On Visualization Analysis of Stock Data

Big data technology is changing with each passing day,generating massive amounts of data every day.These data have large capacity,many types,fast growth,and valuable features.The same is true for the stock investment market.The growth of the amount of stock data generated every day is difficult to predict.The price trend in the stock market is uncertain,and the valuable information hidden in the stock data is difficult to detect.For example,the price trend of stocks,profit trends,how to make a reasonable speculation on the price trend of stocks and profit trends is a major problem that needs to be solved at this stage.This article uses the Python language to visually analyze,calculate,and predict each stock.Realize the integration and calculation of stock data to help people find out the valuable information hidden in stocks.The method proposed in this paper has been tested and proved to be feasible.It can reasonably extract,analyze and calculate the stock data,and predict the stock price trend to a certain extent.

DAViS:a unified solution for data collection, analyzation,and visualization in real‑time stock market prediction

The explosion of online information with the recent advent of digital technology in information processing,information storing,information sharing,natural language processing,and text mining techniques has enabled stock investors to uncover market movement and volatility from heterogeneous content.For example,a typical stock market investor reads the news,explores market sentiment,and analyzes technical details in order to make a sound decision prior to purchasing or selling a particular company’s stock.However,capturing a dynamic stock market trend is challenging owing to high fluctuation and the non-stationary nature of the stock market.Although existing studies have attempted to enhance stock prediction,few have provided a complete decision-support system for investors to retrieve real-time data from multiple sources and extract insightful information for sound decision-making.To address the above challenge,we propose a unified solution for data collection,analysis,and visualization in real-time stock market prediction to retrieve and process relevant financial data from news articles,social media,and company technical information.We aim to provide not only useful information for stock investors but also meaningful visualization that enables investors to effectively interpret storyline events affecting stock prices.Specifically,we utilize an ensemble stacking of diversified machine-learning-based estimators and innovative contextual feature engineering to predict the next day’s stock prices.Experiment results show that our proposed stock forecasting method outperforms a traditional baseline with an average mean absolute percentage error of 0.93.Our findings confirm that leveraging an ensemble scheme of machine learning methods with contextual information improves stock prediction performance.Finally,our study could be further extended to a wide variety of innovative financial applications that seek to incorporate external insight from contextual information such as large-scale online news articles and social media data.

Application of a Bayesian method to data-poor stock assessment by using Indian Ocean albacore (Thunnus alalunga) stock assessment as an example

It is widely recognized that assessments of the status of data-poor fish stocks are challenging and that Bayesian analysis is one of the methods which can be used to improve the reliability of stock assessments in data-poor situations through borrowing strength from prior information deduced from species with good-quality data or other known information. Because there is considerable uncertainty remaining in the stock assessment of albacore tuna（Thunnus alalunga） in the Indian Ocean due to the limited and low-quality data, we investigate the advantages of a Bayesian method in data-poor stock assessment by using Indian Ocean albacore stock assessment as an example. Eight Bayesian biomass dynamics models with different prior assumptions and catch data series were developed to assess the stock. The results show（1） the rationality of choice of catch data series and assumption of parameters could be enhanced by analyzing the posterior distribution of the parameters;（2） the reliability of the stock assessment could be improved by using demographic methods to construct a prior for the intrinsic rate of increase（r）. Because we can make use of more information to improve the rationality of parameter estimation and the reliability of the stock assessment compared with traditional statistical methods by incorporating any available knowledge into the informative priors and analyzing the posterior distribution based on Bayesian framework in data-poor situations, we suggest that the Bayesian method should be an alternative method to be applied in data-poor species stock assessment, such as Indian Ocean albacore.

Evaluation of removal of the size effect using data scaling and elliptic Fourier descriptors in otolith shape analysis, exemplified by the discrimination of two yellow croaker stocks along the Chinese coast

Removal of the length ef fect in otolith shape analysis for stock identification using length scaling is an important issue; however, few studies have attempted to investigate the ef fectiveness or weakness of this methodology in application. The aim of this study was to evaluate whether commonly used size scaling methods and normalized elliptic Fourier descriptors(NEFDs) could ef fectively remove the size ef fect of fish in stock discrimination. To achieve this goal, length groups from two known geographical stocks of yellow croaker, L arimichthys polyactis, along the Chinese coast(five groups from the Changjiang River estuary of the East China Sea and three groups from the Bohai Sea) were subjected to otolith shape analysis. The results indicated that the variation of otolith shape caused by intra-stock fish length might exceed that due to inter-stock geographical separation, even when otolith shape variables are standardized with length scaling methods. This variation could easily result in misleading stock discrimination through otolith shape analysis. Therefore, conclusions about fish stock structure should be carefully drawn from otolith shape analysis because the observed discrimination may primarily be due to length ef fects, rather than dif ferences among stocks. The application of multiple methods, such as otoliths shape analysis combined with elemental fingering, tagging or genetic analysis, is recommended for sock identification.

