Research behind Evolize

Research of the algorithm used in Evolize dates back to 2010. Here we present you with abstracts of each scientific article written about it.


High-low Strategy of Portfolio Composition using Evolino RNN Ensembles
The originally configured 176 Evolino recurrent neural networks (RNN) connected to one ensemble and trained in parallel is an artificial intelligence solution, which allows the successful application of this tool for forecasting financial markets. Predictions made by this tool twice a day with different historical data give two distributions of expected values, which reflect future dynamic exchange rates. Constructing the portfolio, according to shape, parameters of distribution and the current value of the exchange rate allows the optimization of trading in daily exchange-rate fluctuations. Comparison of a high-low portfolio with a close-to-close portfolio shows the efficiency of the new forecasting tool and new proposed trading strategy. Read the full article here


Prediction Capabilities of Evolino RNN Ensembles
Modern portfolio theory of investment-based financial market forecasting use probability distributions. This investigation used an ensemble of genetic algorithm based recurrent neural networks (RNN), which allows to obtain multi-modal distribution for predictions. Comparison of the two different models—scatted points based prediction and distributions based prediction—opens new opportunities to create profitable investment tool, which was tested in real time demo market. Dependence of forecasting accuracy on the number of Evolino recurrent neural networks ensemble was obtained for five forecasting points ahead. This study allows to optimize the cluster based computational time and resources required for sufficiently accurate prediction. Read the full article here


Investment support system using the EVOLINO recurrent neural network ensemble
The chaotic and largely unpredictable conditions that prevail in exchange markets are of considerable interest to speculators because of the potential for profit. The creation and development of a support system using artificial intelligence algorithms provides new opportunities for investors in financial markets. Therefore, the authors have developed a support system that processes historical data, makes predictions using an ensemble of EVOLINO recurrent neural networks, assesses these predictions using a composition of high-low distributions, selects an orthogonal investment portfolio, and verifies the outcome on the real market. The support system requires multi-core hardware resources to allow for timely data processing using anMPI library-based parallel computation approach. A comparison of daily and weekly predictions reveals that weekly forecasts are less accurate than daily predictions, but are still accurate enough to trade successfully on the currency markets. Information obtained from the support system gives investors an advantage over uninformed market players in making investment decisions. Read the full article here

The use of investment portfolio orthogonality to secure investment against bank interventions
Addressing risk from price fluctuations is usual for traders in finance markets, but interventions from banks are extreme and unpredictable. The principle of portfolio orthogonality was investigated as one way of securing investment in the face of interventions in financial markets. The research tested two forecasting tools: the adequate portfolio model and an ensemble of Evolino recurrent neural networks. The paper draws on different
investment portfolios in global capital and foreign exchange markets to illustrate the potential of investment portfolio orthogonality. Banking interventions are relatively rare phenomena which have an impact on the security of investment. The investment portfolio orthogonality principle can be used as a tool to protect against unexpected losses. Read the full article here


Selection of orthogonal investment portfolio using Evolino RNN trading model
Investing in financial market require the reliable predicting of expecting returns, assessment of risk and reliability. Principle of portfolio orthogonality was using to reduce the risk of the investment. An artificial intelligence system may reveal new opportunities for using this principle. Prediction of recurrent neural networks ensemble is stochastically informative distribution, which is helpful for portfolio selection. Shape and parameters of distribution influence decision making in currency market. Assessment of portfolio riskiness, finding most orthogonal elements of portfolio, influence better results for trading in real market. Read the full article here

Comparison of exchange market predictions using extremal data
High and low data otherwise then close and open data are not adventitious on time series curve. Its are extremes and very interesting for traders. Our model based on Evolino RNN ensemble give two distributions based on high and low data. Composition and parameters of these distributions determine the decision of trading. In this paper portfolio constructed by this new method of prediction is compared with portfolio based on Bollinger bands. Comparison well known in technical analysis tools with our support prediction system based on artificial intelligence confirmed the new ability to predict high and low values. Read the full article here

