基于改进SVC的金融时间序列预测简

针对金融时间序列高噪声,强非线性和不确定性等特点,对传统加权支持向量机（WSVM）进行了改进.提出了基于改进加权支持向量机和再加权支持向量机（RWSVM）的金融时间序列预测方法.研究表明,与传统加权支持向量机相比,改进的加权支持向量机有效地提高了金融时间序列预测的精度。     

金融时间序列数据预测方法探析

本文提出了一种改进的金融时间序列数据预测方法,该方法首先对采集到的数据进行预处理,然后利用决策树来对金融时间序列进行特征抽取,并建立基于支持向量机的时间序列预测模型,最后对时间序列数据进行预测并输出预测结果。仿真结果表明,本文提出的方法可以有效地降低预测模型复杂度,同时提高预测能力和泛化性能。     

基于支持向量回归的股市波动性预测

详细介绍利用支持向量回归方法进行金融时间序列预测的建模原理。将其应用到深圳股票市场的数据,进行预测。最后运用6种误差统计量对预测结果与基于BP算法、基于ARCH（1,1）模型、基于GARCH（1,1）模型的4种预测结果进行比较,并得出结论：基于支持向量回归的预测方法最优。     

支持向量机在企业冰箱订单需求中的应用

为了提高企业冰箱订单预测精度,提出基于支持向量的订单需求预测模型,本文在对冰箱订单需求影响因素分析的基础上,选出对冰箱影响订单需求最为重要的五个因素,运用支持向量机(SVM)对冰箱订单需求进行训练、预测分析,得到支持向量机在冰箱订单需求预测中的准确率,通过与BP神经网络、时间序列模型(ARMA)对比证明该模型预测精度较高,是一种有效的方法,值得推广使用。     

支持向量机在春运客流预测中的应用

由于春运客流预测是不确定的,非线性的动态开放性复杂系统,传统方法往往难以正确地描述这种复杂的非线性特征,因而无法正确进行客流预测。本文采用指数平滑的客流预测方法,提出了一种基于时间序列的支持向量机的历史客流预测方法,实验数据表明,预测结果是可信的。     

基于加权最小二乘支持向量机的金融时间序列预测

针对股票市场的高噪声,强非线性和不确定性等特点和以往传统的神经网络预测方法存在的不足,对标准最小二乘支持向量机方法优化,运用给各个样本的惩罚系数和误差要求赋予不同权重的加权最小二乘支持向量机方法结合滚动时间窗来学习建模。对上证地产业类指数的建模和预测表明,该算法具有良好的预测精度和抗燥性能,是对股市进行分析和预测的一种可行而有效的方法。     

基于加权支持向量机的商务采购决策管理

本文在基于一般支持向量机的商务管理决策方法的基础上,对商务采购决策管理问题进行了定性分析,然后对一般支持向量机模型进行了改进,给出了三种加权支持向量机模型,从而使决策方案更具有科学性和针对性。     

基于GA-SVM的物流园区物流需求预测及分析

文章基于支持向量机模型对物流园区物流需求进行预测,相较于传统的网格式搜索对支持向量机参数寻优,使用遗传算法对支持向量机参数寻优,能在实数集内连续地寻找最优参数组合,构建出GA-SVM物流需求预测模型。并通过成都市实例验证了GA-SVM预测模型的有效性。     

基于支持向量机的上证指数预测研究

基于支持向量机的预测模型对上证指数进行预测,并将其预测结果与BP神经网络的预测结果进行对比,其结果表明,支持向量机的预测模型具有较高的拟合和预测精度并优于BP神经网络模型,且支持向量机预测方法计算速度快,准确率高,具有很好的推广应用价值。     

基于主成分的RBF核SVM在财务预测领域的应用

支持向量机(SVM)是实现结构风险最小化归纳原理的一种机器学习理论,在有限的学习模式下具有良好的泛化能力。为了评估支持向量机的预测性能,本文通过对684家企业进行财务分析,进而预测企业在未来两年是否会被ST。建立基于主成分的RBF(核函数)核SVM模型,将支持向量机与传统学习算法进行比较,结果表明支持向量机有效地提高了预测的精度,具有良好的泛化和预测能力。     

基于LSTM深度学习的大豆期货价格预测

面对越来越复杂的金融市场环境,以传统统计学和计量学为主的时间序列预测模型在发现序列中的长期依赖关系方面存在一定局限性,而深度学习中的长短期记忆(LSTM)网络有望克服这一问题。通过构造一个多层LSTM网络价格预测模型,使用中国2007—2019年大豆期货价格数据进行了实证研究。结果显示,参数调优对LSTM网络模型预测效果有着较大影响,其中影响较大的主要参数包括迭代次数、学习率、窗口大小和网络层数等;与ARIMA模型、MLP模型、SVR模型相比,LSTM网络模型的预测结果准确性更高,在拟合优度(R-2)上分别提高了1.064%、2.147%、1.674%。LSTM网络模型在价格预测方面的良好表现,为预测大豆期货价格提供了新思路。     

基于核Fisher鉴别分析的网络入侵检测算法

提出了一种将核Fisher鉴别分析特征抽取与多分类支持向量机算法结合的网络入侵检测技术,扩展了二分类支持向量机．利用经过核Fisher鉴别分析特征抽取后的训练数据构造优化的决策树,从而实现支持向量机的多分类。实验结果表明该算法能够提高检测正确率,同时降低训练时间,取得了良好的效果。     

基于非对称GARCH模型的EUR/USD实证分析

波动率是金融时间序列最重要的特征之一,因而模拟和预测金融市场资产收益率的波动性己经成为众多理论和实证研究的重要领域。本文通过对外汇市场EUR/USD收益率波动性的实证建模分析,验证了在信息不对称的外汇市场上,好消息与坏消息对收益率波动性的不同反应,进而证实了外汇市场中杠杆效应,为外汇投资者提供参考。     