Using Data Mining with Time Series Data in Short-Term Stocks Prediction: A Literature Review

Data Mining (DM) methods are being increasingly used in prediction with time series data, in addition to traditional statistical approaches. This paper presents a literature review of the use of DM with time series data, focusing on shorttime stocks prediction. This is an area that has been attracting a great deal of attention from researchers in the field. The main contribution of this paper is to provide an outline of the use of DM with time series data, using mainly examples related with short-term stocks prediction. This is important to a better understanding of the field. Some of the main trends and open issues will also be introduced.

时序模型ARIMA在数据分析中的应用

时间序列是进行趋势分析的方法之一。随着大数据时代的到来,经济趋势、企业经营、市场预测和天气预测等常常需要进行预测和分析。本文对某知名化妆品公司2010年至2018年间的2122条股票数据,采用ARIMA模型进行趋势分析,预测未来的发展趋势。通过模型的拟合与效果考核,所得到的结果说明了应用ARIMA模型对股票进行趋势分析时,可以取得较好的预测效果。

投资者情绪是否会影响股票定价效率?——来自股票社区的文本证据

股票定价效率是衡量股票市场有效性的重要指标,更高的定价效率有利于促进资本市场资源的合理配置,更好地服务实体经济高质量发展。本文挖掘东方财富的投资者社区的文本发帖信息,利用机器学习方法分析文本情绪状态,构建投资者情绪指标并分析其对股票定价效率的影响。研究表明,投资者情绪与股票定价效率之间存在显著正相关关系,也即乐观的投资者情绪会带动股票定价效率的提升。这种影响效应是通过乐观情绪降低了信息不对称程度,进而提升了股价信息含量,并与定价效率的机制路径产生作用。进一步看,随着卖空限制的降低,股票定价效率对情绪的敏感程度会增大;良好的信息环境会降低情绪对股票定价效率的影响。研究结论为从个体投资者情绪视角透视我国股票市场运行效率以及网络媒体信息监管的必要性提供了证据。

序列稀疏自回归方法及其在美股做空数据分析上的应用

采用序列稀疏回归的思路来处理向量自回归模型,并设计适用于大规模时间序列数据分析的序列稀疏自回归方法。研究表明:从因子角度刻画向量自回归模型可以有效地将稀疏矩阵估计问题分解成稀疏奇异向量的估计问题,从而极大地提高了计算效率。以1523家美股上市公司1973年1月—2014年12月的做空数据为例,利用此方法探索公司之间的大规模做空关联网络。研究发现:此方法可以有效地恢复股票做空份额(即某一公司的空头股份数量)与股票收益率之间隐藏的关联网络,对于股票风险溢价研究具有一定启发意义。

存量地下空间更新价值评估体系研究

存量地下空间在补充地面空间资源、完善城市设施方面具有巨大的潜力,但在发展过程中凸显出功能集聚但空间匮乏、品质参差且风貌缺失、功能错位且动迁成本高、停车供给不足又缺乏联动等众多问题。因其自身特点复杂且受到的限制较多,如对于公众开放性不足,涉及多个发展目标,影响方案决策的因素较多,以及配套管理机制滞后等,加之缺乏高效的价值评估方法,导致在对其进行更新再利用时面临利用方式的单一和利用效率的不足。本文从全要素研究分析的角度出发,以现状质量、更新需求、成本投入和可获效益4个需求准则进行价值评估指标的选取,经过对多种评估方法的对比,选用特征价格法用于城市存量地下空间价值评估,以存量地下空间更新的微观形成机制估算潜在价值,采用定性分析与定量评价相结合的方式,在重要因素与更新利用之间建立回归模型,选择拟合度较好的半对数模型,并提出借助多元数据,提高评估的准确性,拟合存量地下空间的更新价值分布,以期为存量地下空间的高效、高品质更新利用提供参考。

