scholarly journals Artificial Neural Network Algorithms based Nonlinear Data Analysis for Forecasting in the Finance Sector

2018 ◽  
Vol 7 (4.10) ◽  
pp. 169
Author(s):  
Jitendra Kumar Jaiswal ◽  
Raja Das
Keyword(s):  
Neural Network ◽  
Artificial Intelligence ◽  
Stock Price ◽  
Historical Data ◽  
Wireless Systems ◽  
Regulatory Function ◽  
Demand And Supply ◽  
Network Algorithms ◽  
Political Environments ◽  
Moving Pattern

The involvement of big populace in the quantitative trading has been increased remarkably since the wired and wireless systems have become quite ubiquitous in the fields of finance and economics. Statistical, mathematical and technical analysis in parallel with machine learning and artificial intelligence are frequently being applied to perceive prices moving pattern and forecasting. However stock price do not follow any deterministic regulatory function, factor or circumstances rather than many considerations such as economy and finance, political environments, demand and supply, buying and selling tendency, trading and investment, etc. Historical data assist remarkably for prices forecasting as an important option for mathematicians and researchers. In this paper, we have followed backpropagation and radial basis function neural network for predicting future prices by modifying these techniques as per requirements. We have also performed a comparative analysis of the two ANN techniques for existing and our modified models.  

Construction of first-class university course based on artificial intelligence and neural network algorithm

2020 ◽  
pp. 1-12
Author(s):  
Yingli Duan
Keyword(s):  
Neural Network ◽  
Artificial Intelligence ◽  
Vocational Training ◽  
Network Algorithms ◽  
Teaching Efficiency ◽  
Neural Network Algorithm ◽  
Solid Foundation ◽  
University Level ◽  
University Course

Curriculum is the basis of vocational training, its development level and teaching efficiency determine the realization of vocational training objectives, as well as the quality and level of major vocational academic training. Therefore, the development of curriculum is an important issue. And affect the school’s teaching capacity building. The analysis of the latest developments in the main courses shows that there are some deviations or irrationalities in the curriculum in some colleges and universities, and the general problems of understanding the latest courses, such as lack of solid foundation in curriculum setting, unclear direction of objectives, unclear reform ideas, inadequate and systematic construction measures, lack of attention to the quality of education. This paper explains the rules for the establishment of first-level courses, clarifies the ideas and priorities of architecture, and explores strategies for building university-level courses using knowledge of artificial intelligence and neural network algorithms in order to gain experience from them.

Performance Analysis of Sequential and Parallel Neural Network Algorithm for Stock Price Forecasting

2011 ◽  
Vol 3 (1) ◽  
pp. 45-68 ◽  
Author(s):  
Rashedur M. Rahman ◽  
Ruppa K. Thulasiram ◽  
Parimala Thulasiraman
Keyword(s):  
Neural Network ◽  
Stock Price ◽  
Price Forecasting ◽  
Insurance Company ◽  
Memory Architecture ◽  
Backpropagation Algorithm ◽  
Network Algorithms ◽  
Training Time ◽  
Stock Price Forecasting ◽  
Neural Network Algorithm

The neural network is popular and used in many areas within the financial field, such as credit authorization screenings, regularities in security price movements, simulations of market behaviour, and so forth. In this research, the authors use a neural network technique for stock price forecasting of Great West Life, an insurance company based in Winnipeg, Canada. The Backpropagation algorithm is a popular algorithm to train a neural network. However, one drawback of traditional Backpropagation algorithm is that it takes a substantial amount of training time. To expedite the training process, the authors design and develop different parallel and multithreaded neural network algorithms. The authors implement parallel neural network algorithms on both shared memory architecture using OpenMP and distributed memory architecture using MPI and analyze the performance of those algorithms. They also compare the results with traditional auto-regression model to establish accuracy.

scholarly journals Modified Neural Network Algorithms for Predicting Trading Signals of Stock Market Indices

2009 ◽  
Vol 2009 ◽  
pp. 1-22 ◽  
Author(s):  
C. D. Tilakaratne ◽  
M. A. Mammadov ◽  
S. A. Morris
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Global Optimization ◽  
Stock Market ◽  
Historical Data ◽  
Error Function ◽  
Feedforward Neural Networks ◽  
Ordinary Least Squares ◽  
Global Optimization Algorithm ◽  
Network Algorithms

The aim of this paper is to present modified neural network algorithms to predict whether it is best to buy, hold, or sell shares (trading signals) of stock market indices. Most commonly used classification techniques are not successful in predicting trading signals when the distribution of the actual trading signals, among these three classes, is imbalanced. The modified network algorithms are based on the structure of feedforward neural networks and a modified Ordinary Least Squares (OLSs) error function. An adjustment relating to the contribution from the historical data used for training the networks and penalisation of incorrectly classified trading signals were accounted for, when modifying the OLS function. A global optimization algorithm was employed to train these networks. These algorithms were employed to predict the trading signals of the Australian All Ordinary Index. The algorithms with the modified error functions introduced by this study produced better predictions.

scholarly journals The artificial intelligence revolution: Achievements and prospects

2021 ◽  
Author(s):  
Vladimir Sergeevich Smolin
Keyword(s):  
Neural Network ◽  
Artificial Intelligence ◽  
Social Relations ◽  
Human Society ◽  
Network Algorithms ◽  
Further Development