Forecasting volatility

The forecasting ability of the most popular volatility forecasting models is examined and an alternative model developed. Existing models are compared in terms of four attributes: (1) the relative weighting of recent versus older observations, (2) the estimation criterion, (3) the trade‐off in terms of out‐of‐sample forecasting error between simple and complex models, and (4) the emphasis placed on large shocks. As in previous studies, we find that financial markets have longer memories than reflected in GARCH(1,1) model estimates, but find this has little impact on outofsample forecasting ability. While more complex models which allow a more flexible weighting pattern than the exponential model forecast better on an in‐sample basis, due to the additional estimation error introduced by additional parameters, they forecast poorly out‐of‐sample. With the exception of GARCH models, we find that models based on absolute return deviations generally forecast volatility better than otherwise equivalent models based on squared return deviations. Among the most popular time series models, we find that GARCH(1,1) generally yields better forecasts than the historical standard deviation and exponentially weighted moving average models, though between GARCH and EGARCH there is no clear favorite. However, in terms of forecast accuracy, all are dominated by a new, simple, nonlinear least squares model, based on historical absolute return deviations, that we develop and test here. © 2005 Wiley Periodicals, Inc. Jrl Fut Mark 25:465–490, 2005     

Benchmarking sales staffing efficiency in dealerships using extended data envelopment analysis

This study presents an approach to benchmark dealer performance in a business-to-business setting through a rigorous efficiency analysis of sales staff allocation. Using a series of basic and extended data envelopment analysis (DEA) models on data collected from a survey of self-reported financial and statistical information, this research assesses dealer efficiency and compares the efficiency scores to traditional financial benchmarking. Findings support the minimization of outsourcing services that are customer interactive and highly specific to a transaction to differentiate the dealer from its competition. Integrating the results from DEA models, manufacturers obtain a comprehensive view of allocating sales staff to increase dealer efficiency and generating a complementary approach to traditional financial ratio benchmarking in determining best practices to other dealers.     

Return distributions and volatility forecasting in metal futures markets: Evidence from gold,silver, and copper

The characterization of return distributions and forecast of asset‐price variability play a critical role in the study of financial markets. This study estimates four measures of integrated volatility—daily absolute returns, realized volatility, realized bipower volatility, and integrated volatility via Fourier transformation (IVFT)—for gold, silver, and copper by using high‐frequency data for the period 1999 through 2008. The distributional properties are investigated by applying recently developed jump detection procedures and by constructing financial‐time return series. The predictive ability of a GARCH (1,1) forecasting model that uses various volatility measures is also examined. Three important findings are reported. First, the magnitude of the IVFT volatility estimate is the greatest among the four volatility measures. Second, the return distributions of the three markets are not normal. However, when returns are standardized by IVFT and realized volatility, the corresponding return distributions bear closer resemblance to a normal distribution. Notably, the application of financial‐time sampling technique is helpful in obtaining a normal distribution. Finally, the IVFT and realized volatility proxies produce the smallest forecasting errors, and increasing the time frequency of estimating integrated volatility does not necessarily improve forecast accuracy. © 2010 Wiley Periodicals, Inc. Jrl Fut Mark 31:55–80, 2011     

基于第三方电子交易平台的供应链金融服务创新——云仓及其运作模式初探

针对中小企业“融资难”现象,对比分析传统供应链金融与交易型电子商务平台的交易方式和融资模式,将传统供应链金融服务拓展到现货电子交易平台上,提出“云仓”——这一新型商业模式,该模式提供供应链一体化服务,既可线上交易担保和商机拓展,又可线下融资支持和仓储物流服务,同时具有现货连续交易的价格发现机制,能更有效地解决中小企业融资瓶颈,提高商品流通效率,降低融资风险。该文为供应链金融业务和现货电子交易市场持续健康发展提供理论支撑和行业指导。     

基于网络环境下的财务管理的几个重点问题的研究

网络经济的快速发展,给企业参与市场带来了新的机遇,同时对企业传统的财务管理也提出了挑战。传统的支付方式与网络财务发展已不相适应,取而代之的应是新兴的网上支付方式和电子货币;同时,网络环境下要建立与之相配套的高效的集成管理信息系统,以使企业加快对财务信息的处理和利用,提高企业的竞争力;网络财务的诸多优点给企业带来了巨大的商机和财富,也不可避免的引起了一系列的安全问题。     

支持向量机在模式识别中的应用

针对传统神经网络存在网络结构难于确定、过学习以及局部极小等问题，研究了基于支持向量机（SVM）的模式识别问题。通过对棋盘这种典型非线性二值问题的分类研究，分析了支持向量机的分类与泛化能力。支持向量机在分类和泛化能力方面远远优于传统神经网络。最后将支持向量机用于对两类飞机目标的分类识别，通过多组蒙特卡罗试验，获得了较好的识别结果。支持向量机在目标识别中有巨大潜力和广阔前景。     

Predicting financial volatility: High‐frequency time‐series forecasts vis‐à‐vis implied volatility

Recent evidence suggests option implied volatilities provide better forecasts of financial volatility than time‐series models based on historical daily returns. In this study both the measurement and the forecasting of financial volatility is improved using high‐frequency data and long memory modeling, the latest proposed method to model volatility. This is the first study to extract results for three separate asset classes, equity, foreign exchange, and commodities. The results for the S&P 500, YEN/USD, and Light, Sweet Crude Oil provide a robust indication that volatility forecasts based on historical intraday returns do provide good volatility forecasts that can compete with and even outperform implied volatility. © 2004 Wiley Periodicals, Inc. Jrl Fut Mark 24:1005–1028, 2004