Forecasting purpose data analysis and methodology comparison of neural model perspective

Abstract

The goal of this paper is to compare and analyze the forecasting performance of twoartificial neural network models (i.e., MLP (multi-layer perceptron) and DNN (deep neural network)),and to conduct an experimental investigation by data flow, not economic flow. In this paper, weinvestigate beyond the scope of simple predictions, and conduct research based on the merits anddata of each model, so that we can predict and forecast the most efficient outcomes based on analyticalmethodology with fewer errors. In particular, we focus on identifying two models of neural networks(NN), a multi-layer perceptron (i.e., MLP) model and an excellent model between the neural network(i.e., DNN) model. At this time, predictability and accuracy were found to be superior in the DNNmodel, and in the MLP model, it was found to be highly correlated and accessible. The majorpurpose of this study is to analyze the performance of MLP and DNN through a practical approachbased on an artificial neural network stock forecasting method. Although we do not limit SandP(i.e., StandardandPoor's 500 index) to escape other regional exits in order to see the proper flow ofcapital, we first measured SandP data for 100 months (i.e., 407 weeks) and found out the followingfacts: First, the traditional artificial neural network (ANN) model, according to the specificity ofeach model and depending on the depth of the layer, shows the model of the prediction well andis sensitive to the index data; Second, comparing the two models, the DNN model showed betteraccuracy in terms of data accessibility and prediction accuracy than MLP, and the error rate wasalso shown in the weekly and monthly data; Third, the difference in the prediction accuracy of eachmodel is not statistically significant. However, these results are correlated with each other, andare considered robust because there are few error rates, thanks to the accessibility to various otherprediction accuracy measurement methodologies.