1 / 12100%
FINALf PROJECTf f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f
f f f f f 1
Finalf Projectf Report
Decemberf 16,2023
FINALf PROJECTf f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f
f f f f f 2
Introduction/f Problemf area
Thef marketingf initiativesf byf businessesf takef intof considerationf allf kindsf off customerf preferencesf
whilef creatingf customerf profiles.f Thef customerf preferencesf givef anf insightf intof theirf likingsf andf
thef offeringsf thatf theyf willf probablyf purchase.f
Inf thisf projectf wef considerf dataf setf fromf af f bankf whof plansf tof introducef af newf productf inf thef
marketf whichf isf calledf thef ‘Personalf Equityf Plan.’f Thef bankf engagedf withf itsf customersf viaf
diversef communicationf channelsf sof thatf thef newf productf couldf bef sold.Thef bankf wansf tof identifyf
thef factorsf thatf drivef thef salef off newf product.Wef setupf hypothesesf andf determinef relationsf
betweenf variousf variablesf .Wef shallf bef usingf Rf programmingf languagef forf ourf analysisf whichf isf
anf openf sourcef andf availablef online.
Hypotheses
Thef mainf hypothesesf wef aref testingf inf thisf f analysisf are:
f ‘Personalf Equityf Plan’f andf thef typef off customerf bankf accountf havef af directf relation
Gender,f marriage,f car,f loan,f region,f numberf off kids,f etc.,f havef af directf impactf onf thef
purchasef off thef ‘Personalf Equityf Plan’f offeringf f f
Dataf Load
Forf conductingf thef in-depthf analysis,f dataf hasf beenf gatheredf fromf GitHub’sf WEKAf Learningf
databasef (Bluenex,f 2021).f
Thef dataf wasf loadedf inf thef variablef bank,f andf itf wasf readf inf thef formf off thef csvf file.f Thef read.csvf
commandf wasf usedf forf thisf purpose.f
FINALf PROJECTf f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f
f f f f f 3
bankf <-f read.csv(file="bank-data.csv",f head=TRUE,f sep=",")f
Descriptionf off data
Inf thef marketingf context,f bankf dataf setf isf consideredf tof bef highlyf beneficialf forf marketingf
departmentsf off varyingf financialf institutions.f Itf isf essentialf tof maintainf allf thef relevantf customerf
recordsf startingf fromf theirf demographicsf tof thef numberf off accountsf thatf theyf hold.f Whenf af newf
offeringf isf introducedf byf af financialf institutionf inf thef market,f thef availabilityf off bankf dataf canf
assistf inf determiningf thef responsef off thef customers,f includingf thef onesf whof purchasef thef newf
productf (Bluenex,f 2021).f Thef informationf canf helpf tof uncoverf meaningf relatingf tof howf
consumersf behavef inf thef contextf off thef newf product.f Basedf onf thef pastf experiencef off thef financialf
institution,f thef managersf canf ascertainf howf tof deployf appropriatef dataf miningf approachesf andf
techniquesf thatf canf helpf inf creatingf properf customerf profilef models.f Af diversef rangef off fieldsf isf
integratedf intof bankf data,f suchf asf id,f gender,f age,f incomef level,f region,f maritalf status,f car,f
children,f mortgage,f thef typef off accountf andf PEP.f
Thef detailedf customerf recordsf canf bef usedf byf thef marketingf departmentsf off banksf forf thef purposef
off acquiringf potentialf customers.f Thef dataf canf helpf thef financialf institutionf tof targetf potentialf
customers.f Thef fundamentalf aimf off utilizingf bankf dataf isf tof determinef whetherf af customerf isf
likelyf tof bef interestedf inf availingf af specificf financialf productf orf not.f Thef financialf productf
typicallyf encompassesf thef termf depositsf off banks.f
Agef f Thef ’age’f fieldf capturesf thef agef off customersf inf numericalf form.f Itf isf vitalf informationf thatf
canf bef usedf byf thef marketingf department.f Forf instance,f iff thef customerf isf belowf 65f years,f theref isf
af highf possibilityf thatf hef orf shef willf choosef termf deposits.f Onf thef contrary,f iff af customerf isf overf
65f years,f hef isf unlikelyf tof choosef termf deposits.f Thef agef off customersf canf alsof enablef financialf