结构化最大间隔双支持向量机在股票预测中的应用

股票价格受政策、宏观经济以及公司经营状况等多方因素的影响,且各因素之间存在较高的相关性,因此股票数据存在的高噪声、非平稳等特性使得股票预测充满困难。为了减少数据中存在的噪声对股价预测准确性的影响,基于马氏距离的类间隔可分性,提出了结构化最大间隔双支持向量机,其分别针对正类样本和负类样本,寻找两个非平行的超平面,使每一类样本离本类样本的欧式距离尽可能小,同时离异类超平面的马氏距离尽可能大。8组基准数据集的实验结果表明,该方法在含噪声数据的分类问题上具有稳定的准确率,从而提升了模型的预测性能和抗噪能力。同时将其应用到股票涨跌趋势预测中,通过对上证综指、上证A指、上证380指数以及中国平安等14只股票实证分析的结果表明,相较于其他对比模型,结构化最大间隔双支持向量机表现出了较好的预测结果,具有一定的实用价值。

新疆农田和荒漠生态系统土壤有机碳储量及其影响因素

基于中国生态系统研究网络(CERN)长期监测数据,选取新疆维吾尔自治区代表暖温带干旱区的绿洲农田生态系统(阿克苏站)、代表暖温带荒漠区(策勒站)以及温带荒漠区(阜康站)的绿洲农田和荒漠生态系统综合观测场、辅助观测场和农户调查点2005—2020年0—100 cm土层的土壤有机碳(SOC)储量数据,分析新疆农田和荒漠生态系统SOC储量的影响因素。研究结果表明,2005—2020年0—100 cm土层SOC总储量平均值为阿克苏站(5.17 kg/m^(2))>阜康站(4.20 kg/m^(2))>策勒站(2.96 kg/m^(2))。0—20 cm、20—40 cm、40—60 cm土层的SOC分别约占0—100 cm土层储量的27.3%—35.3%、23.1%—24.6%和15.8%—17.5%。在阿克苏站,施肥量最高、灌溉量最低的农户调查点SOC储量最高;而在策勒站和阜康站,农户调查点和辅助观测场的施肥和灌溉措施分别最有利于提高SOC储量。总体来看,土壤含水量、地上生物量与SOC储量呈正相关关系;年平均气温与0—40 cm土层的SOC储量呈负相关关系。在单一生态站的生态系统尺度,年平均气温与SOC储量相关性不显著;地上生物量与策勒站和阜康站的SOC储量呈正相关关系,但是与阿克苏站0—40 cm土层的SOC储量呈负相关关系;施纯钾量与策勒站0—60 cm土层的SOC储量呈正相关关系,但与阜康站40—100 cm土层的SOC储量呈负相关关系。总之,与自然状态下的荒漠和农田不施肥相比,灌溉和施肥的农田管理措施有利于增加干旱区SOC储量。不同生态站要根据自身区域特点制定合理的农田管理模式,以维持较高的SOC储量。

存量数据转换基础地理实体质量检查探讨

国家正加快新型基础测绘体系建设进程,针对存量数据转换基础地理实体数据的质量检验研究,文章首先在现行数字测绘成果质量检验标准基础上,提出基础地理实体成果质量检验内容的变化情况,并结合数据特征综合阐述了其具体质检内容,然后以福建省级某地区新型基础测绘地理实体试点成果质量检查为例,对所发现质量问题进行分析与总结,为后续规范化生产以及建立标准化、通用化的质量检查标准提供参考。

Stock Price Forecasting: An Echo State Network Approach

Forecasting stock prices using deep learning models suffers from pro-blems such as low accuracy,slow convergence,and complex network structures.This study developed an echo state network(ESN)model to mitigate such pro-blems.We compared our ESN with a long short-term memory(LSTM)network by forecasting the stock data of Kweichow Moutai,a leading enterprise in China’s liquor industry.By analyzing data for 120,240,and 300 days,we generated fore-cast data for the next 40,80,and 100 days,respectively,using both ESN and LSTM.In terms of accuracy,ESN had the unique advantage of capturing non-linear data.Mean absolute error(MAE)was used to present the accuracy results.The MAEs of the data forecast by ESN were 0.024,0.024,and 0.025,which were,respectively,0.065,0.007,and 0.009 less than those of LSTM.In terms of con-vergence,ESN has a reservoir state-space structure,which makes it perform faster than other models.Root-mean-square error(RMSE)was used to present the con-vergence time.In our experiment,the RMSEs of ESN were 0.22,0.27,and 0.26,which were,respectively,0.08,0.01,and 0.12 less than those of LSTM.In terms of network structure,ESN consists only of input,reservoir,and output spaces,making it a much simpler model than the others.The proposed ESN was found to be an effective model that,compared to others,converges faster,forecasts more accurately,and builds time-series analyses more easily.

