CBSE Class 12 Question Paper 2026 Solution Data Science

FOR CBSE CLASS 12 EXAM PREPARATION

CBSE Class 12 2026
Question Paper
Solution · Data Science
EXAM YEAR TYPE SUBJECT

CBSE Class 12 2026 Question Paper Solution Data Science

Notes · Sample Papers · Previous Year Papers · Mock Tests

. c s e
m a
se l
Marking SchemeCBSE Class 12 2026 Question Paper Solution Data Science

ag
Strictly Confidential
(For Internal and Restricted use only)
Senior Secondary School Examination, 2026 (XIIth)
SUBJECT NAME : Data Science (Q.P. CODE 844/368)

General Instructions: -
1 The CBSE has decided to introduce On Screen Marking (OSM) for the evaluation of
Class XII answer Book with the 2026 Examination.
2 You are aware that evaluation is the most important process in the actual and
m
.co
correct assessment of the candidates. A small mistake in evaluation may lead to
m
.co m
serious problems which may affect the future of the candidates, education system
and teaching profession. To avoid mistakes, it is requested that before starting
m s e
e policy is a confidential policy as it is related to the confidentialitygla
evaluation, you must read and understand the spot evaluation guidelines carefully.
s
3
la examinations conducted, evaluation done and several other aspects.
“Evaluation
ofgthe a
aIts leakage to public in any manner could lead to derailment of the
examination system and affect the life and future of millions of candidates.
Sharing this policy/document to anyone, publishing in any magazine and
printing in Newspaper/Website, etc. may invite action under various rules of
the Board and IPC.”
4 Evaluation is to be done as per instructions provided in the Marking Scheme. It
should not be done according to one‟s own interpretation or any other
consideration. Marking Scheme should be strictly adhered to and religiously

m
followed. However, while evaluating, answers which are based on latest

.co
information or knowledge and/or are innovative, they may be assessed for
their correctness otherwise and due marks be awarded to them. In Class-XII,
e m
while evaluating two competency-based questions, please try to understand

l as
given answer and even if reply is not from marking scheme but correct

5 ag
competency is enumerated by the candidate, due marks should be awarded.
The Marking scheme carries only suggested value points for the answers.
These are in the nature of Guidelines only and do not constitute the complete
answer. The students can have their own expression and if the expression is
correct, the due marks should be awarded accordingly.
6 The Head-Examiner must go through the first five answer books evaluated by each
evaluator on the first day, to ensure that evaluation has been carried out as per the
instructions given in the Marking Scheme. If there is any variation, the same should
be zero after deliberation and discussion. The remaining answer books meant for

m
evaluation shall be given only after ensuring that there is no significant variation in

.co
the marking of individual evaluators.
m
.co
Evaluators will mark ( √ ) wherever answer is correct. For wrong answer CROSS „X‟
m
7

m
be marked. Evaluators will not put right (✓) while evaluating which gives an
s e
s e impression that answer is correct and no marks are awarded. This is most
l a
l a ag
common mistake which evaluators are committing.

ag 8 If a question has parts, please award marks on the right-hand side for each part in
the OSM Portal. Marks awarded for different parts of the question will be totaled up
by the OSM System.
9 If a question does not have any parts, marks must be awarded in the left-hand
margin in the OSM Portal. This may also be followed strictly.

om .
MS-Data Science/844/368 1 P3680844

.c e m
m
For more Question Papers, Sample Papers, Notes & Syllabus visit
as
Page 1 of 22

10 No marks to be deducted for the cumulative effect of an error. It should be
penalized only once.
11 A full scale of marks __________ (example 0 to 80/70/60/50/40/30 marks as given
in Question Paper) has to be used. Please do not hesitate to award full marks if the
answer deserves it.
12 Every examiner has to necessarily do evaluation work for full working hours i.e., 8
hours every day and evaluate 20 answer books per day in main subjects and 25
answer books per day in other subjects (Details are given in Spot Guidelines).This
is in view of the reduced syllabus and number of questions in question paper.
13 Ensure that you do not make the following common types of errors committed by
the Examiner in the past :-
● Answers marked as correct, but marks not awarded. (Ensure that the right tick
mark is correctly and clearly indicated. It should merely be a line. Same is with
the X for incorrect answer.)
● Half or a part of answer marked correct and the rest as wrong, but no marks
awarded.
14 While evaluating the answer books if the answer is found to be totally incorrect, it
should be marked as cross (X) and awarded zero (0) Marks.
15 The Examiners should acquaint themselves with the guidelines given in the
“Guidelines for Spot Evaluation” before starting the actual evaluation.
16 The candidates are entitled to obtain photocopy of the Answer Book on request on
payment of the prescribed processing fee. All Examiners/Additional Head
Examiners/Head Examiners are once again reminded that they must ensure that
evaluation is carried out strictly as per value points for each answer as given in the
Marking Scheme.
17 If a candidate attempts both alternatives/options in a question where only one
option/ alternative is required to be attempted, the Evaluator shall award
marks in both the options. The system will take the higher of two scores and
disregard the other response.
18 In a question having two options/alternatives, if a candidate has attempted
only one, then the evaluator shall mark “NA” (Not attempted) against the
option that has not been attempted by the candidate.

