資源描述：
《FOR FINANCIAL TIME-SERIES FORECASTING》由會員上傳分享，免費(fèi)在線閱讀，更多相關(guān)內(nèi)容在行業(yè)資料-天天文庫。
1、ALONGMEMORYPATTERNMODELLINGANDRECOGNITIONSYSTEMFORFINANCIALTIME-SERIESFORECASTINGSameerSingh{s.singh@exeter.ac.uk}UniversityofExeterDepartmentofComputerSciencePrinceofWalesRoadExeterEX44PTSingh,S."ALongMemoryPatternModellingandRecognitionSystemforFinancialForecasting",PatternAnalysisandAppl
2、ications,vol.2,issue3,pp.264-273,1999.1ALONGMEMORYPATTERNRECOGNITIONANDMODELLINGSYSTEMFORFINANCIALTIME-SERIESFORECASTINGABSTRACTInthispaper,theconceptofalongmemorysystemforforecastingisdeveloped.PatternModellingandRecognitionSystemsareintroducedaslocalapproximationtoolsforforecasting.Suchsy
3、stemsareusedformatchingcurrentstateofthetime-serieswithpaststatestomakeaforecast.Inthepast,thissystemhasbeensuccessfullyusedforforecastingtheSantaFecompetitiondata.Inthispaper,weforecastthefinancialindicesofsixdifferentcountriesandcomparetheresultswithneuralnetworksonfivedifferenterrormeasu
4、res.Theresultsshowthatpatternrecognitionbasedapproachesintime-seriesforecastingarehighlyaccurateandtheseareabletomatchtheperformanceofadvancedmethodssuchasneuralnetworks.21.MOTIVATIONTime-seriesforecastingisanimportantresearchareainseveraldomains.Traditionally,forecastingresearchandpractice
5、hasbeendominatedbystatisticalmethods.Morerecently,neuralnetworksandotheradvancedmethodsonpredictionhavebeenusedinfinancialdomains[1-3].Aswegettoknowmoreaboutthedynamicnatureofthefinancialmarkets,theweaknessesoftraditionalmethodsbecomeapparent.Inthelastfewyears,researchhasfocussedonunderstan
6、dingthenatureoffinancialmarketsbeforeapplyingmethodsofforecastingindomainsincludingstockmarkets,financialindices,bonds,currenciesandvaryingtypesofinvestments.Peters[4]notesthatmostfinancialmarketsarenotGaussianinnatureandtendtohavesharperpeaksandfattails,aphenomenonwellknowinpractice.Inthef
7、aceofsuchevidence,anumberoftraditionalmethodsbasedonGaussiannormalityassumptionhavelimitationsmakingaccurateforecasts.OneofthekeyobservationsexplainedbyPeters[4]isthefactthatmostfinancialmarketshaveaverylongmemory;whathappenstodayaffectsthefutureforever.