基于存量数据研究基础地理实体生产技术

数字化时代,数据成为推动社会发展和科技创新的重要动力之一。在海量数据中,地理信息数据作为其中重要的一部分,承载着丰富的地球表面信息,具有巨大的潜力和价值。如何充分挖掘和利用存量数据成为当前科研和产业界亟待解决的问题之一。本文在国家新型基础测绘建设背景下,探讨立足存量数据的基础地理实体生产技术,旨在从地理信息数据的存储、处理和分析角度出发,深入研究如何基于现有的数据积累,发展更为高效的地理实体生产技术。

应用空间格网化法估算森林碳储量

为了探究空间格网化方法在森林碳储量估算中的应用,以塞罕坝机械林场的二类调查数据为基础,利用空间格网化方法提取林班中与碳储量估算相关的林龄、株数、郁闭度、蓄积量参数,通过BO-RF算法完成建模与估算,应用反距离加权插值方法完成空间插值统计,最终实现塞罕坝林场森林碳储量的整体性估算。结果表明:在不同格网尺度中,以3×3、5×5格网尺度的主要优势树种碳储量估算模型的精度表现较佳,华北落叶松(Larix gmelinii var.principis-rupprechtii(Mayr) Pilger)、白桦(Betula platyphylla Sukaczev)、樟子松(Pinus sylvestris var.mongholica Litv.)、蒙古栎(Quercus mongolica Fisch. ex Ledeb.)和云杉(Picea asperata Mast.)的决定系数(R2)均高于0.864,偏差、相对偏差、均方根误差、相对均方根误差也都表现较优;5×5格网尺度的主要优势树种的BO-RF的碳储量估算模型分别对主要优势树种的林龄、株数、郁闭度与格网中心碳储量参数的拟合效果明显,决定系数(R2)分别为0.910、0.887、0.956、0.864、0.913;与利用二类调查数据直接估算林班碳储量相比,空间格网化估算碳储量的精度达到99%。

宏观经济对股市波动的影响——基于GARCH-MIDAS-RTSRV模型的证据

本文对GARCH-MIDAS模型进行了拓展。首先,在估计GARCH-MIDAS模型的长期波动成分时,采用同时考虑噪声和跳跃影响的稳健双频已实现波动估计量RTSRV来代替传统的已实现波动估计量RV。其次,选取了经济变量并从中提取出主成分,从其水平值和波动率两个层面研究不同主成分对股市波动的影响。研究发现:本文构造的GARCH-MIDAS-RTSRV模型优于传统的GARCH-MIDAS模型,其预测精度更高并且可使投资者获得更高的经济价值;经济变量的主成分和已实现波动率均对股市的波动有显著的影响,并且相较于其水平值,波动率对股市波动的影响更为显著。

基于立木胸径生长率模型的乔木林碳汇潜力评估

树木生长产生巨大碳汇,对于缓解碳排放带来的全球变暖等环境问题具有重要意义。为准确评估森林碳汇,基于第6至第9次国家森林资源连续清查数据建立北京市13个主要树种(组)4种形式的立木胸径年生长率模型,预测树木胸径变化的未来趋势,从而为生物量转换因子连续函数法计算碳储量提供计算依据,最终获得2050年北京市乔木林碳储量和碳密度。结果表明:8个树种(组)胸径的年生长率模型R2都大于0.900,椴树的R^(2)最高为0.960;除柳树、水胡黄(水曲柳、胡桃楸、黄菠萝)外的11个树种(组)RMSE都小于0.5 cm;除杨树、其他硬阔类和榆树之外,Bias都小于1.0 cm。胸径预测精度验证中整体R^(2)较高,刺槐最高(0.951),其他硬阔类最低(0.766)。预测2050年北京市乔木林碳储量为42.71 Tg C,碳密度为43.35 Mg C·hm^(-2)。基于胸径年生长率模型的树木生长模拟方法可以有效的提高未来北京市乔木林碳汇潜力评估的整体精度,能够为制定温室气体减排政策、实现2060碳中和目标提供基础。