上证A股收益率分布特征的挖掘分析

基于上证A股的每日、周、月行情数据建立数据库系统,采用统计方法进行数据挖掘研究,挖掘研究不同时间范围、时间刻度和股票行业对股票收益率分布的影响. 从单只股票截面,对股票收益率密度分布进行正态性检验,分析其分布特征与股票流通市值、股票行业类别以及所研究的时间刻度（日、周、月）的关系. 从单位时间截面,对股票集合的收益率均值和波动率的相关统计特征进行分析,研究结果表明,股票集合的收益率均值的方差远大于单只股票截面的收益率均值的方差,这是因为股票之间的相关性远大于时间之间的相关性;另外,股票集合的波动率还具有长期记忆性的特征.     

基于高维状态空间方法构建金融市场网络模型

针对金融市场的核心变量--收益率和波动率，基于高维状态空间模型，利用EM和稀疏算法，分别建立了金融产品之间的收益率网络和波动率网络。前者刻画了金融产品收益之间的相互关系，后者刻画了金融产品风险之间的关系。相对于已有模型，上述模型可有效处理高维时间序列数据。对深圳、上海、香港和纽约市场的股票交易数据分析，找出了相应网络结构特征。以上市场的数据分析结果表明，相对于波动率网络，收益率网络具有更高的度数中心势，把这种现象归因于政策等因素对收益率的影响更为直接和简单，而对波动率的影响则是间接和复杂的。上述研究结果也为构建多变量波动率模型提供参考。     

随机金融市场环境下的最优再保险–投资策略

为了对冲保险风险,保险公司可以向再保险公司购买比例再保险;同时,为了保值增值,保险公司将其财富投资于金融市场.假设盈余过程由带漂移的布朗运动所驱动,利率满足仿射利率模型,股票波动率满足Heston随机波动率模型.应用随机最优控制和HJB方程方法得到了指数效用下最优再保险–投资策略的显式解.给出数值算例并分析了模型参数对最优再保险策略和最优投资策略的影响.研究结果表明:最优再保险策略不仅依赖于保险市场参数,而且依赖于金融市场参数;随机利率与随机波动率模型下的最优再保险–投资策略与利率动态密切相关,而与波动率动态无关;再保险行为对投资于股票的数量没有影响,而对投资于零息票债券的数量产生较大的影响.     

基于动态时间弯曲的股票时间序列联动性研究

对于股票联动性的研究,传统时间序列分析方法及目前数据挖 掘技术主要使用国内或者国外股票指数来研究市场、板块或行业之间的联动关系,并得到一 些较为宏观的结论,存在着缺少直接分析与挖掘个股数据之间的联动性的问题。鉴于此,本文提出一种基于动态时间弯曲的股票时间序列联动性研究方法。通过动态时间弯曲找出若干只形态相似的股票,并在此基础上获得相关的重要信息,再提出基于动态时间弯曲的k-means聚类方法实现股票聚类,进而得到具有相同波动趋势的股票簇。实验结果表 明,新方法能从大量股票中准确找到具有联动关系的个股,区分开不同波动趋势的股票簇,具有一定的优越性。     

互联网金融信息量与收益率波动关联研究

基于金融信息采集系统所采集的互联网金融信息流时间序列，对股市收益率进行了分析与检验，通过对比多个时间序列模型，最终构建了EGARCH—GEI）模型，将信息量与收益率两者联系起来。在此模型的基础上，完成了一个设想的实验与分析：在特定时间段向互联网中注入金融信息，金融市场波动情况是否会受到影响，影响程度有多大。通过编程实验得出定量分析结果：金融信息量增加时，金融市场的波动也随之增大，并当信息量增大数倍时，波动才可以摆脱随机因素，显著地受到信息量的影响。最后指出用互联网金融信息量分析股市波动的可改进之处如基于内容的分析。     

直觉模糊层次分析法下投行股票估值模型选择

基于直觉模糊集的模糊逼近理论,给出了将直觉模糊互补判断矩阵转换为模糊逼近矩阵的方法,提出了直觉模糊环境下的AHP方法(简记作IFAHP),并将其应用于投行股票估值模型选择问题,得到了股票估值模型中指标的优劣排序的权重值,是一种实用性较强的股票估值模型评价方法。     

基于NLP的股票选择策略的优化研究

由于股评、新闻对股票价格变化有巨大影响,为选出优质股票以提高投资的收益率,采用了自然语言处理NLP技术对股评数据和新闻数据进行分析,基于朴素贝叶斯模型建立了文本情感倾向分类模型,模型预测准确率达到84%,生成了股评因子。基于LDA主题模型对新闻文本进行话题建模,快速获取新闻文本主题,并引入困惑度寻找文档最优主题数,生成了新闻因子,将股评因子和新闻因子作为筛选股票的依据,从股评和新闻信息中获取对股市带来的影响因素,从而优化选股策略。对于股票基本面数据,采用决策树模型进行因子的重要性分析,选出重要性最高的前5个因子,模型预测准确率达到88%。通过决策树模型,可以更准确地确定哪些因子在影响股价变化方面发挥着关键作用,这种改进的方法能够提高选股策略的有效性和准确性。最终使用主成分分析（PCA）对数据进行降维处理,依据主成分数值的高低来进行股票选择。     

