Problem $2$ Given a data table below. Need to predict based on combination of indicators when it is viable to give a loan. Using entropy as the measure construct the first level of the DT$.$ Consider only multioutcome splits for nominal attributes and only binary splits for interval attributes.

$\backslash$table$[[$Customer$,$Savings,Assets,Income $($$$1000),$Risk?$],[1,$Med,high,$75,$Good$],[2,$Low,low,$50,$Bad$],[3,$High,med,$25,$Bad$],[4,$Med,med,$50,$Good$],[5,$Low,med,$100,$Good$],[6,$High,high,$25,$Good$],[7,$Low,low,$25,$Bad$],[8,$Med,med,$75,$Good$]]$

The results of the following intermediate steps must be given

Parent measure,

for each good attribute$/$split alternative show the following

$($I$)$ measure for each child

$($ii$)$ combined child measure

$($iii$)$ gain.

winning attribute $/$split combinations and it's gain.