MS-Data Science/844/368 2 P3680844

For more Question Papers, Sample Papers, Notes & Syllabus visit Page 2 of 22

. c s e
m a
se l

ag
MARKING SCHEME
Data Science (Subject Code-844)
(PAPER CODE : 368) (P3680844)

Q.No. EXPECTED OUTCOMES/VALUE POINTS Marks
SECTION – A
Answer any 4 out of the given 6 questions on Employability
m
.co
1.
Skills.
o m m
c
योजगाय कौशर. ऩय ददए गए 6 ्ቚश्नों भें से ककनहहॊ 4 के उ्ቈय दहजजए।
s e
e m la
(C) a15 s U-1 Pg-10 ag 1
gl
(i)

(ii)
aIncentives or external rewards U-2 Pg-24 1

(iii) (A) Extroverts U-2 Pg-33 1

(iv) (B) Click the cell, type the data, and press enter. U- 3 Pg-44 1

(v) (C) Social U-4 Pg-84 1

m
.co
(vi) Source of origin and type of waste U-5 Pg-117 1

2.
s
Answer any 5 out of the given 6 questions.em (5x1=5)
la दहजजए।
ददए गए 6 ्ቚश्नों भें से ककनहहॊ 5 के उ्ቈय
g
a
(i) Which data privacy legislation specifically deals with how Chapter-1 1
websites and online companies collect data from children under Page-3
13 years of age ?
(A) GDPR
(B) HIPAA
(C) CCPA
m
m .co
.co
(D) COPPA

e m
कौन सा डेटा गोऩनीमता कानून (data privacy legislation) विशेष रूऩ

as e m las
से इस फात से सॊफॊधधत है कक िेफसाइटें औय ऑनराइन कॊऩननमाॉg13
g l िषष से कभ उ्቞ के फच्चों से डेटा कैसे एक्ቔ कयती हैं ?
a
a
(A) GDPR
(B) HIPAA
(C) CCPA
(D) COPPA

om .
MS-Data Science/844/368 3 P3680844

.c e m
m
For more Question Papers, Sample Papers, Notes & Syllabus visit
as
Page 3 of 22

(i) Answer : (D) COPPA
(ii) Bijoy is performing Exploratory Data Analysis (EDA) on a Chapter-2 1
dataset, which contains only one variable, Math_Score. He Page-8
wants to check if there are any outliers in this variable. Which
graph is most suitable for this purpose ?
(A) Histogram
(B) Box Plot
(C) Bar Chart
(D) Pie Chart
बफजॉम एक डेटासेट (dataset) ऩय Exploratory Data Analysis
(EDA) कय यहा है , जजसभें केिर एक चय (variable), Math_Score
है । िह मह जाॉच कयना चाहता है कक क्मा इस चय भें कोई आउटरामय
(outlier) हैं। इस उद्दे श्म के लरए कौन सा ्ቇाप सफसे उऩमुक्त है ?

(A) दहस्टो्ቇाभ (Histogram)

(B) फॉक्स प्रॉट (Box Plot)

(C) फाय चाटष (Bar Chart)

(D) ऩाई चाटष (Pie Chart)

(ii) Answer : (B) Box Plot
(iii) What is the primary function of each internal node in a Decision Chapter-3 1
Tree ? Page-13
(A) It holds the final class label.
(B) It represents the outcome of a test.
(C) It denotes a question on choosing a particular class.
(D) It represents the probability of success for a decision.
एक डडसीजन ्቏ह भें ्ቚत्मेक आॊतरयक नोड (internal node) का
्ቚाथलभक कामष क्मा है ?