Investigation of exchange market prediction model based on high-low daily data
The model of Evolino recurrent neural networks (RNN) based on ensemble for prediction of daily extremes of financial market is investigated. The prediction distributions of each high and lows of daily values of exchange rates were obtained. Obtained distributions show an accuracy of predictions, re-flects true features of direct time interval unpredictability of chaotic process. Changing of time series data from close to extremes allows to create new strategy of investment built on distributions basic parameters: standard deviation, skewness, kurtosis. Extension of close distribution to the pair of high-low distribution is opening extra capabilities of optimal portfolio creation and risk management for investors. Read the full article here


Financial market prediction system with Evolino neural network and Delphi method
Use of artificial intelligence systems in forecasting financial markets requires a reliable and simple model that would ensure profitable growth. The model presented in the paper combines Evolino recurrent neural networks with orthogonal data inputs and the Delphi expert evaluation method for its investment portfolio decision making process. A statistical study demonstrates the reliability of the model and describes its accuracy. Capabilities of the model are demonstrated using a trading simulation. Read the full article here

Investigation of prediction capabilities using RNN ensembles
Modern portfolio theory of investment-based financial market forecasting use probability distributions. This investigation used a neural network architecture, which allows to obtain distribution for predictions. Com-parison of the two different models -points based prediction and distributions based prediction -opens new investment opportunities. Dependence of forecasting accuracy on the number of EVOLINO recurrent neural networks (RNN) ensemble was obtained for five forecasting points ahead. This study allows to optimize the computational time and resources required for sufficiently accurate prediction. Read the full article here


Influence of data orthogonality: on the accuracy and stability of financial market predictions
Input selection is always important for adapting artificial intelligence systems for forecasting. Recurrent neural networks could predict using the historical data of financial markets but the predictions are very unstable. The goal of our paper is to study the influence of two historical data inputs on accuracy and stability of recurrent neural network forecasting. It is proposed to use orthogonal recurrent neural network inputs for the prediction of financial market exchange rates. Statistical comparison of the predicted results for different degrees of orthogonality of the data inputs shows much tighter distribution of the predicted results, when the more orthogonal input data are used. This proposed data input concept was tested using evolution of recurrent systems with linear Outputs recurrent neural network with historical input data of currency exchange rates. Read the full article here

Application of neural network for forecasting of exchange rates and forex trading
Expert methods, which widely applied for human decision making, were employed for neural networks. It was developed an exchange rates prediction and trading algorithm with using of experts in-formation processing techniques -Delphi method and prediction compatibility. Proposed algorithm lim-ited to eight experts. Each of experts represented recurrent neural network, Evolino-based Long Short-Term Memory (LSTM) by using of genetic learning algorithm, EVOlution of recurrent systems with LINear Outputs (EVOLINO). Statistical investigation of offered algorithm shows the significantly in-crease of the reliability of prediction. Developed algorithm was applied for trading of historical forex ex-change rates. Obtained test trading results were presented. Read the full article here


Investigation of financial market prediction by recurrent neural network. Innovative Technologies for Science
Recurrent neural networks as fundamentally different neural network from feed-forward architectures was investigated for modelling of non linear behaviour of financial markets. Recurrent neural networks could be configured with the correct choice of parameters such as the number of neurons, the number of epochs, the amount of data and their relationship with the training data for predictions of financial markets. By exploring of learning and forecasting of the recurrent neural networks is observed the same effect: better learning, which often is described by the root mean square error does not guarantee a better prediction. There are such a recurrent neural networks settings where the best results of non linear time series forecasting could be obtained. New method of orthogonal input data was proposed, which improve process of EVOLINO RNN learning and forecasting. Read the full article here


Modelling of the history and predictions of financial market time series using Evolino
Artificial neural networks and their systems are already capable of learning, to summarize, filter, and classify information. The increasing amount of authors are trying to teach them to approximate and predict chaotic, fractal processes. One of the greatest challenges of today’s financial researches is forecasting of the commodities, stocks and currency markets. Variations in prices lead to economic indicators as result of investment process of investors and short time market players. Present article investigates recurrent neural network systems as mathematical tool for objective forecasts of fractal behaviour of financial markets by Evolino recurrent neural network learning algorithm. Read the full article here