Figure-1 - uploaded by David Enke
Content may be subject to copyright.
Context in source publication
Citations
... Over the past two decades, this topic has attracted the attention of researchers in different fields, particularly artificial intelligence [5]. Stock prices are nonlinear with regard to historical data and other technical and macroeconomic indicators [6]. Many researchers often preferred to use time-series analyses which is utilized to estimate future events according to historical data before the capabilities of neural networks were discovered. ...
Predicting stock market (SM) trends is an issue of great interest among researchers, investors and traders since the successful prediction of SMs' direction may promise various benefits. Because of the fairly nonlinear nature of the historical data, accurate estimation of the SM direction is a rather challenging issue. The aim of this study is to present a novel machine learning (ML) model to forecast the movement of the Borsa Istanbul (BIST) 100 index. Modeling was performed by multilayer perceptron-genetic algorithms (MLP-GA) and multilayer perceptron-particle swarm optimization (MLP-PSO) in two scenarios considering Tanh (x) and the default Gaussian function as the output function. The historical financial time series data utilized in this research is from 1996 to 2020, consisting of nine technical indicators. Results are assessed using Root Mean Square Error (RMSE), Mean Absolute Percentage Error (MAPE) and correlation coefficient values to compare the accuracy and performance of the developed models. Based on the results, the involvement of the Tanh (x) as the output function, improved the accuracy of models compared with the default Gaussian function, significantly. MLP-PSO with population size 125, followed by MLP-GA with population size 50, provided higher accuracy for testing, reporting RMSE of 0.732583 and 0.733063, MAPE of 28.16%, 29.09% and correlation coefficient of 0.694 and 0.695, respectively. According to the results, using the hybrid ML method could successfully improve the prediction accuracy.
... Before the proliferation of artificial neural networks, most research on decision support systems was based on time series analysis and predicted stock price developments based on historical data. In the field of finance, models developed from time series theory such as ARIMA, ARCH, and GARCH are widely used (Vejendla, Enke 2013). The focus is currently on the use of artificial intelligence, and a number of such support schemes have already been developed (Ozturk et al. 2016;Chiang et al. 2016;Rubell, Jessy 2016;Petropoulos et al. 2017). ...
Successful trading in financial markets is not possible without a support system that manages the preparation of the data, prediction system, and risk management and evaluates the trading efficien-cy. Selected orthogonal data was used to predict exchange rates by applying recurrent neural network (RNN) software based on the open source framework Keras and the graphical processing unit (GPU) NVIDIA GTX1070 to accelerate RNN learning. The newly developed software on the GPU predicted ten high-low distributions in approximately 90 minutes. This paper compares different daily algorith-mic trading strategies based on four methods of portfolio creation: split equally, optimisation, orthogonality, and maximal expectations. Each investigated portfolio has opportunities and limita-tions dependent on market state and behaviour of investors, and the efficiencies of the trading sup-port systems for investors in foreign exchange market were tested in a demo FOREX market in real time and compared with similar results obtained for risk-free rates.
... Finansų srityje plačiai naudojami iš laiko eilučių teorijos susiformavę modeliai, tokie kaip ARIMA, ARCH, GARCH, ir kt. (Vejendla, Enke 2013). Dabar didžiausias mokslininkų dėmesys koncentruojasi į dirbtinio intelekto naudojimą, jau sukurta nemažai tokių investavimo modelių (Dymova et al. 2012). ...
Rapid development of financial markets resulted new challenges for both investors and investment issues. This increased demand for innovative, modern investment and portfolio management decisions adequate for market conditions. Financial market receives special attention, creating new models, includes financial risk management and investment decision support systems.Researchers recognize the need to deal with financial problems using models consistent with the reality and based on sophisticated quantitative analysis technique. Thus, role mathematical modeling in finance becomes important. This article deals with various investments decision-making models, which include forecasting, optimization, stochatic processes, artificial intelligence, etc., and become useful tools for investment decisions.
... They conclude that the prediction of the GARCH model is better, but the analysis relies strongly on the data set. Furthermore, Vejendla and Enke (2013b) applied the same methodology describe previously but in the options market. Specifically, they compare GARCH, FNN and RNN over several data sets and determined which is better for forecasting. ...
This paper builds on previous research and seeks to determine whether improvements can be achieved in the forecasting of oil price volatility by using a hybrid model and incorporating financial variables. The main conclusion is that the hybrid model increases the volatility forecasting precision by 30% over previous models as measured by a heteroscedasticity-adjusted mean squared error (HMSE) model. Key financial variables included in the model that improved the prediction are the Euro/Dollar and Yen/Dollar exchange rates, and the DJIA and FTSE stock market indexes.
The purpose of this research is to identify an artificial intelligence tool based on neural networks to predict the behavior of performance and risk of the set of financial assets based on actions that more accurately reflect the stock market movement of the Peruvian stock market. The research initially identified the most appropriate financial asset to estimate the performance and risk values of the 50% most liquid share portfolio in the Peruvian market in the 2010-2016 period. From the selected asset, the technique of artificial neural networks with a multilayer perceptron with regression configured with 3 layers (21,85,2) was used, using a logistic activation function with an LBFGS optimizer at a learning rate of 0.01 to establish the financial, operational, commercial or corporate governance patterns that can explain and / or predict the behavior of the same in the market. The research concludes that the cash generation capacity and the speed with which the assets are rotated, as well as the speed with which the Capex is disbursed, constitute the main factors that influence the determination of the best combinations of performance and risk for the group of financial assets considered as a subject of study, independent of the market sector in which it operates. The research found a neural network able to approximate the prediction of performance and risk with a 76.93% efficiency for the set of assets selected in the study period. The research provides a recognition of differentiated patterns in financial, operational, commercial and corporate governance aspects with a special emphasis on the managerial capacity that generates them whose influence is reflected in the performance of the set of assets studied through the technique of neural networks generating a predictive tool to estimate its stock market behavior.
