基于支持向量机的股市组合预测模型研究

首先利用线性回归模型提取股市系统的线性特征,其次神经网络提取股市系统的非线性特征,共同生成预测个体;最后利用支持向量机回归组合,时变权重分别赋权生成最终结论。建立基于支持向量机的股市组合预测模型,并对上证指数的日开盘价,收盘价实例分析,结果表明该方法取得较好的效果。     

财务困境预警SVM模型的构建及实证研究

精确的财务困境预测对企业管理层、投资者、债权人、监管层等有着十分重要的意义.本文以支持向量机(SVM)为基础,选取高斯核函数为内积函数,分析惩罚参数和核参数对模型的影响,并通过5-fold cross-validation方法与网格搜索算法选取最优参数,构建财务困境预警的SVM模型.相关的实证结果表明,SVM模型在提前3年的情况下仍能取得较好的预测效果,在预测效率上优于传统的多元判别分析方法.     

基于主成分分析和支持向量机的个人信用评估

本文针对信用评估指标维数较高的问题,运用主成分分析与支持向量机理论建立了一个新的个人信用评估预测模型。为反映该模型在信用评估分类方面的优越性,又分别建立了基于神经网络、K近邻判别分析等多种理论的信用评估模型,并用同一组数据对不同的模型分别进行训练,然后比较其预测分类正确率。实验结果表明,基于主成分分析与支持向量机理论的个人信用评估模型具有较优的预测分类正确率。     

基于企业生命周期理论的企业家绩效——SVM评价方法

本文基于企业生命周期理论,通过考察企业生命周期不同阶段对企业家绩效评价的侧重点,构建了企业家绩效评价指标体系,并应用当今统计学习理论的新方法——支持向量机（Support Vector Machines,缩写为SVM）对企业家绩效进行评价,以克服现有企业家绩效评价体系的不足,增强评价的有效性。     

大数据背景下基于ABC-SVM的建筑工程造价预测

建筑工程项目决策阶段信息量少,精准高效的造价预测是科学决策的关键.为了提高项目前期工程造价预测的精度,探讨如何利用历史项目大数据及机器学习进行新建建筑工程项目的造价预测至关重要.本文首先通过文献研究确定了建筑工程决策阶段造价的主要影响因素,然后利用人工蜂群算法(ABC)对支持向量机(SVM)参数即惩罚因子C和核函数参数g进行优化计算,最终构建了基于ABC-SVM的建筑工程造价预测模型.最后以某工程造价数据平台上的84个建筑工程项目为数据源进行模型验证,结果显示,与GRID-SVM模型和BP神经网络模型相比,本文所提的ABC-SVM模型的预测精度更高,具有更好的适用性.     

基于小波自适应支持向量机的短期电价预测

电价预测对于发电商、供电企业以及市场监管者都具有重要的意义。提出一种小波自适应支持向量机预测模型,先将电价时间序列作小波分解得到低频和高频分量,再采用自适应调整法,自动地为支持向量机选择较好的参数对电价小波分量逐一预测,最后通过小波重构得到电价最终预测结果。实例证明前述方法得到的预测精度高于BP、RBF、SVM等传统预测模型。     

基于粒子群优化支持向量机的冲天炉铁液质量预测

冲天炉铁液质量预测是一项复杂而有难度的技术,受到很多因素的影响。文章提出了基于粒子群优化支持向量机(PSO-SVM)的冲天炉铁液质量预测方法,即将粒子群优化算法(PSO)用于SVM参数优化。它不仅具有很强的全局搜索能力,而且容易实现。经实验结果证明,PSO-SVM的预测输出与实测数据基本一致,其预测精度高于普通的SVM,所有的预测误差都远小于5%的工程许可误差。     

遗传模拟支持向量机在居民消费价格指数预测中的应用

为了能够准确地对我国居民消费指数进行预测,本文深入研究了支持向量机在居民消费价格指数中的预测,首先阐述了最小二乘支持向量机的基本理论,接着提出了遗传模拟退火算法,最后进行实例研究,结果表明该方法具有较高的预测精度.     

三次指数平滑法在民航客运量预测中的应用

文章选取了浙江省1996-2015年民航客运人数,建立了三次指数平滑模型,对该省的民航客运量进行预测,所得的预测值与给出的实际值误差较小,验证了用此模型预测民航客运量的合理可行性.模型的结果和分析表明三次指数平滑法是一种适合民航客运量预测的方法,科学地对客运量进行预测,能为民航企业根据客运量制定合理的运营决策提供一些有价值的参考.     

基于支持向量机旅游需求预测

针对旅游预测中常存在旅游因子难以确定、样本容量小等特点,探讨了一种新的预测方法——支持向量机回归算法(SVR)在旅游需求时间序列预测中的应用。以2004年1月至2007年4月的中国入境旅游人数月度数据为样本,建立了入境旅游需求预测的SVR模型。通过对模型的检验并与神经网络模型(BPNN)的比较,其结果表明SVR模型更优于BPNN模型。     

我国客运交通联系的距离衰减规律

交通运输体现了城市之间的经济联系,是研究区域经济联系的重要依据。通过对省域公路客运、全国铁路和全国航空客运班期与距离关系的实证研究,深入探讨我国客运交通联系的距离衰减规律特征,得到三种客运方式的适宜营运距离、最佳营运里程和平均营运里程以及距离衰减规律的曲线估计模型,并对距离衰减规律的多样性特征进行了评述。     

