Optimal Neural Network Architecture for Stock Market Forecasting

2013 ◽  
Author(s):  
G. Khirbat ◽  
R. Gupta ◽  
S. Singh
Keyword(s):  
Neural Network ◽  
Stock Market ◽  
Network Architecture ◽  
Neural Network Architecture ◽  
Stock Market Forecasting

SCORING MODELING BASED ON NEURAL NETWORKS FOR DETERMINING A BANK BORROWER'S RATING

2020 ◽  
Vol 2020 (10) ◽  
pp. 54-62
Author(s):  
Oleksii VASYLIEV ◽  
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Network Architecture ◽  
Statistical Data ◽  
Activation Function ◽  
Decision Making Process ◽  
Neural Network Architecture ◽  
Acceptable Accuracy ◽  
The Neural Network ◽  
Sigmoid Activation Function

The problem of applying neural networks to calculate ratings used in banking in the decision-making process on granting or not granting loans to borrowers is considered. The task is to determine the rating function of the borrower based on a set of statistical data on the effectiveness of loans provided by the bank. When constructing a regression model to calculate the rating function, it is necessary to know its general form. If so, the task is to calculate the parameters that are included in the expression for the rating function. In contrast to this approach, in the case of using neural networks, there is no need to specify the general form for the rating function. Instead, certain neural network architecture is chosen and parameters are calculated for it on the basis of statistical data. Importantly, the same neural network architecture can be used to process different sets of statistical data. The disadvantages of using neural networks include the need to calculate a large number of parameters. There is also no universal algorithm that would determine the optimal neural network architecture. As an example of the use of neural networks to determine the borrower's rating, a model system is considered, in which the borrower's rating is determined by a known non-analytical rating function. A neural network with two inner layers, which contain, respectively, three and two neurons and have a sigmoid activation function, is used for modeling. It is shown that the use of the neural network allows restoring the borrower's rating function with quite acceptable accuracy.

Maximal Overlap Discrete Wavelet Transform, Graph Theory And Backpropagation Neural Network In Stock Market Forecasting

2018 ◽  
Vol 5 (1) ◽  
pp. 41-46
Author(s):  
Rosalina Rosalina ◽  
Hendra Jayanto
Keyword(s):  
Neural Network ◽  
Graph Theory ◽  
Wavelet Transform ◽  
Stock Market ◽  
Discrete Wavelet Transform ◽  
Stock Price ◽  
Moving Average ◽  
Discrete Wavelet ◽  
Stock Market Forecasting ◽  
Artificial Neural

The aim of this paper is to get high accuracy of stock market forecasting in order to produce signals that will affect the decision making in the trading itself. Several experiments by using different methodologies have been performed to answer the stock market forecasting issues. A traditional linear model, like autoregressive integrated moving average (ARIMA) has been used, but the result is not satisfactory because it is not suitable for model financial series. Yet experts are likely observed another approach by using artificial neural networks. Artificial neural network (ANN) are found to be more effective in realizing the input-output mapping and could estimate any continuous function which given an arbitrarily desired accuracy. In details, in this paper will use maximal overlap discrete wavelet transform (MODWT) and graph theory to distinguish and determine between low and high frequencies, which in this case acted as fundamental and technical prediction of stock market trading. After processed dataset is formed, then we will advance to the next level of the training process to generate the final result that is the buy or sell signals given from information whether the stock price will go up or down.

scholarly journals Learning Subject-Generalized Topographical EEG Embeddings Using Deep Variational Autoencoders and Domain-Adversarial Regularization

Sensors ◽  
2021 ◽  
Vol 21 (5) ◽  
pp. 1792
Author(s):  
Juan Hagad ◽  
Tsukasa Kimura ◽  
Ken-ichi Fukui ◽  
Masayuki Numao
Keyword(s):  
Neural Network ◽  
Network Architecture ◽  
Emotion Classification ◽  
Limited Data ◽  
Neural Network Architecture ◽  
Building Models ◽  
The Subject ◽  
Data Constraints ◽  
Input Level ◽  
Normally Distributed

Two of the biggest challenges in building models for detecting emotions from electroencephalography (EEG) devices are the relatively small amount of labeled samples and the strong variability of signal feature distributions between different subjects. In this study, we propose a context-generalized model that tackles the data constraints and subject variability simultaneously using a deep neural network architecture optimized for normally distributed subject-independent feature embeddings. Variational autoencoders (VAEs) at the input level allow the lower feature layers of the model to be trained on both labeled and unlabeled samples, maximizing the use of the limited data resources. Meanwhile, variational regularization encourages the model to learn Gaussian-distributed feature embeddings, resulting in robustness to small dataset imbalances. Subject-adversarial regularization applied to the bi-lateral features further enforces subject-independence on the final feature embedding used for emotion classification. The results from subject-independent performance experiments on the SEED and DEAP EEG-emotion datasets show that our model generalizes better across subjects than other state-of-the-art feature embeddings when paired with deep learning classifiers. Furthermore, qualitative analysis of the embedding space reveals that our proposed subject-invariant bi-lateral variational domain adversarial neural network (BiVDANN) architecture may improve the subject-independent performance by discovering normally distributed features.

Sign in / Sign up

Export Citation Format

Share Document