Scribd
Upload
47 views3 pages

339 - DADMB End Term

This document contains an 8-question exam on the topic of data analytics for decision making in business. The questions cover topics such as: 1) Calculating entropy gain after splitting a dataset by a categorical variable. 2) Building a decision tree from output provided. 3) Generating decision rules based on information given. 4) Calculating gain in Gini index after splitting a node into two child nodes.

Uploaded by

raf
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
47 views3 pages

339 - DADMB End Term

This document contains an 8-question exam on the topic of data analytics for decision making in business. The questions cover topics such as: 1) Calculating entropy gain after splitting a dataset by a categorical variable. 2) Building a decision tree from output provided. 3) Generating decision rules based on information given. 4) Calculating gain in Gini index after splitting a node into two child nodes.

Uploaded by

raf
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 3

INDIAN INSTITUTE OF MANAGEMENT RANCHI

MBA Programme

END-TERM EXAMINATION

TITLE OF THE COURSE – Data Analytics for Decision Making in


Business

TERM:- End-Term (Open Book) Marks: 30

Time: 2 hrs

INSTRUCTIONS

1. Answer must be precise and to the point. Think and then write

2. Write your answer as per given question sequence

3. Show each step of the calculation

Q1)

The following table provides information about six cars.

Predictors Response
Car ID Age Car Type Risk
1 25 F L
2 20 V H
3 25 F L
4 45 S H
5 20 F H
6 25 S H

Age: numeric variable


Car type: categorical variable with three classes {Fancy (F), SUV(S), Vintage(V)}
Driver classification: Response variable with two classes (High (H), Low (L)}

1
An analyst wants to split the response variable based on Car Type as shown below.

Calculate the entropy gain after a split by Car Type = Fancy of the above database.
[5]

Q2)

A data set has 81 observations and 4 variables on children who have had corrective
spinal surgery. The variables description are given below.

Age: in months
Number: the number of vertebrae involved
Start: the number of the first (topmost) vertebra operated on.
Disease (response variable): It is a factor with two levels absent or present. Present
indicates a type of deformation observed after the surgical operation.

An analyst got the following output using R software:

n= 81

node), split, n, loss, yval, (yprob)


* denotes terminal node

1) root 81 17 absent (0.79012346 0.20987654)


2) Start>=8.5 62 6 absent (0.90322581 0.09677419)
4) Start>=14.5 29 0 absent (1.00000000 0.00000000) *
5) Start< 14.5 33 6 absent (0.81818182 0.18181818)
10) Age< 55 12 0 absent (1.00000000 0.00000000) *
11) Age>=55 21 6 absent (0.71428571 0.28571429)
22) Age>=111 14 2 absent (0.85714286 0.14285714) *
23) Age< 111 7 3 present (0.42857143 0.57142857) *
3) Start< 8.5 19 8 present (0.42105263 0.57894737) *

Build the decision tree using the above output. [5]

Q3)
Generates decision rules based on the information provided in question Q4 [5]

2
Q4)

Consider a node has two response classes, success and failure. 60% is success and 40%
is failure. This node is split into two child nodes. The left child node has 30%
observations of parent node and right child node has 70%. The left child node has 20%
success and rest are failure. The right child node has 75% success and rest failure. Find
out gain in Gini index. [3]

Q5)
For a classification problem with two classes, the proportion of positives at a node is
30%. Determine the value of Gini index at the node. [3]

Q6)
 P(Y  1) 
In a binary logistic regression, the logit function is ln   =  4 +0.25 X . Then
 1  P( Y  1) 
 P ( Y  0) 
determine the equation for logit function ln   ? [3]
 1  P ( Y  0) 

Q7)

We have discussed a case study “Breaking Barriers: Micro Mortgage Analytics”. In


reference to this case study, explain how cost based classification is used to determine
cut-off probability. [3]

Q8)

How conjoint analysis help us for pricing research? Write your answer in brief.
[3]

You might also like