(A) मह अॊनतभ क्रास रेफर (class label) को hold कयता है ।

(B) मह एक ऩयहऺण के ऩरयणाभ (outcome) को दशाषता है।

(C) मह ककसी विशेष क्रास (class) को चन
ु ने के ्ቚश्न को दशाषता
है ।

(D) मह एक ननणषम की सपरता की सॊबािना (probability) को
MS-Data Science/844/368 4 P3680844

For more Question Papers, Sample Papers, Notes & Syllabus visit Page 4 of 22

. c s e
m a
se l

ag
दशाषता है ।

(iii) Answer : (C) It denotes a question on choosing a particular
class.
(iv) What is the common effect of choosing a big value of k in the k- Chapter-4 1

m
NN algorithm ? Page-23

.co
(A) It increases the effect of outliers and makes the decision
m
.co m
surface more specific.

m
(B) It reduces the effect of outlier and causes the decision
s e
s e
surface to generalize.
g la
la
(C) It increases the memory efficiency of the algorithm.
g a
a
(D) It always improves prediction accuracy regardless of the
dataset.
k- NN एल्गोरयथभ (algorithm) भें k का एक फड़ा भान (value) चन ु ने
का साभानम ्ቚबाि क्मा होता है ?
(A) मह आउटरामय (outliers) के ्ቚबाि को फढ़ाता है औय ननणषम
सतह (decision surface) को अधधक विलशष्ट (specific) फनाता
है ।
m
(B) मह आउटरामय (outliers) के ्ቚबाि को कभ कयता है औय
.co
em
ननणषम सतह को साभानमीकृत (generalize) कयने का कायण
s
फनता है ।
g la
(C) मह एल्गोरयथभ की भेभa
ोयह दऺता (memory efficiency) को
फढ़ाता है ।
(D) मह डेटासेट (dataset) की ऩयिाह ककए हभेशा prediction
(ऩूिाषनुभान) सटहकता भें सुधाय कयता है ।
(iv) Answer : (B) It reduces the effect of outlier and causes the
decision surface to generalize.
m
om .co
(v) Consider the scatter plot shown below, that shows the Chapter-5 1
c m
m.
relationship between two variables, X and Y. The line marked as Page-34
L in the graph below is known as __________.
s e
s e l a
g l a ag
a

om .
MS-Data Science/844/368 5 P3680844

.c e m
m
For more Question Papers, Sample Papers, Notes & Syllabus visit
as
Page 5 of 22

(A) Line of Best Fit
(B) Line of Worst Fit
(C) Line of Median
(D) Line of Mode
नीचे ददखाए गए स्कैटय प्रॉट (scatter plot) ऩय विचाय कयें , जो दो
चय (variables), X औय Y के फीच सॊफॊध ददखाता है । नीचे ददए गए
्ቇाप भें L के रूऩ भें धचनहहत ये खा (line) को __________ के रूऩ भें
जाना जाता है ।
(A) Line of Best Fit
(B) Line of Worst Fit
(C) Line of Median
(D) Line of Mode
(v) Answer : (A) Line of Best Fit
(vi) What is the name of the process of dividing entire raw data into Chapter-7 1
several groups such that data points in one group are similar to Page-45
other data points in the same group but different from those in
other groups ?
(A) Supervised Learning
(B) Expectation-Maximization
(C) Clustering
(D) Anomaly detection
सॊऩूणष raw डेटा को कई सभूहों भें विबाजजत कयने की ्ቚकिमा को क्मा
कहा जाता है ताकक एक सभूह भें डेटा ऩॉइॊट (data points) उसी सभूह
के अनम डेटा ऩॉइट के सभान हों रेककन अनम सभूहों के डेटा ऩॉइॊट से
अरग हों ?
(A) सऩ
ु यिाइज्ड रननिंग (Supervised Learning)
(B) एक्सऩेक्टे शन-भैजक्सभाइज़ेशन (Expectation-Maximization)
(C) क्रस्टरयॊग (Clustering)
(D) विसॊगनत का ऩता रगाना (Anomaly detection )
(vi) Answer : (C) Clustering
3. Answer any 5 out of the given 6 questions. (5x1=5)
ददए गए 6 ्ቚश्नों भें से ककनहहॊ 5 के उ्ቈय दहजजए। (5x1=5)
(i) An admission office of a college uses an automated system to Chapter-1 1
pre-screen applications. The process is designed to automatically Page-2
filter out applicants who attended certain low-performing
schools, regardless of the individual student's grades or test
scores.
This automated filtering process violates which ethical
MS-Data Science/844/368 6 P3680844

