期刊文献+
共找到6篇文章
< 1 >
每页显示 20 50 100
基于神经网络的股票交易数据的预测研究 被引量:8
1
作者 师智斌 陈立潮 靳雁霞 《华北工学院学报》 2003年第6期412-415,共4页
 运用前馈神经网络预测时间序列的分析方法对股票数据进行了预测.通过对前馈神经网络时间序列数据预测网络模型的建立方法及预测方法讨论,基于BP网络对股票数据进行实际预测.预测精度明显高于传统方法,说明此种方法是可行的.BP网络可...  运用前馈神经网络预测时间序列的分析方法对股票数据进行了预测.通过对前馈神经网络时间序列数据预测网络模型的建立方法及预测方法讨论,基于BP网络对股票数据进行实际预测.预测精度明显高于传统方法,说明此种方法是可行的.BP网络可用于股票数据预测,其预测精度较高,但实际预测时,如何选择和确定一个合适的神经网络结构需进行反复实验. 展开更多
关键词 股票交易数据 神经网络 预测 时间序列分析
下载PDF
股票交易数据文件的抽取算法研究
2
作者 张志强 杨在义 +1 位作者 叶安胜 王伟钧 《成都大学学报(自然科学版)》 2014年第3期262-265,共4页
目前市场上有很多股票交易软件,这些软件会根据股票交易的实际情况定期产生股票交易信息数据,并将这些信息数据写入二进制格式的文件中,如DAY文件等.由于这些文件不是文本文件,无法直接使用常规的文件读写进行数据的抽取,而必须设计一... 目前市场上有很多股票交易软件,这些软件会根据股票交易的实际情况定期产生股票交易信息数据,并将这些信息数据写入二进制格式的文件中,如DAY文件等.由于这些文件不是文本文件,无法直接使用常规的文件读写进行数据的抽取,而必须设计一种数据抽取算法完成相应操作.对DAY文件进行了分析和研究,在此基础上设计了一种数据抽取算法,并利用JAVA语言实现了数据抽取算法程序,利用该程序完成了从DAY文件中抽取数据并写入数据库的实验.实验结果表明,该程序能够正确地从DAY文件中抽取数据,为后期的股票信息处理和数据挖掘提供了重要的基础. 展开更多
关键词 股票交易数据 DAY文件 数据抽取算法 数据挖掘
下载PDF
基于非对称QKD的股票交易数据库隐私查询协议
3
作者 许敏 石润华 罗振宇 《量子电子学报》 CSCD 北大核心 2017年第5期588-595,共8页
证券交易所的股票交易数据库中包含大量敏感信息,用户查询该数据库时保障账户及数据库的隐私十分重要.分析了非对称量子密钥分配(QKD)及其优良特性,提出了一种基于非对称QKD的不经意集合元素映射判定协议.该协议在查询数据库时保证了用... 证券交易所的股票交易数据库中包含大量敏感信息,用户查询该数据库时保障账户及数据库的隐私十分重要.分析了非对称量子密钥分配(QKD)及其优良特性,提出了一种基于非对称QKD的不经意集合元素映射判定协议.该协议在查询数据库时保证了用户和数据库的隐私。安全性分析结果表明,该协议能有效抵抗量子存储攻击、伪造量子态攻击和纠缠测量攻击,具有很高的信道损耗容忍度。 展开更多
关键词 量子光学 量子隐私查询 非对称量子密钥分配 不经意集合元素映射判定协议 股票交易数据
下载PDF
Crossover Phenomena in Detrended Fluctuation Analysis Used in Financial Markets
4
作者 MA Shi-Hao 《Communications in Theoretical Physics》 SCIE CAS CSCD 2009年第2期358-362,共5页
A systematic analysis of Shanghai and Japan stock indices for the period of Jan. 1984 to Dec. 2005 is performed. After stationarity is verified by ADF (Augmented Dickey-Fuller) test, the power spectrum of the data e... A systematic analysis of Shanghai and Japan stock indices for the period of Jan. 1984 to Dec. 2005 is performed. After stationarity is verified by ADF (Augmented Dickey-Fuller) test, the power spectrum of the data exhibits a power law decay as a whole characterized by 1/f^β processes with possible long range correlations. Subsequently, by using the method of detrended fluctuation analysis (DFA) of the general volatility in the stock markets, we find that the long-range correlations are occurred among the return series and the crossover phenomena exhibit in the results obviously.Further, Shanghai stock market shows long-range correlations in short time scale and shows short-range correlations in long time scale. Whereas, for Japan stock market, the data behaves oppositely absolutely. Last, we compare the varying of scale exponent in large volatility between two stock markets. All results obtained may indicate the possibility of characteristic of multifractal scaling behavior of the financial markets. 展开更多
关键词 financial market crossover phenomena detrended fluctuation analysis
下载PDF
Optimization of Portfolio of Stocks at ZSE through the Analysis of Historical Data
5
作者 Robert Fabac Dusan Mundar 《Computer Technology and Application》 2011年第12期1007-1014,共8页
