/pdf/the-impact-of-the-development-of-methods-for-financial-4e4ddkv6u8.pdf

The impact of the development of methods for financial stability analysis on the transformation of methods for stock market fundamental analysis


Purpose
This study aims to find the impact of the trade war between the USA and China on Asian economies. Apart from macroeconomic variables associated with trade, this study explicitly creates a trade war scenario and trade war participant dummies. Using the neural network multilayer perceptron, this study checks for the causal linkages between the predictors and target output for the panel of Asian economies and the USA.


Design/methodology/approach
A conceptual model of the after effects of trade war in a quadrant is developed. Variables related to trade and tariffs are included in the study for a panel of 19 Asian economies. The feedforward structure of neural network analysis is used to identify strong and weak predictors of trade war.


Findings
The hidden layers of the multilayer perceptron reveal the inconsistency in linkages for the predictors’ services exports, tariff measures, anti-dumping measures, trade war scenario dummy with gross domestic product. The findings suggest that to curtail the impact of the trade war on Asian economies, predictors with neural evidence must be paid due weightage in policy determination and trade agreements.


Originality/value
The study applies a novel and little explored AI/ML technique of Neural Network analysis with training of 70% observations. The paper will provide opportunity for other researchers to explore techniques of AI/ML in trade studies.


Impact of US-China trade war on Asian economies: neural network multilayer perceptron approach

The article discusses the use of artificial neural networks in financial markets, due to the fact that this direction is very promising. Neural networks are well suited for tasks in which there are a large number of influencing factors, both known and unknown. The existing methods of neural networks training are considered, their pros and cons are noted. The use of neural networks in forecasting financial time series in real time is faced with the problem of the duration of the learning process of the neural network and the selection of significant inputs of the neural network. This problem can be solved by using the high-speed method of teaching the perceptron. The high-speed method of training allows for a much smaller number of iterations to train a multilayer perceptron on a given set of examples compared to the method of back propagation of the error. The high-speed method of training a multilayer perceptron allows us to assess whether it is possible to reach a given learning error of the neural network or not. This method of training is proposed to be used as an evaluation in the case of critical tasks before applying the method of back propagation of the error, in the case of non-critical tasks, the results of the neural network trained by this method can be used directly.

https://brain.edusoft.ro/index.php/brain/article/download/943/1123

Dmitry N. Karlov

Papers

Application of High-Speed Algorithms for Training Neural Networks for Forecasting Financial Markets