Previsão do índice bovespa por meio de redes neurais artificiais: uma análise comparada aos métodos tradicionais de séries de tempo

Forecast is the basis for making strategic, tactical and operational business decisions. In financial economics, several techniques have been used to predict the behavior of assets over the past decades.Thus, there are several methods to assist in the task of time series forecasting, however, conventional modeling techniques such as statistical models and those based on theoretical mathematical models have produced unsatisfactory predictions, increasing the number of studies in more advanced methods of prediction. Among these, the Artificial Neural Networks (ANN) are a relatively new and promising method for predicting business that shows a technique that has caused much interest in the financial environment and has been used successfully in a wide variety of financial modeling systems applications, in many cases proving its superiority over the statistical models ARIMA-GARCH. In this context, this study aimed to examine whether the ANNs are a more appropriate method for predicting the behavior of Indices in Capital Markets than the traditional methods of time series analysis. For this purpose we developed an quantitative study, from financial economic indices, and developed two models of RNA-type feedfoward supervised learning, whose structures consisted of 20 data in the input layer, 90 neurons in one hidden layer and one given as the output layer (Ibovespa). These models used backpropagation, an input activation function based on the tangent sigmoid and a linear output function. Since the aim of analyzing the adherence of the Method of Artificial Neural Networks to carry out predictions of the Ibovespa, we chose to perform this analysis by comparing results between this and Time Series Predictive Model GARCH, developing a GARCH model (1.1).Once applied both methods (ANN and GARCH) we conducted the results' analysis by comparing the results of the forecast with the historical data and by studying the forecast errors by the MSE, RMSE, MAE, Standard Deviation, the Theil's U and forecasting encompassing tests. It was found that the models developed by means of ANNs had lower MSE, RMSE and MAE than the GARCH (1,1) model and Theil U test indicated that the three models have smaller errors than those of a naïve forecast. Although the ANN based on returns have lower precision indicator values than those of ANN based on prices, the forecast encompassing test rejected the hypothesis that this model is better than that, indicating that the ANN models have a similar level of accuracy . It was concluded that for the data series studied the ANN models show a more appropriate Ibovespa forecasting than the traditional models of time series, represented by the GARCH model

Índice de aromaticidade baseado na deslocalização, degenerescência e densidade (D3BIA) para acenos e moléculas homoaromáticas

The aromaticity index is an important tool for the investigation of aromatic molecules. This work consists on new applications of the aromaticity index developed by teacher Caio Lima Firme, so-called D3BIA (density, delocalization, degeneracy-based index of aromaticity). It was investigated its correlation with other well-known aromaticity indexes, such as HOMA (harmonic oscillator model of aromaticity), NICS (nucleus independent chemical shielding), PDI (para-delocalization index), magnetic susceptibility (), and energetic factor in the study of aromaticity of acenes and homoaromatic species based on bisnoradamantanyl cage. The density functional theory (DFT) was used for optimization calculations and for obtaining energetic factors associated with aromaticity and indexes HOMA and NICS. From quantum theory of atoms in molecules (QTAIM) it was obtained the indexes D3BIA, PDI and . For acenes, when the over-mentioned indexes were applied it was observed no correlation except for D3BIA and HOMA (R2=0.752). For bisnoradamantenyl dication and its derivatives, it was obtained a good correlation between D3BIA and NICS. Moreover, it was evaluated solely one of the factors used on D3BIA calculation, the delocalization index uniformity (DIU), so as to investigate its possible influence on stability of chemical species. Then, the DIU was compared with the formation Gibbs free energy of some pairs of carbocations, isomers or not, which each pair had small difference in point group symmetry and no difference among other well-known stability factors. The obtained results indicate that DIU is a new stability factor related to carbocations, that is, the more uniform the electron density delocalization, the more stable the is carbocation. The results of this work validate D3BIA and show its importance on the concept of aromaticity, indicating that it can be understood from degeneracy of atoms belonging the aromatic site, the electronic density in the aromatic site and the degree of uniformity of electron delocalization

Previsão do índice bovespa por meio de redes neurais artificiais: uma análise comparada aos métodos tradicionais de séries de tempo

Forecast is the basis for making strategic, tactical and operational business decisions. In financial economics, several techniques have been used to predict the behavior of assets over the past decades.Thus, there are several methods to assist in the task of time series forecasting, however, conventional modeling techniques such as statistical models and those based on theoretical mathematical models have produced unsatisfactory predictions, increasing the number of studies in more advanced methods of prediction. Among these, the Artificial Neural Networks (ANN) are a relatively new and promising method for predicting business that shows a technique that has caused much interest in the financial environment and has been used successfully in a wide variety of financial modeling systems applications, in many cases proving its superiority over the statistical models ARIMA-GARCH. In this context, this study aimed to examine whether the ANNs are a more appropriate method for predicting the behavior of Indices in Capital Markets than the traditional methods of time series analysis. For this purpose we developed an quantitative study, from financial economic indices, and developed two models of RNA-type feedfoward supervised learning, whose structures consisted of 20 data in the input layer, 90 neurons in one hidden layer and one given as the output layer (Ibovespa). These models used backpropagation, an input activation function based on the tangent sigmoid and a linear output function. Since the aim of analyzing the adherence of the Method of Artificial Neural Networks to carry out predictions of the Ibovespa, we chose to perform this analysis by comparing results between this and Time Series Predictive Model GARCH, developing a GARCH model (1.1).Once applied both methods (ANN and GARCH) we conducted the results' analysis by comparing the results of the forecast with the historical data and by studying the forecast errors by the MSE, RMSE, MAE, Standard Deviation, the Theil's U and forecasting encompassing tests. It was found that the models developed by means of ANNs had lower MSE, RMSE and MAE than the GARCH (1,1) model and Theil U test indicated that the three models have smaller errors than those of a naïve forecast. Although the ANN based on returns have lower precision indicator values than those of ANN based on prices, the forecast encompassing test rejected the hypothesis that this model is better than that, indicating that the ANN models have a similar level of accuracy . It was concluded that for the data series studied the ANN models show a more appropriate Ibovespa forecasting than the traditional models of time series, represented by the GARCH model