions to identify successfully trades with a high Sharpe ratio.

Exchange rate forecasting: comparison of various architectures of neural networks

This paper evaluates the predictive accuracy of neural networks in forecasting exchange rate. The multi-layer perceptron (MLP) and radial basis function (RBF) networks with different architectures are used to forecast five exchange rate time series. The results of each prediction are evaluated and compared according to the networks and architectures used. It is found that neural networks can be effectively used in forecasting exchange rate and hence in designing trading strategies. RBF networks performed better than MLP networks in our simulation experiment. This experiment suggests that it is possible to extract information hidden in the exchange rate and predict it into future.     

Learning to trade via direct reinforcement

We present methods for optimizing portfolios, asset allocations, and trading systems based on direct reinforcement (DR). In this approach, investment decision-making is viewed as a stochastic control problem, and strategies are discovered directly. We present an adaptive algorithm called recurrent reinforcement learning (RRL) for discovering investment policies. The need to build forecasting models is eliminated, and better trading performance is obtained. The direct reinforcement approach differs from dynamic programming and reinforcement algorithms such as TD-learning and Q-learning, which attempt to estimate a value function for the control problem. We find that the RRL direct reinforcement framework enables a simpler problem representation, avoids Bellman's curse of dimensionality and offers compelling advantages in efficiency. We demonstrate how direct reinforcement can be used to optimize risk-adjusted investment returns (including the differential Sharpe ratio), while accounting for the effects of transaction costs. In extensive simulation work using real financial data, we find that our approach based on RRL produces better trading strategies than systems utilizing Q-learning (a value function method). Real-world applications include an intra-daily currency trader and a monthly asset allocation system for the S&P 500 Stock Index and T-Bills.     

A hybrid genetic-neural architecture for stock indexes forecasting

In this paper, a new approach for time series forecasting is presented. The forecasting activity results from the interaction of a population of experts, each integrating genetic and neural technologies. An expert of this kind embodies a genetic classifier designed to control the activation of a feedforward artificial neural network for performing a locally scoped forecasting activity. Genetic and neural components are supplied with different information: The former deal with inputs encoding information retrieved from technical analysis, whereas the latter process other relevant inputs, in particular past stock prices. To investigate the performance of the proposed approach in response to real data, a stock market forecasting system has been implemented and tested on two stock market indexes, allowing for account realistic trading commissions. The results pointed to the good forecasting capability of the approach, which repeatedly outperformed the “Buy and Hold” strategy.     

A stacked generalization system for automated FOREX portfolio trading

Multiple FOREX time series forecasting is a hot research topic in the literature of portfolio trading. To this end, a large variety of machine learning algorithms have been examined. However, it is now widely understood that, in real-world trading settings, no single machine learning model can consistently outperform the alternatives. In this work, we examine the efficacy and the feasibility of developing a stacked generalization system, intelligently combining the predictions of diverse machine learning models. Our approach establishes a novel inferential framework that comprises the following levels of data processing: (i) We model the dependence patterns between major currency pairs via a diverse set of commonly used machine learning algorithms, namely support vector machines (SVMs), random forests (RFs), Bayesian autoregressive trees (BART), dense-layer neural networks (NNs), and naïve Bayes (NB) classifiers. (ii) We generate implied signals of exchange rate fluctuation, based on the output of these models, as well as appropriate side information obtained by analyzing the correlations across currency pairs in our training datasets. (iii) We finally combine these implied signals into an aggregate predictive waveform, by leveraging majority voting, genetic algorithm optimization, and regression weighting techniques. We thoroughly test our framework in real-world trading scenarios; we show that our system leads to significantly better trading performance than the considered benchmarks. Thus, it represents an attractive solution for financial firms and corporations that perform foreign exchange portfolio management and daily trading. Our system can be used as an integrated part in international commercial trade activities or in a quantitative investing framework for algorithmic trading and carry-trade speculation.     

The use of data mining and neural networks for forecasting stock market returns

It has been widely accepted by many studies that non-linearity exists in the financial markets and that neural networks can be effectively used to uncover this relationship. Unfortunately, many of these studies fail to consider alternative forecasting techniques, the relevance of input variables, or the performance of the models when using different trading strategies. This paper introduces an information gain technique used in machine learning for data mining to evaluate the predictive relationships of numerous financial and economic variables. Neural network models for level estimation and classification are then examined for their ability to provide an effective forecast of future values. A cross-validation technique is also employed to improve the generalization ability of several models. The results show that the trading strategies guided by the classification models generate higher risk-adjusted profits than the buy-and-hold strategy, as well as those guided by the level-estimation based forecasts of the neural network and linear regression models.     