上证指数短期预测的数学模型

本文通过对上证指数K-线图、准备金率、CPI、宏观政策等进行分析,得到一些对上证指数有影响的因子,利用人工神经网络与粗糙集理论的优势,先采用粗糙集对数据进行处理,然后利用人工神经网络构造出上证指数短期预测模型,并以此模型进行分析,最后应用于股票市场,在股票的交易中取得了很好的效果。     

融合市场动态层次宏观信息的股票趋势预测

股票市场结构复杂、信息多样，股票趋势预测极具挑战性。但现有研究大都把每只股票当作一个独立的个体，或者使用图结构对股票市场中复杂的高阶关系进行建模，缺少对股票、行业、市场三者间相互影响的层次性和动态性考量。针对上述问题，提出一种动态宏观记忆网络（DMMN），并基于DMMN同时对多只股票进行价格趋势预测。该方法按照“股票-行业-市场”的层次对市场宏观环境信息进行建模，并捕获这些信息在时序上的长期依赖；然后将市场宏观环境信息与股票微观特征信息动态融合，在增强个股对市场整体情况的感知能力的同时间接捕获到股票、行业、市场三者间的相互依赖。在收集的CSI300数据集上得到的实验结果表明，相较于基于注意力长短期记忆（ALSTM）网络、添加了图卷积的LSTM网络（GCN-LSTM）、卷积神经网络（CNN）等模型的股票预测方法，基于DMMN的方法在F1分数、夏普比率上都取得了更好的效果，和表现最优的对比方法 ALSTM相比分别提升了4.87%和31.90%，这表明DMMN在具备较好预测性能的同时还具备更好的实用价值。     

基于背景先验与低秩恢复的显著性目标检测方法

显著性检测是指计算机通过算法自动识别出图像中的显著性目标，广泛应用于目标识别、图像检索与图像分类等领域。针对现有基于稀疏与低秩矩阵恢复的显著性检测模型中低秩转换矩阵的获取、前景稀疏矩阵的处理以及超像素块之间的关系，需对现有的稀疏与低秩矩阵恢复模型进行优化，使之更好地适用于图像的显著性检测。首先，根据背景的对比度和连通度原则获取图像低秩的背景字典，采用3种尺度分割图像的多个特征矩阵获得图像的前景稀疏矩阵；其次，通过计算邻居像素点之间的影响因子矩阵与置信度矩阵对显著图的结果进行结构约束，并且采用稀疏与低秩矩阵恢复模型对图像进行显著性检测；最后，利用K-means聚类算法的传播机制优化得到的显著图。在公开数据集上进行实验验证,结果证明本文方法能够准确有效地检测出显著性目标。     

结合公司财务报表数据的股票指数预测方法

股票市场参与者的所有市场活动综合影响着股票市场的变化,使股票市场的波动充满复杂性,也使得准确预测股票价格成为难题。在这些影响股市变化的活动中,财务披露是预测股票指数变化的一种吸引人的且具有潜在财务回报的手段。为了应对股票市场的复杂变化,提出一种结合公司披露的财务报表数据进行股票指数预测的方法。该方法首先对股票指数历史数据和公司财务报表数据进行预处理,主要是对公司财务报表数据生成的高维矩阵进行降维,然后用双通道的长短期记忆（LSTM）网络对归一化后的数据进行预测研究。在上证50指数和沪深300指数数据集上的实验结果表明,该方法的预测效果优于仅使用股票指数历史数据的预测效果。     

Another Look at Large-Cap Stock Return Comovement: A Semi-Markov-Switching Approach

The paper revisits the question of how stock return comovement varies with volatility and market returns. I propose an eigenvalue-based measure of comovement implied by the state-dependent correlation matrix estimated using a novel multivariate semi-Markov-switching approach. I show that compared to a basic Markov-switching structure the refined model performs very well in terms of capturing the well-known stylized facts of stock returns such as volatility clustering. With a focus on large-cap stocks, I illustrate the significance of comovement differential across states and document the different comovement patterns in different industries. Although the financial sector tends to conform to the conventional sentiment that comovement is highest when market is down and volatile, the conclusion should be tempered with caution when applied to other industries. In some cases, it is the high return state that registers the highest comovement.     

Predicting published news effect in the Brazilian stock market

The Efficient Market Hypothesis states that the value of an asset is given by all information available in the present moment. However, there is no possibility that a single financial analyst be aware of all published news which refers to a collection of stocks in the moment they are published. Thus, a computer system that applies text mining techniques and the GARCH model for predicting the volatility of financial assets may helps analysts and simple investors classifying automatically the news which cause the higher impact on stock market behavior. This work has the goal of creating a method for analyzing Portuguese written news’s content about companies that have their stocks negotiated in a stock market and trying to predict what kind of effect these news will cause in the Brazilian stock market behavior. Also, it was demonstrated in this study that it is possible to find out whether certain news may cause a considerable impact on prices of a negotiated stock.     