Decision-making of investors at the stock exchange can be based on the fundamental indicators of stocks, on the technical indicators, or can exist as a combination of these two methods. The paper gives emphasis to the... Decision-making of investors at the stock exchange can be based on the fundamental indicators of stocks, on the technical indicators, or can exist as a combination of these two methods. The paper gives emphasis to the domain of technical analysis. In the broader sense the technical analysis enables the dynamics of the expected future values of the shares estimation. This can be performed on the basis of the data on historical trends of the revenues, profits and other indicators from the balance sheet, but also on the basis of historical data on changes in the values of the shares. Companies generally belong to the different sectors that have different presumptions of development resulting from the global market trends, technology and other characteristic. Processing of historical data values of the outstanding shares of the Zagreb Stock Exchange (ZSE) is origination of this research. Investors are interested to know the estimation of future returns for the stocks as well as the size of the risk associated with the expected returns. Research task in this paper is finding the optimal portfolio at the ZSE based on the concept of dominant portfolio by Markowitz approach. The portfolio is created by solving non-linear programming problem using the common software tools. The results of obtained optimal portfolios contain relevant conclusions about the specifics of the shares as well as the characteristics of the industrial sectors but also provide a further knowledge about diverse sectors treatment at the stock exchange in a multi-year period. 展开更多
关键词 Historical data Markowitz portfolio selection economic sectors Zagreb stock exchange expected yield risk.
下载PDF
Accounting variables and stock returns: Evidence from Istanbul stock exchange
6
作者 Beng Vuran Burcu Adiloglu 《Journal of Modern Accounting and Auditing》 2010年第8期38-46,共9页
The fundamental relationship between accounting variables and stock returns is a recurring theme in financial research. One of the major purposes of accounting is to help investors provide reliable, comparable and acc... The fundamental relationship between accounting variables and stock returns is a recurring theme in financial research. One of the major purposes of accounting is to help investors provide reliable, comparable and accurate information. If accounting data are informative about fundamental values and changes in values, they should be correlated with stock price changes. This study provides theory and evidence showing how accounting variables explain stock returns and examines the relationship between the stock returns and accounting variables of listed non financial companies in ISE-100 Indice for 2006-2008 period by using panel data methodology. Empirical analysis consists of 192 observations of 64 companies in years 2006-2008 to examine the effects of inventory, accounts receivable, gross margin, operating expense, return on assets, cash flow, leverage, liquidity, price/earnings, return on equity on stock returns. The results of the study confirm that the predicted roles of fundamental factors and stock returns are significantly related to gross margin, cash flow, leverage and equity variables. The model explains about 13.35 % of the variation of annual stock returns with the leverage variable with most of the significant power. 展开更多
关键词 stock returns accounting variables panel data methodology
下载PDF
上一页 1 下一页 到第
使用帮助 返回顶部