Exploring Trading Strategies and Their Effects in the Foreign Exchange Market

One of the most critical issues that developers face in developing automatic systems for electronic markets is that of endowing the agents with appropriate trading strategies. In this article, we examine the problem in the foreign exchange (FX) market, and we use an agent‐based market simulation to examine which trading strategies lead to market states in which the stylized facts (statistical properties) of the simulation match those of the FX market transactions data. Our goal is to explore the emergence of the stylized facts, when the simulated market is populated with agents using different strategies: a variation of the zero intelligence with a constraint strategy, the zero‐intelligence directional‐change event strategy, and a genetic programming‐based strategy. A series of experiments were conducted, and the results were compared with those of a high‐frequency FX transaction data set. Our results show that the zero‐intelligence directional‐change event agents best reproduce and explain the properties observed in the FX market transactions data. Our study suggests that the observed stylized facts could be the result of introducing a threshold that triggers the agents to respond to periodic patterns in the price time series. The results can be used to develop decision support systems for the FX market.     

Evolving Recurrent Neural Network using Cartesian Genetic Programming to Predict The Trend in Foreign Currency Exchange Rates

Forecasting the foreign exchange rate is an uphill task. Numerous methods have been used over the years to develop an efficient and reliable network for forecasting the foreign exchange rate. This study utilizes recurrent neural networks (RNNs) for forecasting the foreign currency exchange rates. Cartesian genetic programming (CGP) is used for evolving the artificial neural network (ANN) to produce the prediction model. RNNs that are evolved through CGP have shown great promise in time series forecasting. The proposed approach utilizes the trends present in the historical data for its training purpose. Thirteen different currencies along with the trade-weighted index (TWI) and special drawing rights (SDR) is used for the performance analysis of recurrent Cartesian genetic programming-based artificial neural networks (RCGPANN) in comparison with various other prediction models proposed to date. The experimental results show that RCGPANN is not only capable of obtaining an accurate but also a computationally efficient prediction model for the foreign currency exchange rates. The results demonstrated a prediction accuracy of 98.872 percent (using 6 neurons only) for a single-day prediction in advance and, on average, 92% for predicting a 1000 days’ exchange rate in advance based on ten days of data history. The results prove RCGPANN to be the ultimate choice for any time series data prediction, and its capabilities can be explored in a range of other fields.     

The Role of Heterogeneous Agents’ Past and Forward Time Horizons in Formulating Computational Models

The conditioning of strategies by market environment and the simultaneous emergence of market structure in the presence of evolving trading strategies are investigated with major international stock indexes. Models for price forecasting and trading strategies evolution are examined under different time horizons. The results demonstrate that trading strategies can become performative in thin markets, thereby shaping the price dynamics, which in turn feeds back into the strategy. The dominance in thin markets by some (short-memory) traders produces a better environment for learning profitable strategies with computational intelligence tools.The experiment conducted contradicts assertions that long-term fitness of traders is not a function of an accurate prediction, but only of an appropriate risk aversion through a stable saving rate. The stock traders’ economic performance is found to be best with a 1-year forward time horizon, and it deteriorates significantly for tests with horizons exceeding 2 years, identifying frequent structural breaks. To model the turmoil in an economic system with recurrent shocks, short-memory horizons are optimal, as older data is not informative about current or future states.     

Developing and assessing an intelligent forex rolling forecasting and trading decision support system for online e‐service

An effective foreign exchange (forex) trading decision is usually dependent on effective forex forecasting. In this study, an intelligent system framework integrating forex forecasting and trading decision is first proposed. Based on this framework, an advanced intelligent decision support system (DSS) incorporating a back‐propagation neural network (BPNN)‐based forex forecasting subsystem and Web‐based forex trading decision support subsystem is developed, which has been used to predict the directional change of daily forex rates and provide intelligent online decision support for financial institutions and individual investors. This article describes the forex forecasting and trading decision method, the system architecture, main functions, and operation of the developed DSS system. A comparative study is conducted between our developed system and others commonly used in order to assess the overall performance of the developed system. The assessment results show that our developed DSS outperforms some commonly used forex forecasting and trading decision systems and can provide intelligent e‐service for forex traders to make useful trading decisions in the forex market. © 2007 Wiley Periodicals, Inc. Int J Int Syst 22: 475–499, 2007.     