The commercially successful application of neural network algorithms in artificial intelligence (AI) systems and devices after 2010 has significantly accelerated the process of achieving new successes in solving “intellectual problems. Further development of work on AI will affect not only the technological order, but also social relations in human society, and it is necessary to think about the possible consequences of such an influence right now.

scholarly journals Subjectness of digital communication in the context of technological evolution of the Internet: features and transformation scenarios

2021 ◽  
Author(s):  
S.V. Volodenkov ◽  
S.N. Fedorchenko
Keyword(s):  
Neural Network ◽  
Artificial Intelligence ◽  
Neural Networks ◽  
Current Practice ◽  
Digital Communication ◽  
Social Practices ◽  
Network Algorithms ◽  
Political Sphere ◽  
Communication Processes ◽  
Self Learning

The work aimed to study the peculiarities of the subjectness of the phenomenon of digital communication in the context of intensive digitalization of key spheres of life of modern society, as well as to identify the prospects and threats of introducing self-learning neural network algorithms and artificial intelligence technologies into communication processes unfolding in the social and political sphere. One of the study's key objectives was to identify scenarios of possible social changes in the context of society digitalization and the traditional social practices transformation in terms of the emergence of new digital subjects of mass public communication that form the pseudo structure of digital interaction between people. As a methodological optics, the work used the method of discourse analysis of scientific research devoted to the implementation and application of artificial intelligence technologies and self-learning neural networks in the processes of socio-political digitalization, as well as the method of critical analysis of current communication practice in the socio-political sphere. At the same time, when analyzing the current practice of digitalization in foreign countries, the case study method was used. In turn, to determine the scenarios for the transformation of traditional social space and social practices, the method of scenario techniques and scenario forecasting was applied. As a research result, it was concluded that the introduction of technological solutions based on artificial intelligence algorithms and self-learning neural networks into contemporary socio-political communication processes creates the potential for the problem of identifying the subjects of communicative acts in the socio-political sphere of the contemporary society life. Based on the results of the study, it is shown that artificial intelligence and self-learning neural network algorithms are increasingly being implemented in the current practice of contemporary digital communications, forming a high potential for information and communication impact on the mass consciousness of technological solutions that no longer require self-control from human operators. The work also concludes that in the current practice of social interactions in the digital space, a person faces a new phenomenon – interfaceization, within which self-communication stimulates the universalization and standardization of digital behavior, creating, disseminating, strengthening, and imposing special digital rituals. The article proves that digital rituals blur the line between digital avatars' activity based on artificial intelligence and the activity of real people, resulting in the potential for a person to lose their own subjectness in the digital universe.

scholarly journals Study on the prediction of stock price based on the associated network model of LSTM

2019 ◽  
Vol 11 (6) ◽  
pp. 1307-1317 ◽  
Author(s):  
Guangyu Ding ◽  
Liangxi Qin
Keyword(s):  
Neural Network ◽  
Artificial Intelligence ◽  
Stock Market ◽  
Statistical Methods ◽  
Network Model ◽  
Recurrent Neural Network ◽  
Neural Network Model ◽  
Stock Price ◽  
Artificial Intelligence Methods ◽  
Deep Recurrent Neural Network

AbstractStock market has received widespread attention from investors. It has always been a hot spot for investors and investment companies to grasp the change regularity of the stock market and predict its trend. Currently, there are many methods for stock price prediction. The prediction methods can be roughly divided into two categories: statistical methods and artificial intelligence methods. Statistical methods include logistic regression model, ARCH model, etc. Artificial intelligence methods include multi-layer perceptron, convolutional neural network, naive Bayes network, back propagation network, single-layer LSTM, support vector machine, recurrent neural network, etc. But these studies predict only one single value. In order to predict multiple values in one model, it need to design a model which can handle multiple inputs and produces multiple associated output values at the same time. For this purpose, it is proposed an associated deep recurrent neural network model with multiple inputs and multiple outputs based on long short-term memory network. The associated network model can predict the opening price, the lowest price and the highest price of a stock simultaneously. The associated network model was compared with LSTM network model and deep recurrent neural network model. The experiments show that the accuracy of the associated model is superior to the other two models in predicting multiple values at the same time, and its prediction accuracy is over 95%.

Performance Analysis of Sequential and Parallel Neural Network Algorithm for Stock Price Forecasting

2013 ◽  
pp. 97-121
Author(s):  
Rashedur M. Rahman ◽  
Ruppa K. Thulasiram ◽  
Parimala Thulasiraman
Keyword(s):  
Neural Network ◽  
Stock Price ◽  
Price Forecasting ◽  
Memory Architecture ◽  
Backpropagation Algorithm ◽  
Network Algorithms ◽  
Training Time ◽  
Stock Price Forecasting ◽  
The Neural Network ◽  
Neural Network Algorithm

The neural network is popular and used in many areas within the financial field, such as credit authorization screenings, regularities in security price movements, simulations of market behaviour, and so forth. In this research, the authors use a neural network technique for stock price forecasting of Great West Life, an insurance company based in Winnipeg, Canada. The Backpropagation algorithm is a popular algorithm to train a neural network. However, one drawback of traditional Backpropagation algorithm is that it takes a substantial amount of training time. To expedite the training process, the authors design and develop different parallel and multithreaded neural network algorithms. The authors implement parallel neural network algorithms on both shared memory architecture using OpenMP and distributed memory architecture using MPI and analyze the performance of those algorithms. They also compare the results with traditional auto-regression model to establish accuracy.

Sign in / Sign up

Export Citation Format

Share Document