GREY DEEP NEURAL NETWORK-BASED DATA ANALYSIS FOR FINANCIAL REPORTS IN TEXT MINING APPLICATIONS

Abstract

 The proposes the epic Gray Deep Neural Network Model (GDNNM), Multi-Layer Perception (MLP) Neural Network (NN) and computer integration, Model Identification Failure Prediction (MIFP) schemes. Data analysis for financial they can approximate both GDNNM and non-linear individual frame elements as a class. Based on the neural network model, unlike previous discrimination proof strategies, GDNNM subordinates frame elements to acquire an independent direct characteristic. This model has a good relationship with the project structure but is difficult to fit. The PGDM program is installed online financial data as a common sample criteria to get the remaining amount between the frame release and the GDNNM release. Early Diagnosis of Problem detection is important when building a structure, as it can save a considerable amount of space and time. With the progress of intelligent assembly, the lack of information-based search becomes an interesting issue. There are so many sources Text mining is a wide range of information testing used in semi-primary and non-basic information inquiries. This type of data is expected to cause problems in the financial information industry and problems in text mining for basic non-information testing. Besides, the checkpoints have been application research in the field of currency data, past research, auditing and control.