scaling predictive analytics with data science automation

scaling predictive analytics with data science automation

ID:5289649

大小:5.23 MB

頁數(shù):13頁

時(shí)間:2017-12-07

scaling predictive analytics with data science automation_第1頁
scaling predictive analytics with data science automation_第2頁
scaling predictive analytics with data science automation_第3頁
scaling predictive analytics with data science automation_第4頁
scaling predictive analytics with data science automation_第5頁
資源描述:

《scaling predictive analytics with data science automation》由會(huì)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、ScalingPredictiveAnalyticswithDataScienceAutomation主講人:MaxKanter,F(xiàn)eatureLabsCEO數(shù)據(jù)改變企業(yè)決策,數(shù)據(jù)改善人類生活WhoamI??Passionateaboutmakingdatasciencemoreaccessible?FormerstudentandmachinelearningresearcherattheMassachusettsInstituteofTechnology(MIT)?Previously,anengineeratTwitte

2、r,HewlettPackard,TheNewYorkTimes,andFitbitComputerScienceandArtificialIntelligenceLab?Currently,theCEOofFeatureLabs@MIT(Boston,USA)數(shù)據(jù)改變企業(yè)決策,數(shù)據(jù)改善人類生活WhyisDataScienceImportant?SalesandCustomerEconomicEnergyMarketingBehaviorHealthFinanceDataproblemsAgricultureSupplycha

3、inareeverywhereCyberEnterpriseSportsOperationsDeviceandEducationIOTManufacturing數(shù)據(jù)改變企業(yè)決策,數(shù)據(jù)改善人類生活TheDataScienceProcess數(shù)據(jù)改變企業(yè)決策,數(shù)據(jù)改善人類生活FeatureEngineering?Human-driven?Iterative?Mosttimeconsumingpartofdatascienceprocess?BUT,itiskeytodevelopinghighperformingmodelsTypi

4、calfeatureengineeringprocess數(shù)據(jù)改變企業(yè)決策,數(shù)據(jù)改善人類生活A(yù)utomatedFeatureEngineeringInventedatMITin2015數(shù)據(jù)改變企業(yè)決策,數(shù)據(jù)改善人類生活HowDFSworks1)Definerepositoryof"primitive"functions?Primitiveseachdefinesimpletransformation2)Applyprimitivestocolumnsoracrossrelationships3)"Stack"primitives

5、toformcomplexApplyingDFStoexamplecalculationsdatabase數(shù)據(jù)改變企業(yè)決策,數(shù)據(jù)改善人類生活ValidatingDeepFeatureSynthesistestedagainstonaverageover100092%1200datascientistsonoftopscoredayssaved數(shù)據(jù)改變企業(yè)決策,數(shù)據(jù)改善人類生活ValidatingDeepFeatureSynthesis1.ProjectExcitement2.RepeatBuyer3.DropoutPredic

6、tion數(shù)據(jù)改變企業(yè)決策,數(shù)據(jù)改善人類生活OpenSourceLibraryforDeepFeatureSynthesisInstallforfreeatwww.featuretools.com數(shù)據(jù)改變企業(yè)決策,數(shù)據(jù)改善人類生活Relationaldata->featurematrixwithonefunction數(shù)據(jù)改變企業(yè)決策,數(shù)據(jù)改善人類生活ConclusionsWhatisDataScienceAutomation?1.Technologytohelpthosenewtodatascience2.Toolsfortoi

7、mproveexistingdatascientists3.ReadytouseTODAY!(featuretools.com)數(shù)據(jù)改變企業(yè)決策,數(shù)據(jù)改善人類生活THANKSEmail:max@featurelabs.comTwitter:@maxk數(shù)據(jù)改變企業(yè)決策,數(shù)據(jù)改善人類生活

當(dāng)前文檔最多預(yù)覽五頁,下載文檔查看全文

此文檔下載收益歸作者所有

當(dāng)前文檔最多預(yù)覽五頁,下載文檔查看全文
溫馨提示:
1. 部分包含數(shù)學(xué)公式或PPT動(dòng)畫的文件,查看預(yù)覽時(shí)可能會(huì)顯示錯(cuò)亂或異常,文件下載后無此問題,請(qǐng)放心下載。
2. 本文檔由用戶上傳,版權(quán)歸屬用戶,天天文庫負(fù)責(zé)整理代發(fā)布。如果您對(duì)本文檔版權(quán)有爭(zhēng)議請(qǐng)及時(shí)聯(lián)系客服。
3. 下載前請(qǐng)仔細(xì)閱讀文檔內(nèi)容,確認(rèn)文檔內(nèi)容符合您的需求后進(jìn)行下載,若出現(xiàn)內(nèi)容與標(biāo)題不符可向本站投訴處理。
4. 下載文檔時(shí)可能由于網(wǎng)絡(luò)波動(dòng)等原因無法下載或下載錯(cuò)誤,付費(fèi)完成后未能成功下載的用戶請(qǐng)聯(lián)系客服處理。