北京市区域生产总值与公路道路设施建设的关系——基于分布滞后模型

利用Almon方法,建立分布滞后回归模型,对北京市公路里程和GRDP两个经济指标的关系进行了研究,旨在考察道路建设对北京市GRPD的影响。研究表明,公路道路建设对北京区域经济发展具有长期持续的拉动作用。最后,科学推算出北京市公路道路的平均使用年限为22年。     

基于重力模型的河南省公路客流空间运输联系

运用重力模型,在ArcGIS平台上通过VBA编程,模拟河南省公路客流空间运输联系。节点连接图表明,河南省区域公路客流连接关系呈明显的轴—辅系统特征。通过潜能和交流量对比,发现从河南省西北的济源市到东南的周口市、从濮阳市到洛阳市两条交通优先发展带,可为交通规划提供借鉴。     

Estimating the impact of incidents on urban controlled-access highways: an empirical analysis

An empirical analysis is developed that quantifies the impact of different types of traffic incidents on the speed and maximum flow averages of vehicles on a controlled-access highway. The incident types considered include damage to highway infrastructure, vehicle rollover, crashes (into stationary objects), collisions (with moving vehicles), rain, fog, vehicle breakdowns, pedestrians on roadway, etc. Using real-world data from Chile’s most heavily used urban motorway/freeway, estimates of incident impacts on speed are generated using a multiple linear regression model incorporating instrumental variables to correct for endogeneity. Flow results are then generated using the fundamental traffic equation relating speed, flow and density. A ranking of the impacts on highway traffic of the different incident types based on incident frequency as well as impact size demonstrates that for the real case studied, the incidents with the greatest cumulative effect are (in order of magnitude) vehicle breakdown, collisions and rain.     

Highway Spending and Induced Vehicle Emissions: Evidence from the US states

This paper investigates the impact of state and local government highway spending on vehicle emissions. A theoretical framework is constructed to show the effect of government highway spending on passenger and freight vehicle emissions and decompose the effect into a rebound effect, an induced demand effect and an interaction effect. We then develop an empirical strategy and combine state-level data in the US to test the induced CO2 emissions by government highway spending. We find that there are positive and significant total effects of government highway spending on passenger and freight vehicle emissions. The magnitude of these effects, however, significantly differs from one another as the elasticity of freight vehicle emissions with respect to government highway spending is four times larger than that in the passenger sector. The difference can be plausibly explained by the rebound effect and the interaction effect. We argue that policies regarding government spending on highway projects, especially those relying on cost-benefit analysis, should account for the potential difference in induced environmental impacts between passenger and freight vehicles.     

Applying engineering and fleet detail to represent passenger vehicle transport in a computable general equilibrium model

A well-known challenge in computable general equilibrium (CGE) models is to maintain correspondence between the forecasted economic and physical quantities over time. Maintaining such a correspondence is necessary to understand how economic forecasts reflect, and are constrained by, relationships within the underlying physical system. This work develops a method for projecting global demand for passenger vehicle transport, retaining supplemental physical accounting for vehicle stock, fuel use, and greenhouse gas (GHG) emissions. This method is implemented in the MIT Emissions Prediction and Policy Analysis Version 5 (EPPA5) model and includes several advances over previous approaches. First, the relationship between per-capita income and demand for passenger vehicle transport services (in vehicle-miles traveled, or VMT) is based on econometric estimates and modeled using quasi-homothetic preferences. Second, the passenger vehicle transport sector is structured to capture opportunities to reduce fleet-level gasoline use through the application of vehicle efficiency or alternative fuel vehicle technologies, introduction of alternative fuels, or reduction in demand for VMT. Third, alternative fuel vehicles (AFVs) are represented in the EPPA model. Fixed costs as well as learning effects that could influence the rate of AFV introduction are captured explicitly. This model development lays the foundation for assessing policies that differentiate based on vehicle age and efficiency, alter the relative prices of fuels, or focus on promoting specific advanced vehicle or fuel technologies.     

Fiscal Policy,Expectations, and Exchange-Rate Dynamics*

This paper uses the sticky-price monetary model to analyze the effects of fiscal policy on the exchange rate under alternative assumptions about exchange-rate expectations. the use of different expectations mechanisms-specifically the perfect-foresight model and the popular models tested by Frankel and Froot: regressive, adaptive, and distributed-lag-is based on recent empirical evidence suggesting that exchange-rate expectations may not be rational. the most surprising finding in the paper is that with adaptive and distributed-lag expectations, fiscal expansion has no initial impact on the exchange rate, and the same may be true for regressive expectations.     

基于城市微观土地利用影响下的碳排放评测研究——以南京市某单位为例

文章借助连续逼近法与交通周转量法构建城市微观土地利用影响下的碳排放评测模型,并依据该模型对南京市某单位双园区土地利用模式所带来的碳排放进行了评测。结果表明：（1）不同交通方式下的碳排放量不同,城市公交交通方式年碳排放量最低,为203008.80kg;私人轿车交通方式年碳排放量最高,为659398.01kg。（2）同一交通方式下,不同等级车型的碳排放量相同。单位通勤交通方式中,中型客车〉大型客车〉轻型客车;私人轿车交通方式中,中级轿车〉普通轿车〉微型轿车。据此定量化城市微观土地利用与碳排放的关系,为土地利用配置过程中碳减排的研究提供参考。