英语论文网

日本早稻田大学硕士论文范文硕士范文题目：基于结构学习以及自组织映射对中国股票的预测
论文语种：英文
您的研究方向：金融工学
是否有数据处理要求：否
您的国家：日本
您的学校背景：早稻田大学
要求字数：1万2千字
论文用途：硕士毕业论文 Master Degree
是否需要盲审（博士或硕士生有这个需要）：否
补充要求和说明： 

硕士范文：基于结构学习以及自组织映射对中国股票的预测

Abstract
Self-organizing mapping (SOM) neural network is the main artificial neural network model used to cluster. In the basis of the SOM network, he network neighborhood function was improved, and was applied to analyze the price of stock of central enterprises in China. The results was obtained and used to the further forecasting of stock price. Artificial https://www.51lunwen.org/jrfx/  Neural network is a nonlinear dynamic system, which can attain the reflection of nonlinear relations among variables within any precision, possessing the ability of solving nonlinear problems, therefore also meeting requirements of economic forecasting. Taking advantages of the nonlinear and dynamic characteristics, by adjusting the number of hidden layers, enough precision of forecasting was obtained. The improved BP algorithm was contrasted with the traditional. From the forecasting results, it showed this method is possible and useful in stock price forecasting and analysis.

 
Table of Content
Abstract 1
Table of Content 2
1 Introduction 2
1.1 Background 2
1.2 Stocks Classification 5
1.3 Stock Price Forecasting Model 6
1.4 Using BP of NN for Stock Price Prediction 6
2 Neural network and structural learning 8
2.1 Neural network 8
2.2 Back Propagation Neural Network 11
2.2.1 The structure of BP neural network 11
2.2.2 The learning formula of Back Propagation (BP) Algorithm 13
2.3 Structural Learning 14
2.3.1 Economy control and central enterprises in China 17
2.3.2 Generating Method 22
2.3.3 Eliminating Method 23
2.3.4 Elimination of Ineffective Units by Goodness Factor 23
3 Self-Organizing-Map-Based Neural Network Method 25
3.1 Self-Organizing Map 25
3.2 The improved SOM learning algorithm 31
3.3 Application of Structural Learning to Stock Forecasting 36
4 Conclusions 39
 
1 Introduction
1.1 Background
In today's economic life, the stock market plays a very important position supply and demand determine the behavior of the market, but supply and demand but by the promise the interaction of multiple factors including international environment, national policies, economic situation, social issues, and investor psychology, and many other factors, abnormal relationship complex. Therefore, to accurately describe the behavior of the stock market is very difficult.
As a rational investor, would like to reduce unnecessary risks that are in certain circumstances the risk as much as possible to obtain high-yield return newspaper; or on the basis of certain expected return to minimize risk. Therefore analysis, forecast the behavior of the stock market in terms of investors becomes extremely important. This naturally raises the question of whether the future behavior of stock market data used to predict the past.

4 Conclusions
This research showed that the operation that the stock forecasting by the neural network that used the structural learning was possible. SOM was firstly used to cluster the 30 stocks. Then the China Union was used as the research object. The neighboring stocks were selecte本论文由英语论文网提供整理，提供论文代写，英语论文代写，代写论文，代写英语论文，代写留学生论文，代写英文论文，留学生论文代写相关核心关键词搜索。