For more Question Papers, Sample Papers, Notes & Syllabus visit Page 6 of 22

. c s e
m a
se l

guidelines ?
ag
(A) Security of Data
(B) Privacy of Data
(C) Non discrimination
(D) Openness
एक कॉरेज ्ቚिेश कामाषरम (admissions office) आिेदनों को ्ቚी -
स्िीन (pre-screen) कयने के लरए एक स्िचालरत ्ቚणारह का उऩमोग
m
c o m
कयता है । मह ्ቚकिमा व्मजक्तगत छा्ቔ के ्ቇेड मा टे स्ट स्कोय (test
m .co
. ककए बफना, कुछ कभ ्ቚदशषन िारे स्कूरों के
scores) की ऩयिाह
m s e
आिेदकोंs eको स्ित: रूऩ से किल्टय आउट (filter out) कयने के लरए g la
g la की गई है। मह स्ित: किल्टरयॊग ्ቚकिमा ककस नैनतक
डडज़ाइन
a
a
ददशाननदे श (ethical guidelines) का उल्रॊघन
कयती है ?
(A) Security of Data
(B) Privacy of Data
(C) Non discrimination
(D) Openness
m
.co
(i) Answer : (C) Non discrimination

m

s e
(ii)
g l a
A data analyst is working on a dataset. She notices that a
variable has some missing entries. What is the most appropriate
Chapter-2 1

a
Page-11
way(s) to handle these missing values during the data cleaning
process ?
(i) Leave the missing values as they are
(ii) Remove the row of the variable that is missing
(iii) Insert a value close to mean/mode of the variable that is
missing
(iv) Duplicate the missing entries
(v) Replace the missing values with negative numbers
m
m एक डेटा विश्रेषण (data analyst) एक डेटासेट ऩय काभ कय यहह है । .co
.co िह दे खती है कक एक चय (variable) भें कुछ ्ቚविजष्टमाॉ (entries) e m
s e m as
गामफ हैं। डेटा क्रहननॊग (data cleaning) ्ቚकिमा के दौयान इन gगlुभ
g l a a
भानों (missing values) को handle कयने का सफसे उऩमुक्त तयहका
a
क्मा है /हैं ?
(i) गुभ भानों को िैसे हह छोड़ दें
(ii) गुभ चय की ऩॊजक्त (row) को हटा दें
(iii) गभ
ु चय के भाध्म (mean)/ फहुरक (mode) के कयहफ एक भान

om .
MS-Data Science/844/368 7 P3680844

.c e m
m
For more Question Papers, Sample Papers, Notes & Syllabus visit
as
Page 7 of 22

insert कयें
(iv) गुभ ्ቚविजष्टमों की ्ቚनतलरवऩ (duplicate) फनाएॉ
(v) गभ
ु भानों को ऋणात्भक सॊख्माओॊ (negative numbers) से
फदर दें
Options :
(A) (i), (ii) and (iv)
(B) (ii) and (iii)
(C) (ii), (iii) and (v)
(D) (iii) and (iv)
(ii) Answer : (B) (ii) and (iii)
(iii) Sara is creating a decision tree to plan her weekend activities. Chapter-3 1
One of the decisions is whether to go hiking or stay home. If she Page-16,17
goes hiking, the weather could be sunny or rainy, but she isn't
sure which it will be. When representing the uncertain weather
outcome in her decision tree, what type of node should Sara
use ?
(A) Square node
(B) Circular node
(C) Triangular node
(D) Diamond node
साया अऩनी सप्ताहाॊत की गनतविधधमों की मोजना फनाने के लरए एक
डडसीजन ्቏ह फना यहह है । ननणषमों भें से एक मह है कक हाइककॊग
(hiking) के लरए जाना है मा घय ऩय यहना है । अगय िह हाइककॊग के
लरए जाती है , तो भौसभ धऩ
ू िारा मा फारयश िारा हो सकता है ,
रेककन िह ननजश्चत नहहॊ है कक क्मा होगा। डडसीजन ्቏ह भें uncertain
weather outcome को दशाषने के लरए, साया को ककस ्ቚकाय के नोड
(node) का उऩमोग कयना चादहए ?
(A) चौकोय नोड (Square node)
(B) गोराकाय नोड (Circular node)
(C) ब्ቔकोणीम नोड (Triangular node)
(D) डामभॊड नोड (Diamond node)
(iii) Answer : (B) Circular node
(iv) Which of the following describes the problem where the K-NN Chapter-4 1

