You have been hired by a non$-$profit organization that wishes to develop predictive models to improve the cost$-$effectiveness of their direct marketing campaigns to prior donors. According to their recent records, the typical overall response rate is approximately $10\%.$ Out of those who respond and donate to the mailing, the average donation is $$14\mathrm{.}50.$ Each mailing costs $$2\mathrm{.}00$ to produce and send; the mailing includes a gift of personalized address labels. It is not cost$-$effective to mail everyone because the expected profit from each mailing is $14\mathrm{.}50$ x $10\%2=-$$$0\mathrm{.}55.$

Your client would like to develop a classification model using data from the most recent campaign that can effectively capture likely donors so that the expected net profit is maximized $($i$.$e$.,$ ideally maximize the number of donors who receive a flyer and minimize the recipients who are non$-$donors$).$ Note that weighted sampling has been used, over$-$representing the responders so that the sample have approximately $50\%$ of either of donors or non$-$donors.

Your client would also like predict expected gift amounts from donors.

Introduction$/$Business understanding$/$Analytics questions: Describe the business opportunities that the data present and formulate relevant business questions. If a business question is not appropriate for the data, just state the analytics questions of interest that your analysis will address.

Data Dictionary

$$ id number $[$Do NOT use this as a predictor variable in any models$]$

$$ region: five geographic regions including ter$1,$ ter$2,$ ter$3,$ ter$4,$ ter$5$

$$ ownd: $(1=$ homeowner, $0=$ not a homeowner$)$

$$ kids: Number of children

$$ inc: Household income $(7$ categories$)$

$$ sex: Gender $(0=$ Male, $1=$ Female$)$

$$ wlth: Wealth Rating $($Wealth rating uses median family income and population statistics from each area to index relative wealth within each state. The segments are denoted $0-9,$ with $9$ being the highest wealth group and $0$ being the lowest.$)$

$$ hv: Average Home Value in potential donor's neighborhood in $ thousands

$$ incmed: Median Family Income in potential donor's neighborhood in $ thousands

$$ incavg: Average Family Income in potential donor's neighborhood in $ thousands

$$ low: Percent categorized as $$low income$$ in potential donor's neighborhood

$$ npro: Lifetime number of promotions received to date

$$ gifdol: Dollar amount of lifetime gifts to date

$$ gifl: Dollar amount of largest gift to date

$$ gifr: Dollar amount of most recent gift

$$ mdon: Number of months since last donation

$$ lag: Number of months between first and second gift

$$ gifa: Average dollar amount of gifts to date

$$ donr: Classification Response Variable $(1=$ Donor, $0=$ Non$-$donor$)$

$$ damt: Prediction Response Variable $($Donation Amount in $$).$

Note that the donr and damt variables are set to missing for the score data.