FINALf PROJECTf f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f
f f f f f 4
institutionsf tof makef thef decisionf onf whetherf lifef insurancef plansf orf retirementf plansf canf bef
offeredf tof elderlyf customers.f influencef f f f
Regionf f Thef ‘region’f fieldf informsf thef marketingf departmentf aboutf thef locationf inf whichf thef
customersf stayf asf wellf asf theirf livingf conditions.f Basedf onf locationf inf whichf theyf residef i.e.,f ruralf
regionsf orf urbanf regions,f financialf institutionsf andf banksf canf offerf relevantf andf suitablef financialf
productsf andf servicesf tof potentialf customers.f f f
Incomef levelf f Thef incomef levelf off thef customers,f isf anotherf vitalf fieldf thatf canf givef thef
marketingf departmentf off banksf valuablef insights.f Itf basicallyf givesf af glimpsef intof thef financialf
healthf andf positionf off thef customers.f Thef informationf canf enablef thef marketingf departmentf off
banksf tof ascertainf thef suitablef financialf offeringsf thatf canf bef madef forf consumers.f Thef
informationf canf helpf banksf tof fulfillf thef needsf off consumersf whilef meetingf theirf businessf goalsf
andf objectives.f Thus,f af win-winf situationf canf bef created.f Thef levelf off incomef off thef customersf
canf helpf banksf tof ascertainf whetherf af customerf isf inf needf off loanf productsf orf not.f
Maritalf statusf andf childrenf f Detailsf pertainingf tof maritalf statusf andf thef numberf off childrenf thatf
af marriedf couplef hasf isf anf importantf fieldf thatf canf bef usedf byf thef marketingf departmentf off banks.f
Forf example,f thef possibilityf off marriedf customersf purchasingf financialf products,f suchf asf
insurancef products,f isf higherf asf comparedf tof unmarriedf customers.f Thisf isf becausef theyf mayf
purchasef thef financialf offeringsf forf theirf spousesf orf forf theirf children.f Byf knowingf whetherf bankf
customersf aref marriedf orf not,f itf isf possiblef forf financialf institutionsf tof understandf theirf needsf inf af
betterf wayf andf offerf thef rightf kindf off productsf andf servicesf thatf canf satisfyf theirf needs.f
Accountf typef andf thef numberf off accountsf f Marketingf departmentsf off financialf institutionsf canf
alsof derivef richf insightsf fromf detailsf suchf asf thef accountf detailsf off theirf customers.f Typically,f
FINALf PROJECTf f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f
f f f f f 5
individualsf whof workf asf professionalsf maintainf savingsf accounts.f Onf thef otherf hand,f individualsf
whof aref intof businessf maintainf currentf accountsf (Bankf Marketingf Dataf Set,f 2019).f Basedf onf
accountf details,f marketingf departmentsf aref ablef tof getf anf insightf intof thef financialf statusf off theirf
customers.f Itf canf helpf tof makef suitablef offeringsf tof them.f Forf example,f inf casef af customerf ownsf af
car,f af bankf canf offerf himf vehiclef insurance.f
Eachf off thef fieldsf relatingf tof thef bankf setf givesf valuablef insightf asf wellf asf information.f Thef
informationf canf bef usedf byf banksf andf financialf institutionsf tof makef thef bestf offersf tof thef
customersf andf fulfillf theirf unfulfilledf needsf andf wants.f Inf thef capturedf dataset,f theref aref af totalf off
600f observationsf andf 12f variables:
id,f age,f sex,f region,f income,f married,f children,f car,f save_act,f current_act,f mortgagef andf PEPf
(dependentf variable).
f
Fromf thef availablef data,f itf canf bef observedf thatf thef income,f age,f andf thef numberf off childrenf
categoriesf aref inf numericalf form.f Thef otherf elementsf aref factorf variables.f Thef summaryf commandf
wasf runf tof checkf thef summaryf forf thef dataf set.f Theref isf af balancef betweenf malesf andf females.f Af
considerablef numberf off customersf havef respondedf ‘No’f forf thef newf PEPf product.f Furthermore,f itf
canf alsof bef observedf thatf af largef numberf off respondentsf aref married.
FINALf PROJECTf f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f
f f f f f 6
f f
Preprocessingf off dataf
Inf thef dataf analysisf process,f preprocessingf off dataf isf af vitalf component.f Thisf activityf mustf bef
carriedf outf sincef itf canf helpf tof eliminatef irrelevantf variables.f Itf canf alsof helpf tof processf thef
variablesf thatf aref missing.f Initially,f thef idf variablef wasf removedf sincef itf wasf justf beingf usedf forf
identifyingf thef customersf off thef bank.f Itf didf notf servef anyf purposef inf thef dataf analysisf processf andf
sof itf wasf removed.f
bankf <-f bank[,-1]
Af summaryf commandf hadf beenf runf atf anf earlierf stagef inf thef dataf descriptionf section.f Nof
missingf valuesf (NA)f weref found.f Af boxf plotf highlightingf incomef inf relationf tof thef PEPf
variablef hasf beenf constructed.f Itf canf bef observedf thatf theref existf af fewf pointsf belongingf tof
thef Nof category,f andf theyf aref abovef IQR.f Butf whenf thef incomef boxf plotf hasf beenf
constructedf alone,f itf canf bef observedf thatf theref existf nof outliers.f Thef incomef valuesf thatf actf
asf outliersf havef beenf removed.f
FINALf PROJECTf f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f
f f f f f 7
Inf thef nextf stagef off dataf analysis,f thef outliersf inf thef agef categoryf weref checked,f andf itf wasf
identifiedf thatf theref weref nof outliers.f
FINALf PROJECTf f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f
f f f f f 8
Thef numericf variablesf weref furtherf discretizedf sof thatf thef apriorif algorithmf couldf bef usedf forf thef
analysisf process.f
Inferences
Inf thef specificf studyf context,exploratoryf analysisf hasf helpedf tof getf valuablef insightsf relatingf tof
thef variablesf andf locatef vitalf associationsf betweenf them.
Initially,f thef graphf relatingf tof agef versusf thef numberf off customersf wasf thoroughlyf checked.f Thef
chieff observationf thatf wasf madef wasf thatf thef agef off thef customersf wasf evenlyf distributedf
(Bedfordf &f Malmi,f 2015).f
f
Thef associationf betweenf genderf andf regionf wasf alsof checkedf withf respectf tof thef ‘Personalf Equityf
Plan’f loanf productf thatf wasf beingf offeredf byf thef bank.f
FINALf PROJECTf f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f
f f f f f 9
Itf hasf beenf identifiedf thatf genderf doesf notf havef anyf kindf off impactf onf thef preferencef relatingf tof
thef newf PEPf product.f Furthermore,f itf hasf alsof beenf revealedf thatf inf thef suburbanf region,f overf 50f
%f off individualsf whof hadf beenf approachedf showedf af positivef responsef towardsf thef purchasef off
thef newf PEPf product.f
Whilef checkingf thef relationshipf betweenf thef typef off accountf (savingsf orf current)f tof purchasef
PEP,f itf wasf foundf thatf theref existedf nof association.f Butf customersf withf af savingsf orf currentf
accountf havef takenf PEPf asf comparedf tof individualsf whof dof notf havef suchf accounts.
FINALf PROJECTf f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f
f f f f f 10
Thef associationf betweenf carf andf PEPf purchasingf intentionf wasf identified.f Thef associationf
betweenf thef childrenf numberf andf purchasingf PEPf wasf ascertained.f Itf hasf beenf ascertainedf thatf
owningf af carf doesf notf impactf thef decisionf tof purchasef PEP.f Inf regardsf tof children,f familiesf withf
nof childrenf orf 1f childf aref moref likelyf tof buyf PEPf asf comparedf tof familiesf withf 2f orf moref kids.f f
Thef effectf off incomef onf thef purchasef off thef PEPf productf hasf alsof beenf ascertained.f Itf canf bef
observedf thatf forf familiesf withf lowerf income,f theref existsf nof interlinef betweenf theirf incomef andf
intentionf tof purchasef PEP.f Butf asf incomef rises,f thef intentionf tof purchasef PEPf alsof increases.f
Duringf preprocessingf off data,f itf wasf identifiedf thatf higherf agef andf incomef aref associatedf withf
higherf purchasef intentionf off PEP.
FINALf PROJECTf f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f
f f f f f 11
Thef associationf betweenf marriedf statusf andf PEPf purchasef showsf thatf 50f %f off unmarriedf
customersf purchasedf PEP,f whereasf lessf thanf 50f %f off marriedf customersf purchasedf PEP.
Thef associationf betweenf thef numberf off kidsf andf PEPf purchasef intentionf shownf belowf showsf thatf
whenf thef numberf off childrenf isf one,f customersf buyf PEPf asf itf isf consideredf anf investment.f Butf
whenf thef numberf off childrenf increases,f thef intentionf tof buyf PEPf diminishes.f
FINALf PROJECTf f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f
f f f f f 12
References
Bluenex.f (2021).f WekaLearningDataset/bank-data.csvf atf masterf ·f bluenex/wekalearningdataset.f
GitHub.f Retrievedf Decemberf 16,f 2022,f fromf
https://github.com/bluenex/WekaLearningDataset/blob/master/bank/bank-data.csvf
f
Students also viewed