the ux of predictive behavior for the iot (2016: o'reilly designing for the iot)

62
Good afternoon and thanks for having me here. In this talk I want to look at the design challenges of systems that anticipate users’ needs and then act on them. That means it sits at the intersection of the internet of things, user experience design and machine learning, and although people have dealt with one of those disciplines before, I don’t think they’ve ever been combined in quite the ways they are now, or with the current enthusiasm. The talk is divided into several parts: it starts with an overview of how I think Internet of Things devices are primarily components of services, rather than being self-contained experiences, how predictive behavior enables key components of those services, and then I finish by trying to to identify user experience issues around predictive behavior and suggestions for patterns to ameliorate those issues. A couple of caveats: - My current work in this field focuses almost exclusively on the consumer internet of things, so I see most things through that lens. Predictive AI has a long history in industrial applications, it’s in the consumer space that we really the the UX issues. - I want to point out that few if any of the issues I raise are new. Though the terms “internet of things” and “machine learning” are hot right now, the ideas have been discussed in research circles for decades. Search for “ubiquitous computing,” “ambient intelligence,” and “pervasive computing” and you’ll see a lot of great thought in the space. If you’re really ambitious, you can read the Artificial Intelligence and Cybernetics works of the 50s and 60s and you’ll be surprised by the prescience of the people working in this space when the entire world’s compute power was about as much as my key fob. - There are a lot of ideas here, and I will almost certainly under-explain something. For that I apologize in advance. My goal here is to give you a general sense of how these the pieces connect, rather than an in-depth explanation of any one of the pieces. - Finally, most of my slides don’t have words on them, so I’ll make the complete deck with a transcript available as soon I’m done. 0

Upload: mike-kuniavsky

Post on 15-Jan-2017

166 views

Category:

Design


0 download

TRANSCRIPT

Page 1: The UX of Predictive Behavior for the IoT (2016: O'Reilly Designing for the IOT)

Good afternoonandthanksforhavingmehere.InthistalkIwanttolookatthedesign

challengesofsystemsthatanticipateusers’needsandthenactonthem.Thatmeansitsitsat

theintersectionoftheinternetofthings,userexperiencedesignandmachinelearning,and

althoughpeoplehavedealtwithoneofthosedisciplinesbefore,Idon’tthinkthey’veever

beencombinedinquitethewaystheyarenow,orwiththecurrententhusiasm.

Thetalkisdividedintoseveralparts:itstartswithanoverviewofhowIthinkInternetof

Thingsdevicesareprimarilycomponentsofservices,ratherthanbeingself-contained

experiences,howpredictivebehaviorenableskeycomponentsofthoseservices,andthenI

finishbytryingtotoidentifyuserexperienceissuesaroundpredictivebehaviorand

suggestionsforpatternstoamelioratethoseissues.

Acoupleofcaveats:

- Mycurrentworkinthisfieldfocusesalmostexclusivelyontheconsumerinternetofthings,

soIseemostthingsthroughthatlens.PredictiveAIhasalonghistoryinindustrial

applications,it’sintheconsumerspacethatwereallythetheUXissues.

- IwanttopointoutthatfewifanyoftheissuesIraisearenew.Thoughtheterms“internet

ofthings”and“machinelearning”arehotrightnow,theideashavebeendiscussedin

researchcirclesfordecades.Searchfor“ubiquitouscomputing,”“ambientintelligence,”and

“pervasivecomputing”andyou’llseealotofgreatthoughtinthespace.Ifyou’rereally

ambitious,youcanreadtheArtificialIntelligenceandCyberneticsworksofthe50sand60s

andyou’llbesurprisedbytheprescienceofthepeopleworkinginthisspacewhentheentire

world’scomputepowerwasaboutasmuchasmykeyfob.

- Therearealotofideashere,andIwillalmostcertainlyunder-explainsomething.ForthatI

apologizeinadvance.Mygoalhereistogiveyouageneralsenseofhowthesethepieces

connect,ratherthananin-depthexplanationofanyoneofthepieces.

- Finally,mostofmyslidesdon’thavewordsonthem,soI’llmakethecompletedeckwitha

transcriptavailableassoonI’mdone.

0

Page 2: The UX of Predictive Behavior for the IoT (2016: O'Reilly Designing for the IOT)

Let me begin by telling you a bit about my background. I�m a user experience designer. I was one of the first professional Web designers. This is the navigation for a hot sauce shopping site I designed in the spring of 1994.

1

Page 3: The UX of Predictive Behavior for the IoT (2016: O'Reilly Designing for the IOT)

I’vealsoworkedontheuserexperiencedesignofalotofconsumerelectronics

productsfromcompaniesyou’veprobablyheardof.

2

Page 4: The UX of Predictive Behavior for the IoT (2016: O'Reilly Designing for the IOT)

Iwroteacoupleofbooksbasedonmyexperienceasadesigner.Oneisacookbookof

userresearchmethods,andtheseconddescribeswhatIthinkaresomeofthecore

concernswhendesigningnetworkedcomputationaldevices.I’malsomarriedtoone

oftheauthorsofthisbook,sothinkingabouttheimpactofthedesignofconnected

devicesonpeopleiskindofafamilybusiness.

3

Page 5: The UX of Predictive Behavior for the IoT (2016: O'Reilly Designing for the IOT)

Ialsostartedacoupleofcompanies.Thefirst,AdaptivePath,wasprimarilyfocused

ontheweb, andwiththesecondone,ThingM,Igotdeepintodevelopinghardware.