Realized volatility of index constituent stocks in Hong Kong

High-frequency financial data are useful for studying the statistical properties of asset returns at lower frequencies, and they have been widely used to study various market microstructure related issues. However, most studies to date have been concentrated on markets in developed economies such as the stock markets in US or UK. This article aims to investigate the statistical properties of stock return volatility in Hong Kong. Using the sample of constituent stocks of Hang Seng Index (HSI) and Hang Seng China Enterprises Index (HSCEI or “H-shares Index”), we found that the mean daily realized volatilities of HSCEI stocks to be significantly higher than their HSI counterpart, while the correlations between H-shares stay relatively lower than that of HSI stocks. A long-memory effect is also reported for the logarithmic standard deviations of all shares, with most of them showing slow decay over the series.     

The role of algorithmic trading systems on stock market efficiency

The rapid development of information technology has changed the dynamics of financial markets. The main purpose of this study is laid on examining the role of IT based stock trading on financial market efficiency. This research specifically focused on algorithmic trading. Algorithmic trading enables investors to trade stocks through a computer program without the need for human interventions. Based on an empirical analysis of the Korean stock market, this study discovered the positive impact of algorithmic trading on stock market efficiency at three-fold. First, the study results indicate that algorithmic trading contributes to the reduction in asymmetric volatility, which causes inefficiency of information in a stock market. Second, an algorithmic trading also increases the operation efficiency of a stock market. Arbitrage trading contributes on the equilibrium between the spot market and futures market as well as on the price discovery. Third, algorithmic trading provides liquidity for market participants contributing to friction free transactions. The research results indicate that stock exchanges based on electronic communications networks (ECNs) without human intervention could augment a financial market quality by increasing trading share volumes and market efficiency so that it can eventually contribute to the welfare of market investors.     

Robust technical trading strategies using GP for algorithmic portfolio selection

This paper presents a Robust Genetic Programming approach for discovering profitable trading rules which are used to manage a portfolio of stocks from the Spanish market. The investigated method is used to determine potential buy and sell conditions for stocks, aiming to yield robust solutions able to withstand extreme market conditions, while producing high returns at a minimal risk. One of the biggest challenges GP evolved solutions face is over-fitting. GP trading rules need to have similar performance when tested with new data in order to be deployed in a real situation. We explore a random sampling method (RSFGP) which instead of calculating the fitness over the whole dataset, calculates it on randomly selected segments. This method shows improved robustness and out-of-sample results compared to standard genetic programming (SGP) and a volatility adjusted fitness (VAFGP). Trading strategies (TS) are evolved using financial metrics like the volatility, CAPM alpha and beta, and the Sharpe ratio alongside other Technical Indicators (TI) to find the best investment strategy. These strategies are evaluated using 21 of the most liquid stocks of the Spanish market. The achieved results clearly outperform Buy&Hold, SGP and VAFGP. Additionally, the solutions obtained with the training data during the experiments clearly show during testing robustness to step market declines as seen during the European sovereign debt crisis experienced recently in Spain. In this paper the solutions learned were able to operate for prolonged periods, which demonstrated the validity and robustness of the rules learned, which are able to operate continuously and with minimal human intervention. To sum up, the developed method is able to evolve TSs suitable for all market conditions with promising results, which suggests great potential in the method generalization capabilities. The use of financial metrics alongside popular TI enables the system to increase the stock return while proving resilient through time. The RSFGP system is able to cope with different types of markets achieving a portfolio return of 31.81% for the testing period 2009–2013 in the Spanish market, having the IBEX35 index returned 2.67%.     

倾向性分析用于金融市场波动率的研究

互联网金融信息对于金融市场的影响在当代已经越来越不可忽视。面对海量的信息,其中大部分为非结构化的文本数据,该论文结合目前已有的文本倾向性算法,把信息的褒贬值作为外部变量加入到针对股价波动率建立的时间序列模型中去,对金融市场的股价波动率进行预测。实验揭示出金融市场波动率与互联网上金融新闻的相关性,并且提出了一种有效的股市预测方法。     

Application of Optimistic and Pessimistic OWA and DEA Methods in Stock Selection

One of the main objectives of fund managers in financial service industry is to select superior stocks by analyzing financial ratios. This paper proposes a novel methodology for stock selection by integrating optimistic and pessimistic ordered weighted averaging (OWA) and data envelopment analysis (DEA) methods. The paper first reveals the drawback of using the standard DEA models for stocks evaluation and then proposes a new method by using the OWA operator. Unlike the classical DEA, the proposed method in this paper does not involve the specification of inputs and outputs. The paper incorporates optimistic and pessimistic scenarios and generates interval OWA scores for all stocks. This is followed by using appropriate interval DEA models for selecting superior stocks. The proposed method in this paper is applied to identify high financial performance stocks in the Tehran stock market.