Genetic Programming Prediction of Stock Prices

Based on predictions of stock-pricesusing genetic programming (or GP), a possiblyprofitable trading strategy is proposed. A metricquantifying the probability that a specific timeseries is GP-predictable is presented first. It isused to show that stock prices are predictable. GPthen evolves regression models that produce reasonableone-day-ahead forecasts only. This limited ability ledto the development of a single day-trading strategy(SDTS) in which trading decisions are based onGP-forecasts of daily highest and lowest stock prices.SDTS executed for fifty consecutive trading days ofsix stocks yielded relatively high returns oninvestment.     

基于遗传编程的中国股票市场有效性检验

现代资本市场理论与金融投资实践之间存在着有效市场假说与技术分析之间的矛盾,使用流行的技术交易规则检验股票市场有效性可能导致两种结论偏差。遗传编程使用树形结构表示问题的候选解,可以很好地描述技术交易规则。利用遗传编程算法生成一种技术交易策略,并用其检验上证综合指数和5个沪深股市个股。回测结果表明,提出的方法相对于“买入-持有”策略能够获得超额收益,并且优于常用的流行技术指标,也说明我国股票市场并未达到弱式有效。     

Applying Dynamic Training‐Subset Selection Methods Using Genetic Programming for Forecasting Implied Volatility

Volatility is a key variable in option pricing, trading, and hedging strategies. The purpose of this article is to improve the accuracy of forecasting implied volatility using an extension of genetic programming (GP) by means of dynamic training‐subset selection methods. These methods manipulate the training data in order to improve the out‐of‐sample patterns fitting. When applied with the static subset selection method using a single training data sample, GP could generate forecasting models, which are not adapted to some out‐of‐sample fitness cases. In order to improve the predictive accuracy of generated GP patterns, dynamic subset selection methods are introduced to the GP algorithm allowing a regular change of the training sample during evolution. Four dynamic training‐subset selection methods are proposed based on random, sequential, or adaptive subset selection. The latest approach uses an adaptive subset weight measuring the sample difficulty according to the fitness cases' errors. Using real data from S&P500 index options, these techniques are compared with the static subset selection method. Based on mean squared error total and percentage of non‐fitted observations, results show that the dynamic approach improves the forecasting performance of the generated GP models, especially those obtained from the adaptive‐random training‐subset selection method applied to the whole set of training samples.     

Piecewise nonlinear goal-directed CPPI strategy

Traditional portfolio insurance (PI) strategy, such as constant proportion portfolio insurance (CPPI), only considers the floor constraint but not the goal aspect. This paper proposes a goal-directed (GD) strategy to express an investor’s goal-directed trading behavior and combines this floor-less GD strategy with the goal-less CPPI strategy to form a piecewise linear goal-directed CPPI (GDCPPI) strategy. The piecewise linear GDCPPI strategy shows that there is a wealth position M at the intersection of the GD and CPPI strategies. This M position guides investors to apply the CPPI strategy or the GD strategy depending on whether current wealth is less than or greater than M, respectively. In addition, we extend the piecewise linear GDCPPI strategy to a piecewise nonlinear GDCPPI strategy. This paper applies genetic algorithm (GA) technique to find better piecewise linear GDCPPI strategy parameters than those under the Brownian motion assumption. This paper also applies forest genetic programming (GP) technique to generate the piecewise nonlinear GDCPPI strategy. The statistical tests show that the GP strategy outperforms the GA strategy which in turn outperforms the Brownian strategy.     

System for foreign exchange trading using genetic algorithms and reinforcement learning

Foreign exchange trading has emerged recently as a significant activity in many countries. As with most forms of trading, the activity is influenced by many random parameters so that the creation of a system that effectively emulates the trading process will be very helpful. A major issue for traders in the deregulated Foreign Exchange Market is when to sell and when to buy a particular currency in order to maximize profit. This paper presents novel trading strategies based on the machine learning methods of genetic algorithms and reinforcement learning.     

Knowledge-intensive genetic discovery in foreign exchange markets

This paper considers the discovery of trading decision models from high-frequency foreign exchange (FX) markets data using genetic programming (GP). It presents a domain-related structuring of the representation and incorporation of semantic restrictions for GP-based searching of trading decision models. A defined symmetry property provides a basis for the semantics of FX trading models. The symmetry properties of basic indicator types useful in formulating trading models are defined, together with semantic restrictions governing their use in trading model specification. The semantics for trading model specification have been defined with respect to regular arithmetic, comparison and logical operators. This study also explores the use of two fitness criteria for optimization, showing more robust performance with a risk-adjusted measure of returns