4

Page 6: The UX of Predictive Behavior for the IoT (2016: O'Reilly Designing for the IOT)

TodayIworkforPARC,thefamousresearchlabthatinventedthepersonalcomputer,

objectorientedsoftware,thetabletcomputer,andlaserprinter,asaprincipalinits

InnovationServicesgroup.Wehelpcompaniesreducetheriskofadoptingnovel

technologiesusingamixofsocialresearch,designandbusinessstrategy.

5

Page 7: The UX of Predictive Behavior for the IoT (2016: O'Reilly Designing for the IOT)

IwantstartbyfocusingonwhatIfeelisa keyaspectofconsumerIoTthat’soften

missedwhenpeoplefocusonthehardwareoftheIoT,whichisthatconsumerIoT

productshaveaverydifferentbusinessmodelthantraditionalconsumerelectronics.

6

Page 8: The UX of Predictive Behavior for the IoT (2016: O'Reilly Designing for the IOT)

Historically,acompanymadeanelectronicproduct,sayaturntable,theyfound

peopletosellitforthem,theyadvertiseditandpeopleboughtit.Thatwas

traditionallytheendofthecompany’srelationshipwiththecustomeruntilthat

personboughtanotherthing,andallofthevalueoftherelationshipwasinthe

device.WiththeIoT,thesaleofthedeviceisjustthebeginningoftherelationship

andphysicalthingholdsalmostnovalueforeitherthecustomerorthemanufacturer.

7

Page 9: The UX of Predictive Behavior for the IoT (2016: O'Reilly Designing for the IOT)

When you have a multitude of connected devices and apps, value shifts to services and the devices, software applications and websites used to access it—its avatars—become secondary. A camera becomes a really good appliance for taking photos for Instagram, while a TV becomes a nice Instagram display that you don’t have to log into every time, and a phone becomes a convenient way to check your friends’ pictures on the road.

Hardware, physical things, become simultaneously more specialized and devalued as users see “through” each device to the service it represents. The avatars exist to get better value out of the service.

8

Page 10: The UX of Predictive Behavior for the IoT (2016: O'Reilly Designing for the IOT)

Amazon reallygetsthis.Here�satellingolderadfromAmazonfortheKindle. It’s

saying�Look,usewhateverdevice youwant.Wedon�tcare,aslongyoustayloyaltoourservice.Youcanbuyourspecializeddevices,butyoudon�thaveto.�

9

Page 11: The UX of Predictive Behavior for the IoT (2016: O'Reilly Designing for the IOT)

WhenFirewasreleased5yearsago,JeffBezosevencalled itaservice.

10

Page 12: The UX of Predictive Behavior for the IoT (2016: O'Reilly Designing for the IOT)

Mostlarge-scaleIoT productsareserviceavatars.Theyusespecialized sensorsand

actuatorstosupportaservice,buthavelittlevalue—ordon’tworkatall—without

thesupportingservice.SmartThings,whichwasacquiredbySamsung, clearlystates

itsserviceofferingrightupfrontontheirsite.Thefirstthingtheysayabouttheir

productlineisnotwhatthefunctionalityis,butwhateffecttheirservicewillachieve

fortheircustomers.Theirhardwareproducts’functionality,howtheywilltechnically

satisfytheservicepromise,isalmostanafterthought.

11

Page 13: The UX of Predictive Behavior for the IoT (2016: O'Reilly Designing for the IOT)

Compare thattoX10,theirspiritualpredecessorthat’sbeeninthebusinessfor30

years.AllthatX10tellsisyouiswhatthedevicesare,notwhattheservicewill

accomplishforyou.Idon’tevenknowifthereISaservice.WhyshouldIcarethat

theyhave“modules”?Ishouldn’t,andIdon’t.

12

Page 14: The UX of Predictive Behavior for the IoT (2016: O'Reilly Designing for the IOT)

Simplyconnectingexistingstufftotheinternetdoesnotproduce customervalue…

13

Page 15: The UX of Predictive Behavior for the IoT (2016: O'Reilly Designing for the IOT)

Simpleconnectivityhelpswhenyou’retryingtomaximizetheefficiencyofafixed

process,butthat’snotaproblemthatmostpeoplehave.We’vebeenabletosimply

connectvariousdevicestoacomputersinceaTandyColorComputerscouldlightsoff

andonoverX10in1983.TodayyoucanbuyamodulefromParticle,ElectricImpora

dozenothercompaniesandintegrateitinamonthtoconnectanyarbitrarydeviceto

theInternet.Theproblemisthatthatwasn’tveryusefulthen,andit’snotveryuseful

now.IfyoureplacetheTandywithaniPhoneandthelampwithawashingmachine…

14

Page 16: The UX of Predictive Behavior for the IoT (2016: O'Reilly Designing for the IOT)

…oraneggcarton,youstillhavethesameproblem,andit’sauserexperience

problem.

TheUXproblemisthatendusershavetoconnectallthedotstocoordinatebetween

awidevarietyofdevices,andtointerpretthemeaningofallofthesesensorsto

createpersonalvalue.Formanysimplyconnectedproductsthereissolittleefficiency

tobehadrelativetothecognitiveloadthatit’sjustnotworthit.What’sworse,the

extracognitiveloadisexactlyoppositetowhattheproductpromises,andcustomers

feelintenselydisappointed,perhapsevenbetrayed,whentheyrealizehowlittlethey

getoutofsuchaproductThatmakesmostsuchproductseffectivelyWORSEthan

useless.

Thatpromisegapiswhatdistinguishesagadgetfromatool,whythiseggcartonis

funny,andwhyQuirkywhomadeit,filedforbankruptcyafterburningthrough

hundredsofmillionsofdollars.

15

Page 17: The UX of Predictive Behavior for the IoT (2016: O'Reilly Designing for the IOT)

Howdoyoumakemoneyinthisspace ofdematerializeddevicesandcloudservices?

16

Page 18: The UX of Predictive Behavior for the IoT (2016: O'Reilly Designing for the IOT)

Oneapproachistochangefromanownershipmodeltoasubscriptionmodel.Now

thedevicegivesaccesstoadesiredendresult,withouttheburdensofownershipor

maintenance.TheIoT technologyiswhatgivesanefficientwaytotrackandcharge

forassets.Carsharing,bikesharing,Uber andAirBNB followthismodel.Youdon’t

useiteveryday,sowhyownit?High-endclothingisgoingthisway.Doyoureally

needtoownthatPradahandbagsoyoucanuseittwiceayear?

17

Page 19: The UX of Predictive Behavior for the IoT (2016: O'Reilly Designing for the IOT)

Hewlett Packard’sprinterdivisionisreallyaninkcompanythatalsomakesink

consumptiondevices.SimilarlyAmazonistryingtocornerthemarketonall

consumables,whetherthey’redigital…

18

Page 20: The UX of Predictive Behavior for the IoT (2016: O'Reilly Designing for the IOT)

..orphysical.Their Dashreplenishmentservicecanturnanydevicewith

consumables…

19

Page 21: The UX of Predictive Behavior for the IoT (2016: O'Reilly Designing for the IOT)

…intoanautomaticAmazonreorderingmachine.

TheDashbuttonisanetworkedcomputerwhoseonlypurposeistobeanavatarfor

productswhereit’snotyeteconomicallyfeasibletoincludeconnectedelectronics,

likeamacaroniandcheesebox.That’sgoingtochangeastheelectronicsgetcheaper.

Moreover,thebuttonisasensorforpeople’sintent,whichthendovetailsintothe

realbusinessmodel,whichisnotjustshippingyoumintswhenyou’retoolazyto

leavethehouse…buttoidentifyyourbuyingpatterns,yourcravings,yourimpulses,

sothattheycanpredictthemandshipyoumintsnotwhenyouaskforthem,but

whenyouwantthem.

20

Page 22: The UX of Predictive Behavior for the IoT (2016: O'Reilly Designing for the IOT)

Ithink therealvalueconnectedservicesofferistheirabilitytomakesenseofthe

worldonourbehalf,toreducecognitiveloadbyenablingpeopletointeractwith

devicesatahigherlevelthansimpletelemetry,atthelevelofintentionsandgoals,

ratherthandataandcontrol.Humansarenotbuilttocollectandmakesenseofhuge

amountsofdataacrossmanydevices,ortoarticulateourneedsassystemsof

mutuallyinterdependentcomponents.Computersaregreatatit.

21

Page 23: The UX of Predictive Behavior for the IoT (2016: O'Reilly Designing for the IOT)

Theinterestingthingisthatthisnotjusttheory.

Predictionandresponseisattheheartofthevaluepropositionmanyofthemost

compellingIoT services,startingwiththeNest.TheNestsaysthatitknowsyou.How

doesitknowyou?Itpredictswhatyou’regoingtowantbasedonyourpastbehavior.

22

Page 24: The UX of Predictive Behavior for the IoT (2016: O'Reilly Designing for the IOT)

Amazon’sEchospeaker saysit’scontinuallylearning.Howisthat?Predictivemachine

learningbasedonyouractionsandyourwords.

23

Page 25: The UX of Predictive Behavior for the IoT (2016: O'Reilly Designing for the IOT)

The Birdi smartsmokealarmsaysitwilllearnovertime,whichisagainthesame

thing.

24

Page 26: The UX of Predictive Behavior for the IoT (2016: O'Reilly Designing for the IOT)

Jaguar, learning…ANDintelligent.

25

Page 27: The UX of Predictive Behavior for the IoT (2016: O'Reilly Designing for the IOT)

TheEdyn plantwateringsystemadapts toeverychange.Whatisthatadaptation?

Predictivemachinelearning.

26

Page 28: The UX of Predictive Behavior for the IoT (2016: O'Reilly Designing for the IOT)

Canary,ahomesecurity service.

27

Page 29: The UX of Predictive Behavior for the IoT (2016: O'Reilly Designing for the IOT)

Cocoon,anotherhomesecuritysystem knows.Howdoesitknow?Machinelearning.

28

Page 30: The UX of Predictive Behavior for the IoT (2016: O'Reilly Designing for the IOT)

Here’sfoobot,anairqualityservice.

[Ialsolikehowoneof itsimplicitservicepromisesistoidentify whenyourkidsare

smokingpot.]

29

Page 31: The UX of Predictive Behavior for the IoT (2016: O'Reilly Designing for the IOT)

Silk’sSenseadapts

30

Page 32: The UX of Predictive Behavior for the IoT (2016: O'Reilly Designing for the IOT)

Mistbox sprayswaterintoyourairconditionertoreduceyourenergybill.You’dthink

that’saprettysimpleprocess,butno,it’salwayslearning.

31

Page 33: The UX of Predictive Behavior for the IoT (2016: O'Reilly Designing for the IOT)

Anumberofcompaniesaremakingchipsthatmakemachinelearningmuchcheaper

andmorepower-efficient,whichmeansthatit’sgoingtobeveryeasytoinstallitin

everydevice,fromstreetlightstomedicalequipmenttotoys.It’snotjustlikely,it’s

inevitable.Here’sonethatwasannouncedacoupleofweeksago.

32

Page 34: The UX of Predictive Behavior for the IoT (2016: O'Reilly Designing for the IOT)

33

Page 35: The UX of Predictive Behavior for the IoT (2016: O'Reilly Designing for the IOT)

Theydothisthroughprocessesthathavemanynames,butI’lllumpthemallunderMachine

Learning,whichisabigpartofwhatusedtobecalledArtificialIntelligence.Manyofthecore

ideasheregobacktothe1950sandit’sthebasisofeveryemailspamfilter,soifyou’vehad

yourspamautomaticallyfiltered,you’veexperiencedthevalueofmachinelearning.

AbigpartofMachineLearningispatternrecognition.Wehumansevolvedverysophisticated

facultiestorapidlyidentifyvisualimagesinallkindsofdifficultconditions.Youlookata

pictureofanorangeonaredplateandyoucantellinstantlythatit’snotasunset,butuntil

recentlythatwasreally,reallyhardforacomputer.BecauseofacombinationofMoore’s

Lawandsomebreakthroughs,computershavegottenmuchbetteratpatternrecognitionin

thelastcoupleofyears.

Foracomputer,recognizingsomethingstartswithaprocesswheresomebasicattributesof

animageareextracted,suchastheshapeofboundariesbetweenclustersofpixels,orthe

dominantcolorofapatchofanimage.Thesearecalledfeaturesinmachinelearning.By

examininglotsandlotsofexamplesoffeaturesinanimage,amachinelearningsystembuilds

astatisticalmodelofwhatthatclusterrepresents.

Basicformsofthiskindofimagerecognitionhasbeenusedindustriallyfordecade.Legohas

acompletelyautomatedfactorythatinjectionmoldsamillionLegobricksanhour,examines

everysinglepiece,automaticallysorts,bagsandboxesthem,allusingcomputervision.That’s

relativelyold.

Imagesfrom:Region-basedConvolutionalNetworksforAccurateObjectDetectionand

SemanticSegmentation,R.Girshick,J.Donahue,T.Darrell,J.Malik,IEEETransactionson

PatternAnalysisandMachineIntelligence

Real-TimeImageandVideoProcessing:FromResearchtoRealitybyKehtarnavaz and

Gemadia

34

Page 36: The UX of Predictive Behavior for the IoT (2016: O'Reilly Designing for the IOT)

What’snewisaclassofsystemsthatunderstandthecontentofimages.Theydon’tjustlook

atfeatures,butclustersoffeatures,andclustersofclustersoffeatures,andtheycannow

identifyanorangefromthesettingsun,orapersonfromanairplane,orapolarbearfroma

dalmatian.

ThisiswhyFacebookasksyoutosaywhoisinanimage.It’snotjustforyou,it’sfortheirface

recognizer.

Nowhere’stheinterestingpart:we’rebuilttoidentifypatternsinvisualphenomena,but

we’reprettybadatidentifyingtheminotherkindsofsituations.Forexample,ifyou’veever

triedtounderstandsomeone’sfoodsensitivities,it’sreallyhardtoextractwhatthatperson

isreactingto,evenifyoukeepverycarefultrackofwhatthey’veeaten.We’rejustnotbuilt

forit.Itwasneverevolutionarilysufficientlyimportant,sowedidn’tevolveanorganforit.

Computers,ontheotherhand,don’tcare,andnowthatwe’vefoundreallygoodwaystofind

patternsinvisualimages,thesesametechniquescanfindpatternsinanything.

Insteadofamatrixofpixels,whatifyouhadamatrixofmedicalprescriptions,witheachrow

asthehistoryofoneperson’sprescriptionsfromthefirsttimethatpersonwenttothedoctor

foraproblem,throughwhentheywereprescribedcertainthings,towhentheygotbetter,or

theydidn’t.Thesamekindofsystemcouldlearnthetypicalpatternforprescribing,say,a

wheelchair.Itwouldessentiallyseethegeneralshapeofthesequencefortheprescriptionof

achairovertimeandacrossmanypeople.

Thenifyousawawheelchairbeingprescribedthatwasoutsideofthetypicalpattern,you

couldidentifyit.That’scalledanomalydetection.That’sinfactexactlyhowwebuiltasystem

toidentifyMedicarefraud.Peopleareterribleatthatstuff,butcomputersaregreat.

35

Page 37: The UX of Predictive Behavior for the IoT (2016: O'Reilly Designing for the IOT)

Whenoneofthedimensionsistimeandanotheristheoutcomeofaseriesofactions

youcanmakeapatternrecognizerthatassociatesasequenceofactionswithasetof

statisticalprobabilitiesforpossibleoutcomesbasedondatacollectedacrossawide

varietyofsimilarsituations.Inotherwords,becausepeopleandmachinesbehavein

fairlyconsistentways,thesemachinelearningsystemscanincreasinglypredictthe

futureandattempttoadaptthecurrentsituationtocreateamoredesirable

outcome.

36

Page 38: The UX of Predictive Behavior for the IoT (2016: O'Reilly Designing for the IOT)

37

Page 39: The UX of Predictive Behavior for the IoT (2016: O'Reilly Designing for the IOT)

Asinterestingastheseissuesare,Ithinkthat, moreimportantly,whattheyrepresent

isthatwe’reentering intoanewrelationshipwithourdeviceecosystem,asea

changeinourrelationshiptothebuiltworld.

38

Page 40: The UX of Predictive Behavior for the IoT (2016: O'Reilly Designing for the IOT)

Thinkofasewingmachine.It’sverycomplex,butitstillonlyactsinresponsetous.

39

Page 41: The UX of Predictive Behavior for the IoT (2016: O'Reilly Designing for the IOT)

Computersacting autonomously erodethissimpletool/userrelationship.Predictive

IoTismorethanjustrecommendinganewsong,it’sactingonyourbehalfonthe

basisofitsassumptionaboutwhatyouwant,andwhat’sbestforyou.

Atthedawnofcomputinginthelate1940scyberneticistslikeNorbert Wiener

philosophizedabouttheincreasinglycomplexrelationshipbetweenpeopleand

computers,andhowitwasfundamentallydifferentthanthewayweinteractwith

otherkindsofmachines.Developersworkinginsupervisorycontrolofmanufacturing

machinesandroboticshavehadtodealwiththesequestionspragmaticallyforabout

30years,butthankstotheInternetofThings,thisisnowaproblemthateveryone

willhavetograpplewithgoingforward.

Here’sadiagrambythegreatsTomSheridanandBillVerplank from1978,inwhich

theyillustratefourwaysthatsemi-autonomouscomputersandhumanscanwork

togethertosolveaproblem.

40

Page 42: The UX of Predictive Behavior for the IoT (2016: O'Reilly Designing for the IOT)

By2000SheridanexpandedtheseideaswithParasuraman andWickens todefinea

spectrumofresponsibilitybetweenpeopleandcomputers.Itrangesfromhumans

doingallthework(thisisyouwritinganessay)tocomputersdoingallthework

completelyautonomously(thisisyourcar’sfuelinjectioncontroller).Ofcoursethe

goalistogetasystemtolevel9or10.That’sthemaximumreductionincognitive

load.However,forasystemtoqualifyforthat,ithastobeverystable,itseffects

needtobehighlypredictableand,equallyimportantly,it’sroleneedstobe

adequatelyembeddedinsociety.ItneedstobeOKforacomputertotakeonthat

levelofresponsibility.Attheairportwetrustthemonorailcomputerstowork

withouthumanintervention,butwedon’ttrusttheplaneautopilottodothat,even

though-–asIunderstandit—planescanbasicallyflythemselvesthesedays.

PredictiveIoT devicesgenerallyfallbetween5and7onthisscalerightnow.The

problemisthatthisistheexactrangewhereyou’remaximizingsomeone’scognitive

load,butnotnecessarilydoingalltheworkforthem,sotheresultoftheautomation

hadbetterbeworthit.Thisfundamentallyundermineswhatweexpectfromour

tools,andwhenthattoolistryingtoanticipatewhatwe’retryingtodo,it

fundamentallychangesourworkingrelationshipwithit.

41

Page 43: The UX of Predictive Behavior for the IoT (2016: O'Reilly Designing for the IOT)

Theidealscenariothesethingspaintisprettyseductive.Imagineaworldofespresso

machinesthatstart brewingasyou’rethinkingit’sagoodtimeforcoffee;officelights

thatdimwhenit’ssunnytosaveenergy,andmacandcheesethatneverrunsout.The

problemisthatalthoughthevaluepropositionisofabetteruserexperience,it’s

unspecificinthedetails.Previousmachinelearningsystemswereusedinareassuch

aspredictivemaintenance andfinance.Theyweremadebyandforspecialists.Now

thatthesesystemsareforgeneralconsumers,wehavesomesignificantquestions.

Howexactlyhowwillourexperienceoftheworld,ourabilitytouseallthecollecteddata,becomemoreefficientandmorepleasurable?

We’restillearlyinourunderstandingofpredictivedevices,andinthedisciplineof

whatAaronShapiroofHugehasdubbedAnticipatoryDesign,sorightnowthe

problemsareworsethansolutions.IwanttostartbyarticulatingtheissuesI’ve

observedinourwork.

42

Page 44: The UX of Predictive Behavior for the IoT (2016: O'Reilly Designing for the IOT)

We’veneverhad mechanicalthingsthatmakesignificantdecisionsontheirown.As

devicesadapttheirbehavior,howwilltheycommunicatethatthey’redoingso?Do

westickasignonthemthatsays“adapting”,likethelightonavideocamerasays

“recording”?Shouldmychairvibratewhenadjustingtomyposture?Howwillusers,

orjustpassers-by,knowwhichthingsadapt?Icouldendupsittinguncomfortablefor

alongtime,waitingformychairtochange,beforerealizingitdoesn’tadaptonits

own.Howshouldsmartdevicessettheexpectationthattheymaybehavedifferently

inwhatappearstobeidenticalcircumstances?

How doweknowHOWintelligentthesedevicesare?Peoplealreadyoftenproject

moresmartsondevicesthanthosedevicesactuallyhave,soacoupleofaccurate

predictionsmayimplyamuchbettermodelthanactuallyexists.Howdoweknow

we’renotjust homesteadingtheuncannyvalleyhere?

43

Page 45: The UX of Predictive Behavior for the IoT (2016: O'Reilly Designing for the IOT)

Theironyinpredictivesystemsisthat they’reprettyunpredictable,atleastatfirst.

Whenmachinelearningsystemsarenew,they’reofteninaccurateandunpredictable,

whichisnotwhatweexpectfromourdigitaldevices.60%-70% accuracyistypicalfor

afirstpass,buteven90%accuracyisn’tenoughforapredictivesystemtofeelright,

sinceifit’smakingdecisionsallthetime,it’sgoingtobemakingmistakesallthetime,

too.It’sfineifyourhouseisacoupleofdegreescoolerthanyou’dlike,butwhatif

yourwheelchairrefusestogotoadrinkingfountainnexttoadoorbecauseit’sbeen

trainedondoorsanditcan’ttellthat’snotwhatyoumeaninthisoneinstance?For

allthetimesasystemgetsitright,it’sonthemistakesthatwejudgeitandacouple

suchinstancescanshatterpeople’sconfidence.Anxietyisakindofcognitiveload,

andalittledoubtaboutwhetherasystemisgoingtodotherightthingisenoughto

turnaUXthat’srightmostofthetimeintoonethat’smoretroublethanit’sworth.

Whenthathappens,you’vemorethanlikelylostyourcustomer.

Unfortunately,soonerthanwethink, suchinaccuratepredictivebehaviorisn’tgoing

tobeanisolatedincident.Soonwe’regoingtohave100connecteddevices

simultaneouslyactingonpredictionsaboutus.Ifeachis99%accurate,thenoneis

alwayswrong.Sotheproblem is:Howcanyoudesignauserexperiencetomakea

devicestillfunctional,stillvaluable,stillfun,evenwhenit’sspewingjunkbehavior?

Howcanyoudesignforuncertainty?

Photo CCBY2.0photo2011PopCultureGeektakenbyDougKline:

https://www.flickr.com/photos/popculturegeek/6300931073/

44

Page 46: The UX of Predictive Behavior for the IoT (2016: O'Reilly Designing for the IOT)

Thelastissuecomesasaresult oftheprevioustwo:control.Howcanwemaintain

somelevelofcontroloverthese devices,whentheirbehaviorisbydefinition

statisticalandunpredictable?

Ontheonehandyoucanmangleyourdevice’spredictivebehaviorbygivingittoo

muchdata.WhenIvisitedNestoncetheytoldmethatnoneoftheNestsintheir

officeworkedwellbecausethey’reconstantlyfiddlingwiththem.Inmachinelearning

thisiscalledovertraining.Theotherhand,ifIhavenodirectwaytocontrolitother

thanthroughmyownbehavior,howdoIadjustit?AmazonandNetflix’s

recommendationsystems,whichisakindofpredictiveanalyticssystem,giveyou

somecontextaboutwhytheyrecommendedsomething,butwhatdoIdowhenmy

onlyinterfaceisagardenhose?

45

Page 47: The UX of Predictive Behavior for the IoT (2016: O'Reilly Designing for the IOT)

Hereare7 patternsI’veobservedindevelopingpredictivesystemsthatIthinkmapto

theIoT.FormostoftheseI’mgoingtobeusingexamplesfromNestand

recommendersystemslikeAmazon’s,Google’sandNetflix’s.Recommendersystems

havebeenaroundformorethanadecadeandthey’vebeenextensivelystudied.The

moveintopredictivebehaviorisbuiltonacombinationofrecommendersystemsand

supervisorycontrol,soIrecommendnotreinventingthewheel,butlearningfrom

thosedisciplines.

46

Page 48: The UX of Predictive Behavior for the IoT (2016: O'Reilly Designing for the IOT)

To buildaneffectiveanticipatorymachinelearningsystem,youneedtoknowwhatto

anticipate,andtodothatyouneedtomakeamodelofwhatpeopleneed,valueand

desire.Simplyautomatingexistingactivitieswithoutunderstandingwhypeopledo

them,whattheirgoalsareindoingthem,missesthepointofcreatingvalue.

Predictabilityisveryvaluable,evenwhenthepredictabilityisinsomethingthat’s

flawed.Whenweincludeanticipatorybehaviorinanexperience,we’reessentially

tradingawayanincrediblyvaluablecommoditysothattradehadbetterbeworthit.

Toknowwhetherit’sworthit,weneedtohaveamodelofwhatpeoplevaluewhich

we’rereplacingoraugmenting.

47

Page 49: The UX of Predictive Behavior for the IoT (2016: O'Reilly Designing for the IOT)

Whatgoes intothatmentalmodel?

Therearelotsofwaystostructurehowyourepresentpeople’sviewoftheworld.It’s

asignificantfocusofcognitivescience,andIcan’tdoitjustice,buthere’sanicelistI

grabbedfromtheintelligentagentliterature.

Asadesigner,manyoftheseboildowntodecisions.Whatdecisionwillan

anticipatorysystemhelpsomeonemake?Whatdecisionswillitmakeonthat

person’sbehalf?Whataretheparametersofthatdecision?Forexample,ifIhada

real-timebloodglucosemonitorandinsulinpumpthatadjustedmybloodglucosein

realtime,whichofmydecisionswoulditmakeforme?Whichdecisionswouldittell

mehowtomake?Whichdecisionswoulditgivemeadviceabout?

Withoutaclearclearlyarticulatedstoryaboutwhatdecisionsasystemhelps

someonemake,Ibelieveyoudon’thaveaclearstoryaboutwhatvalueitbrings

them.Howdoyoufigureoutwhatthosedecisionsare?Youtalktopeople.User

research.Ethnography.Leavingtheoffice.

48

Page 50: The UX of Predictive Behavior for the IoT (2016: O'Reilly Designing for the IOT)

Oneofthegreatcliches inUXdesignisthesearchfordelight,suchastheseasonally

changingbackgroundsinGoogleCalendar.Mydefinitionfordelightisthatit’s

functionalitythatsubvertspeople’snear-termexpectations,butsupportstheirlong-

termneedsanddesires.Thisisparticularlyimportantindesigningpredictivesystems,

becauseifyousubvertexpectationsWITHOUTsupportingtheirneeds,youget

cognitivedissonanceandyouhaveviolatedtheirmentalmodel.

49

Page 51: The UX of Predictive Behavior for the IoT (2016: O'Reilly Designing for the IOT)

Becausemachinemeansyour toolsadapttoyouandlearnsfromyou,adaptivetoolsare

morelikeapprentices,ratherthanimplementsandouruseofthemismorelikea

conversationratherthanthanlineartooluse.Infact,IheardoneofNest’sUXdesignerssay

thatheconsideredusers’evolvingrelationshipstotheNestasaconversation.

Thisisespeciallyrelevantintheeraofchatbots andvoiceUI.Ifyoulistentoahuman

conversation,it’salmostneveralinear,straightforward,well-structuredprocess.Westop,

werephrase,weaskforcorrections,wetalkpasteachother,weinterrupt.Morelikelythan

not,thisishowapredictivemachinelearningsystemwillinteractwithpeople,fromwhomit

willwantguidance,confirmation,andwhowillaskitforrecommendationsorchangestoits

behavior.

Ethnomethdologists andconversationanalystshavebeenmodelinghowpeopletalktoeach

otherforabout40years,soI’mgoingtoborrowsomeoftheirconcepts.

• Sequenceorganizationisaboutorganizingactionintime.Whathappensfirst,what

happensnext?Howdothetwopartiesexpandonambiguity?Forexample,ifahome

securitysystemdecidesyou’renothome,itcantellyou“Iseeyou’redrivingawayfrom

home.I’mgoingtoturnallthealarmson.”Youcanthensay“Alloftheexceptfortheback

yard.”

• Turn-takingiscritical.Wedon’tjustsimplytaketurnswhentalking,wecontinuously

providefeedbackandcorrect.Wehaveexpectationsforwhoseturnisnextandwhat

they’resupposedtodo.“Ok,chair,I’msittinghere,nowit’syourturn.Confirmyouknow

I’mhere.Warnmeifyou’regoingtoadjust.”

• Repairisbacktracking,clarifying,continuingafteraninterruption,etc.Whathappens

whentheexpectedsequence,eitherfromtheperspectiveofthepersonortheservice,is

brokenandneedstobereconstructed?

50

Page 52: The UX of Predictive Behavior for the IoT (2016: O'Reilly Designing for the IOT)

Inadditiontoteachingapprentices aboutourneeds,wealsolearnfromapprentices

whattheircapabilitiesareandwhytheymadecertaindecisions,ratherthanothers,

whendoingthethingswetaughtthemtodo.Thisisbothapartofhowtheylearn

aboutusandhowwelearntoworkwiththemeffectively.TheBMWiDrive system

wasnotoriousforitsUI,whichdidn’ttellyouwhatitcouldorcouldn’tdo,andhowto

doit.Youhadaknobandthatwasbasicallyit.

HowdoIinterrogateanadaptivesystemtounderstandwhatitcando,andtoaskit

toexplainwhatitjustdid.

HowdoyouknowwhatSiriorGoogleNowhavelearnedtodo?Well,youusethe

app.Butwhataboutservicesforwhichyoudon’thaveadisplay?Chatbots todayare

essentiallycommandlineinterfaces.Theyknowspecificwordsandsequences,but

whatifthosecommandschangeovertime?Whatifthedevicelearnsnewthingsover

time?

51

Page 53: The UX of Predictive Behavior for the IoT (2016: O'Reilly Designing for the IOT)

Thenextpatternisthatyouneedauserstoryforeverystageofthemachinelearning

andpredictionprocess,evenforstepsthatseemsinvisible.Howwillyouincentivize

peopletoaddtheirbehaviordatatothesystematall?WhyshouldIuploadmycar’s

dashcam videotoyourtrafficpredictionsystemEVERYDAY?Howwillyou

communicateyou’reextractingfeatures?IlikethewaythatGooglespeechtotext

showsyoupartialphrasesasyou’respeakingintoit,andhowitcorrectsitself.That

smallbitoffeedbacktellspeopleit’spullinginformationoutandittrainsusershow

tomeetthealgorithmhalfway.Howdomachine-generatedclassificationscompareto

people’sorganizationofthesamephenomena?Howisacontextmodelpresentedto

endusersanddevelopers?Howwillyougetpeopletotrainitandtellyouwhenthe

modeliswrong?Doesthefinalbehavioractuallymatchtheirexpectation?

52

Page 54: The UX of Predictive Behavior for the IoT (2016: O'Reilly Designing for the IOT)

Sincepredictivesystemsareneitherconsistent, norarethereasonsfortheirbehavior

clear,thiscanbereallyconfusing.Thesamethingcanbehavedifferentlyinwhat

appeartobesimilarcircumstances.Ifweunderminepeople’sconfidenceinasystem

byviolatingtheirexpectations,they’relikelytobedisappointedandstopusingit.

Whenwe’redealingwithahuman orananimal,unpredictablebehaviorsare

expectedandtolerated,butthat’snotthecasewithcomputers.ApredictiveUX

needstodoistosetpeople’sexpectationsappropriately.Itneedstoexplain the

natureofthedevice, todescribeitistryingtopredict, thatit’stryingtoadapt,that

it’sgoingtosometimesbewrong,toexplainhowit’slearning,andhowlongit’lltake

beforeitcrossesoverfromcreatingmoretroublethanbenefit.

Recommendersystems,suchasGoogleNow,describewhyacertainkindofcontent

wasselected,andthatsetstheexpectationthatinthefuturethesystemwill

recommendotherthingsbasedonotherkindsofcontentyou’verequested.Nest’s

FAQkindofburiestheinformation,butitdoesexplainthatyoushouldn’texpectyour

thermostattomakeamodelofwhenyou’rehomeornotuntilit’sbeenoperatingfor

aweekorso.

53

Page 55: The UX of Predictive Behavior for the IoT (2016: O'Reilly Designing for the IOT)

Aboutten yearsagoTimo Arnall andhisstudentstriedtoaddressasimilarsetof

questionsaroundinteractionswithRFID-enableddevicesbycreatinganiconography

systemthatcommunicatedtopotentialusersthatthesedeviceshadfunctionality

thatwasinvisiblefromtheoutside.Perhapsweneedsomethinglikethisforbehavior

createdbypredictivebehavior?