MS-Data Science/844/368 8 P3680844

For more Question Papers, Sample Papers, Notes & Syllabus visit Page 8 of 22

. c s e
m a
se gl

a
algorithm struggles to predict the output of a new data point as Page-25
the number of input variables grows ?
(A) Imbalanced Data Problem
(B) No Training Step
(C) Sensitivity to Outliers
(D) Curse of Dimensionality
ननम्नलरखखत भें से कौन सी सभस्मा का िणषन कयता है जहाॉ इनऩुट
m
c o m
िैरयएफर (input variables) की सॊख्मा फढ़ने ऩय K-NN एल्गोरयथभ
m .co
एक नए डेट.ा ऩॉइॊट (data point) के आउटऩुट का ऩूिाषनुभान e
emकयने भें सॊघषष कयता है ? las
s
laImbalanced Data Problem
(prediction)
ag
a g
(A)
(B) No Training Step
(C) Sensitivity to Outliers
(D) Curse of Dimensionality
(iv) Answer : (D) Curse of Dimensionality
(v) The Root Mean Square Deviation is the square root of : Chapter-5 1
Page-35
(A) Mean of residuals
m
(B) Variance of residuals
.co
em
(C) Standard deviation
(D) Mean absolute error s
la Mean Square Deviation)
रुट भीन स्क्िामय डेविएशन (Root
a g
ककसका िगषभरू (square root) है ?
(A) Mean of residuals
(B) Variance of residuals
(C) Standard deviation
(D) Mean absolute error
(v) Answer : (B) Variance of residuals
m
(vi)
c om
The approach that the K-means Clustering Algorithm follows to
m .co
Chapter-7 1

m. e
solve a given clustering problem is called : Page-46

e
(A) Anomaly Detection
l as
l as (B) Expectation-Maximization
ag
g
(C) Decision Tree
a (D) Linear Regression
िह approach जजसका K-भीनस क्रस्टरयॊग एल्गोरयथभ (K-means
Clustering Algorithm) एक दह गई क्रस्टरयॊग सभस्मा को हर कयने
के लरए ऩारन कयता है , उसे क्मा कहा जाता है ?
(A) विसगनत का ऩता रगाना (Anomaly Detection)

om .
MS-Data Science/844/368 9 P3680844

.c e m
m
For more Question Papers, Sample Papers, Notes & Syllabus visit
as
Page 9 of 22

(B) एक्सऩेक्टे शन-भैजक्सभाइज़ेशन (Expectation-Maximization)
(C) डडसीजन ्቏ह (Decision Tree)
(D) रहननमय रय्ቇेशन (Linear Regression)
(vi) Answer : (B) Expectation-Maximization
4. Answer any 5 out of the given 6 questions. (5x1=5)
ददए गए 6 ्ቚश्नों भें से ककनहहॊ 5 के उ्ቈय दहजजए। (5x1=5)
th
(i) On 11 December, 2019, which ministry tabled the personal Chapter-1 1
Data protection Bill, 2019, in the Indian Page-4
parliament ?
(A) Ministry of Health and Family Welfare
(B) Ministry of Law and Justice
(C) Ministry of Finance
(D) Ministry of Electronics and Information Technology
11 ददसॊफय, 2019, को ककस भॊ्ቔारम (ministry) ने बायतीम सॊसद भें
personal Data protection Bill, 2019, ऩेश ककमा
?
(A) स्िास््म औय ऩरयिाय कल्माण भॊ्ቔारम
(B) कानन
ू औय नमाम भॊ्ቔारम
(C) वि्ቈ भॊ्ቔारम
(D) इरेक््቏ॉननक्स औय सूचना ्ቚौद्मोधगकी भॊ्ቔारम
(i) Answer : (D) Ministry of Electronics and Information
Technology
(ii) While entering data, Rehan has mistakenly recorded the variable Chapter-2 1
Distance as text instead of numeric. Which of the Page-10
following statements is true for this scenario ?
(A) Once the data is recorded, it cannot be cleaned during any
phase of data analysis.
(B) It will cause problems while using the data to build a
model.
(C) It will allow all mathematical operations without any
issues.
(D) It has no effect on any type of analysis.
डेटा दजष (entering) कयते सभम, ये हान ने गरती से Distance
(दयू ह) चय (variable) को सॊख्मात्भक (numeric) के फजाम टे क्स्ट
(text) के रूऩ भें दजष कय ददमा है । इस ऩरयदृश्म के लरए
ननम्नलरखखत भें से कौन सा कथन सत्म है ?
(A) एक फाय डेटा दजष हो जाने के फाद, इसे डेटा विश्रेषण के ककसी
बी चयण के दौयान साप (clean) नहहॊ ककमा जा सकता है ।
MS-Data Science/844/368 10 P3680844

