简介:Creditriskpredictionmodelsseektopredictqualityfactorssuchaswhetheranindividualwilldefault(badapplicant)onaloanornot(goodapplicant).Thiscanbetreatedasakindofmachinelearning(ML)problem.Recently,theuseofMLalgorithmshasproventobeofgreatpracticalvalueinsolvingavarietyofriskproblemsincludingcreditriskprediction.OneofthemostactiveareasofrecentresearchinMLhasbeentheuseofensemble(combining)classifiers.Researchindicatesthatensembleindividualclassifiersleadtoasignificantimprovementinclassificationperformancebyhavingthemvoteforthemostpopularclass.Thispaperexploresthepredictedbehaviouroffiveclassifiersfordifferenttypesofnoiseintermsofcreditriskpredictionaccuracy,andhowcouldsuchaccuracybeimprovedbyusingpairsofclassifierensembles.Benchmarkingresultsonfivecreditdatasetsandcomparisonwiththeperformanceofeachindividualclassifieronpredictiveaccuracyatvariousattributenoiselevelsarepresented.Theexperimentalevaluationshowsthattheensembleofclassifierstechniquehasthepotentialtoimprovepredictionaccuracy.
简介:Thepaperdescribedthreemethodsofscalingthebondportfolioprice.Theywereduration,convexityandtimevalue.FromtheprincipleofNo-arbitrage,therewasoneandonlyonerelationshipofduration,convexityandtimevalue.ItchosethreecorporationbondsofChinaandanalyzedtheriskoftwoinvestmentstrategies.
简介:社会风险分类是为社会风险感觉的一个基本、复杂的问题。进行社会风险分类,Tianya论坛帖子作为数据来源,和四种代表被选择:字符串表示,术语频率表示,TF-IDF表示和BBS帖子的分布式的表示被使用。用作为距离度量标准编辑距离或余弦类似,四个k近邻居(kNN)分类器基于不同代表被开发并且比较。由于词顺序的优先级和神经网络模型段向量的语义抽取,kNN为社会风险分类由段向量(kNN-PV)表演有效性基于分布式的表示产生了。而且,通过不同重量,kNN-PV作为一个整体模型与另外的三个kNN分类器被相结合改进社会风险分类的表演。通过蛮力格子搜索方法,最佳的重量被分到不同kNN分类器。与kNN-PV相比,试验性的结果表明整体方法的Macro-F显著地为社会风险分类被改进。
简介:Calculatingandmeasuringcreditriskisthekeytechniqueofcommercialbankmanagement.InternationalrelativeachievementsmainlyincludeZandZETAmodelofAltman,Standard&poolexternalratingsystem,Moodyexternalratingsystem,KMVmodel,CreditMetricsmodel,CreditRiskmodel,McKinseymodelandsoon.Chineserelativeachievementsmainlyincludes:creditscoremethod,comprehensiveestimatingmethod,discriminativeanalysismethod,artificialneuralnetworkmethodetc.Thispaperanalyzestherelativeresearchachievementsofcreditriskmeasurementandthefutureresearchtrend.
简介:Itisanimportanttasktoanalyzethescheduleriskinaprojectmanagement.Asasemi-constructedornon-constructedcomplexsystem,therearemanydifficultiesinthequantitativeanalysisoftheschedulerisk(SRA).Thepaperintegratesintelligenttechniquestoobtainmassivebasicdatarequiredintheriskanalysisprocess.ItgreatlyimprovestheprecisionandefficiencyoftheSRA.Inaddition,thepaperpresentsamechanismandarchitectureoftheintegratedintelligentsystems.Finally,theconcludingremarksareprovidedforbasicdataacquisitionintheSRA.
简介:在制造工程师协会之中的联合贷款保证合同和相互的保证合同形成制造工程师协会保证网络的基础。这些网络的扩大由于在他们以内嵌入的地区性、工业的风险传染增加一个金融系统的脆弱。由提供一个贷款保证网络的一个理论框架,一个方法为计算拿全部网络的观点的贷款保证引起的风险溢出的数量被建议。另外,在保证网络的风险传染的线路被分析,表明当缺省风险震动发生时,风险传染要不是几个回合沿着节点旅行不一次并且一个公司的风险控制不能阻止这些全身的风险。因此,一个风险控制计划在网络基于公司的地点和重要性被设计。用从一个真实保证网络的数据,我们表明那鉴别在保证的公司的节点地点联网(包括公司的coritivity和亲密)能在理解风险传染机制并且在一个危机发生以前,阻止全身的信用风险帮助。
简介:Majorsocietalproblemsaffectthesocialstability.Itisnecessarytounderstandthepublicopiniontowardthoseissuestoavoidsocialconflicts.Nowadaysthesocialmediabecomethemajorplatformtotrackwhatthepublicisconcernedaboutandwhichmaybeofthesocietalrisk.However,itisverytoughtocapturethepublicattentioninshorttimeduetohugeflowofuser-generatedcontents.Inthispaper,weapproachthisproblembyexpandingthemethodofgeneratingstorylinewiththeresultdisplayedbyamulti-viewgraph.Onereal-worldexampleisillustratedandevaluationisgiventoshowtheeffectivenessoftheproposedmethod.
简介:Thenearly30-yeareconomicgrowthmiraclebringstheconsequenttremendouspoor-richgapleadingstrongdrivesforsocialtransformationincurrentChina.Chinesetopleadershaverealizedtoincreasethepeoples'income,improvequalityoflifeandconstructa'harmonioussociety'askeymissionsespeciallyinrecent10years.Howtomeasureaharmonioussocietyisoneimportanttopicasdifferentmeasuresmayleadtodifferentdevelopmentpolicies.Thispaperoutlinesover10indicesrelevanttomeasureaharmonioussociety.Someareglobalindicators,whilesomearecontributedbydomesticresearchersandarousedebates.Mostofthoseindicatorsrequireconductingsurveysonsocialattitudesundermicrolevels,whichisalwaystimeconsumingwithproblemofdataquality.AsInternettechnologyadvancesprovidewaystorecordanddisseminatefreshcommunityideasandthoughtsconveniently,detectingtopicsoremotionsfromon-linepublicopinionsisbecomingatrendoronesupplementwaytoovercomethosedataacquisitionproblems.Thispaperdiscussesoneapproachtoon-linesocietalriskperceptionusinghotsearchwordsandBBSposts.Suchatrialaimstoprovideanotherwaytosocietalriskperceptiondifferentfromthoseintraditionalsociopsychologystudies.Challengesarealsoindicated.
简介: