Download Part 4 Modeling Profitability Instead of Default.txt...
Description
Modeling Profitability Instead of Default Modeling Profitability Level as a Continuous Output (Instead of Binary Classification Default/No Default) Introduction Bot your o!n "odel and te forecast based on #ggertopia scores are binary classifications classifications$ $ tey forecast forecast one of %ust t!o outco"es$ outco"es$ � Default� or � No Default& Default&� 'our boss is interested in te idea tat it "igt be preferable instead to "odel and forecast profits and losses as continuous values using a a "ultivariate linear regression "odel on te sa"e si input variables& *is idea as arisen because te ban+ as been revie!ing individual profit and loss nu"bers for eac custo"er over te tree,year period and as "ade an interesting discovery$ so"e defaulting custo"ers carried so "uc debt for so long and paid so "uc interest on it tat tey !ere profitable for te ban+ even toug tey defaulted- Many custo"ers !o see" to ave ris+y spending beaviors are also a"ong te "ost profitable for a lending business& .nd at te opposite etre"ecusto"ers !o al!ays paid off teir cards in full eac "ont never defaulted but !ere not very profitable$ te ban+ barely barely bro+e bro+e even even or even even lost lost "oney "oney on its� safest safest� borro!e borro!ers& rs& 'our boss as+s as+s you to forecast forecast eac applicant applicant� s epected profitabi profitability lity in dollarsbefore deciding !eter or not to issue te" a credit card& e !ants to +no! o! reliable tis type of forecast !ould be$ !at is te range above and belo! te point esti"ate tat !ill be correct 012 of te ti"e3 .ltoug it "igt be possible to co"bine te si inputs in oter !ays in te interests of ti"e and focusing on te +ey learning ob%ectives !e !ill use only a si"ple linear co"bination of te si input variables for Part 4 of tis Pro%ect& ('ou sould not include te #ggertopia 5cores as an input variable)& 6uestion 7 is about te coefficie coefficients nts or or � betas� used to co"bine co"bine te standard standardi8ed i8ed inputs to get te best,fit,line on standardi8ed outputs on te *raining 5et& 9e ten use tose fied betas to "easure te observed residual error of te "odel on te *est 5et& 6uestions : troug ; concern te forecasts on te *est 5et& 6uestions < troug 77 loo+ at te *raining 5et results so tat tey can be co"pared (for possible over,fitting) against te *est 5et =esults& 6uestions 7: troug 74 are about te uncertainty tat re"ains in a ne! individual forecast of profitability& >se te te #cel #cel � Linest� function function on te si si inputs inputs and and profitabil profitability ity output output on te te :11 *raining *raining 5et applican applicants ts to calculate calculate te te coefficient coefficients s (te (te � betas� ) tat tat result result in te best,fit line& 6uestion$ Do you feel prepared to ta+e tis ?ui83 'es
r
6uestion$ 6uestion$ 9at 9at are your values for eac .ge
�
beta� on te te *raining *raining 5et3
'ears at current e"ployer 'ears at current address Inco"e over te past year Current credit card debt Current auto"obile debt &17 &70 ,&1
Thank you for interesting in our services. We are a non-profit group that run this website to share documents. We need your help to maintenance this website.