54

Page 56: The UX of Predictive Behavior for the IoT (2016: O'Reilly Designing for the IOT)

Predictivebehavior,isallabouttime,aboutsequencesofactivities.Manypredictive

UXissues aroundexpectationsanduncertaintyhavetimeastheirbasis:whatwere

youexpectingtohappenandwhy.Ifitdidn’thappen,why?Ifsomethingelse

happened,orithappenedatanunexpectedtime,whydidthathappen?

Knowing thatadevicehasactedonyourbehalf,andthatit’sgoingtoact—andHOW

it’sgoingtoact—inthefutureisimportanttogivingpeopleamodelofhowit’s

working,settingtheirexpectations,reducingtheuncertainty.Nest,forexample,hasa

calendarofitsexpectedbehavior,anditshowsthatit’sactingonyourbehalfto

changethetemperature,andwhenyoucanexpectthattemperaturewillbereached.

55

Page 57: The UX of Predictive Behavior for the IoT (2016: O'Reilly Designing for the IOT)

Youhavetogivepeopleaclear waytoteachthesystemandtellitwhenitsmodelis

wrong.Statisticalsystems,bydefinition,don’thavesimplerulesthatcanbechanged.

Therearen’tobvious handlestoturnordialstoadjust,becauseeverythingis

probabilistic.Ifthemodelismadefromdatacollectedbyseveraldevices,which

deviceshouldIinteractwithtogetittochangeitsbehavior?GoogleNowasks

whetherIwantmoreinformationfromasiteIvisited,Amazon showsaexplanation

ofwhyitgavemeasuggestion.MappingthistotheconsumerIoT meanswaymore

explanationthanwe’recurrentlygetting,whichiseitherthatathinghashappened,

orithasn’t.

56

Page 58: The UX of Predictive Behavior for the IoT (2016: O'Reilly Designing for the IOT)

Finally,don’tautomate. Thesesystemsshouldn’ttrytoreplacepeople,buttosupport

them,toaugment andextenttheircapabilities,tohelpthembebetteratwhatthey

wanttodo,nottoreplacethem.

Forexample,EmberfromMeshfire, isamachinelearningassistantforsocialmedia

management.Itdoesn’ttrytoreplacethesocialmediamanager.Insteaditmanages

themediamanager’stodo list.Itaddsthingsthatitthinksaregoingtobeinteresting,

deletesoldthings,andreprioritizesthemanager’slistbasedonwhatitthinksis

important.Ithinkthisisagoodmodelforhowsuchsystemscanaddvaluetoa

person’sexperiencewithoutcreatingasituationwhererandom,unexplained

behaviorsconfusepeople,frustratethemandmakethemfeelpowerless.Emberisan

augmentationtothesocialmediamanager,ithelpsthatpersonfocusonwhat’s

importantsothattheycanbesmarterabouttheirdecisions.Itdoesn’ttrytobe

smarterthantheyare.HowcanourdevicesHELPus,ratherthantryingtoreplaceus?

57

Page 59: The UX of Predictive Behavior for the IoT (2016: O'Reilly Designing for the IOT)

Finally,anantipattern:makingpeople doallofthetraining,askingthemtoidentify

whetherabehaviorisappropriateornot,shouldbedoneselectivelyand

infrequently.Yes,itwillreallyhelpyoursupervisedmodel’saccuracytohavepeople

identifythecorrectpositivesfromthefalsepositives,butunlessyou’repayingthese

people,it’sincrediblyannoyingtohavecustomersdoitallthetime.LastFridayone

consumerIoT productwithamachinelearningsystemI’mplayingwithaskedmeto

classifyitsoutputat1:11PM,thenagainat1:26,andagainat1:47andagainand

again.Ithinkitwasonroughlyten-minutesensingcycle,andateverycycleittriedto

makeadecision,andaskedmetoverifyit.I’msureit’sstilldoingit,butIturnedoff

allnotificationsfromit,andnowI’mconsideringturningitoffentirely.Peoplewill

sometimeswillinglyactassensorsandactuatorsforyoursystem,butbecausethey

arenotmachines,theywillnotdoitallthetimeandyou’rejustgoingtohavetofind

abetterwaytotrainyourmodel.

58

Page 60: The UX of Predictive Behavior for the IoT (2016: O'Reilly Designing for the IOT)

Finally,formetheIoT isnotaboutthethings,buttheexperiencecreatedby the

servicesforwhichthethings areavatars.

59

Page 61: The UX of Predictive Behavior for the IoT (2016: O'Reilly Designing for the IOT)

Ultimatelyweareusingthesetoolstoextendourcapabilities,tousethedigitalworld

asanextensionofourminds.Todothatwellwehavetorespectthatasinteresting

andpowerfulasthesetechnologiesare,theyarestillintheirinfancy,andourjobas

entrepreneurs,developersanddesignerswillbetocreatesystems,services,thathelp

people,ratherthanaddingextraworkinthenameofsimplisticautomation.Whatwe

wanttocreateisasymbioticrelationshipwherewe,andourpredictivesystems,work

togethertocreateaworldthatprovidesthemostvalue,fortheleastcost,forthe

mostpeople,forthelongesttime.

Wearecurrentlyshovelingourolddevicesintothisnewmedium.Wehavenotyet

figuredoutwhattheessentialcapabilitiesofthisnewmediumare.

LiteralMcLuhanquotation:"Thecontentofthepressisliterarystatement,asthe

contentofthebookisspeech,andthecontentofthemovieisthenovel."

60

Page 62: The UX of Predictive Behavior for the IoT (2016: O'Reilly Designing for the IOT)

Thankyou.

61