For more Question Papers, Sample Papers, Notes & Syllabus visit Page 10 of 22

. c s e
m a
se l

ag
(B) भॉडर फनाने के लरए डेटा का उऩमोग कयते सभम मह
सभस्माएॉ उत्ऩनन कये गा।
(C) मह बफना ककसी सभस्मा के सबी गखणतीम कामों
(mathematical operations) को होने दे गा।
(D) इसका ककसी बी ्ቚकाय के विश्रेषण ऩय कोई ्ቚबाि नहहॊ ऩड़ेगा।
m
.co
(ii) Answer : (B) It will cause problems while using the data to
m
.co
build a model.
e m
s
e m la
s
(iii) Why is K-NN considered as non-parametric algorithm ? Chapter-4 1

la
(A) It assumes a specific distribution for the data before Page-23
ag
ag classification.
(B) It requires learning parameters for the data distribution.
(C) It does not assume anything about the distribution of the
data.
(D) It uses a fixed number of parameters to model the data.
K-NN को नॉन-ऩैयाभीद्቏क एल्गोरयथभ (non-parametric algorithm)
क्मों भाना जाता है ?
(A) मह िगीकयण (classification) से ऩहरे डेटा के लरए एक
m
.co
विलशष्ट वितयण (specific distribution) भानता है ।
em
इसे डेटा वितयण के लरए रननिंग ऩैयाभीटय (learning
s
la होती है।
(B)

g
parameters) सीखने की आिश्मकता
a
(C) मह डेटा के वितयण के फाये भें कुछ बी नहहॊ भानता है ।
(D) मह डेटा को भॉडर कयने के लरए ऩैयाभीटय (parameters) की
एक ननजश्चत सॊख्मा का उऩमोग कयता है ।
(iii) Answer : (C) It does not assume anything about the
distribution of the data.
m
c. o
(iv) Sneha is performing linear regression. She is using the Root Chapter-5 1
m
.co
Mean Square Deviation method to determine how close the Page-35
e m
s
observed points are to the model's predicted values. What is the
e m recommended action if a large deviation value is obtained ?
l a
l as (A) Remove the dependent variable from the model.
ag
ag (B) Change the independent variable to the dependent
variable (y).
(C) Retrain the model.
(D) Switch from linear regression to a classification algorithm.
स्नेहा रहननमय रय्ቇेशन (linear regression) कय यहह है औय मह
ननधाषरयत कयने के लरए रूट भीन स्क्िामय डेविएशन (Root Mean

om .
MS-Data Science/844/368 11 P3680844

.c e m
m
For more Question Papers, Sample Papers, Notes & Syllabus visit
as
Page 11 of 22

Square Deviation) विधध का उऩमोग कय यहह है कक observed points
भॉडर के अनुभाननत भानों (predicted values) के ककतने कयहफ हैं।
मदद एक फड़ा विचरन भान (deviation value) ्ቚाप्त होता है तो
recommended action क्मा है ?
(A) भॉडर से dependent variable (y) को हटा दें ।
(B) independent variable (x) को dependent variable (y) भें फदर
दें ।
(C) भॉडर को ऩन
ु : ्ቚलश्ቌऺत कयें (Retrain the model)।
(D) रहननमय रय्ቇेशन से िगीकयण एल्गोरयथभ (classification
algorithm) ऩय जस्िच कयें ।
(iv) Answer : (C) Retrain the model.
(v) Statement (1) : Logarithmic functions are examples of linear Chapter-6 1
function. Page-41
Statement (2) : The graph of non-linear regression follows the
equation of a curve.
(A) Both Statement (1) and Statement (2) are correct
(B) Both Statement (1) and Statement (2) are incorrect
(C) Statement (1) is correct but Statement (2) is incorrect
(D) Statement (1) is correct but Statement (2) is incorrect
कथन (1) : Logarithmic functions linear function के उदाहयण हैं।
कथन (2) : नॉन-रहननमय रय्ቇेशन (non-linear regression) का ्ቇाप
एक िि (curve) के सभीकयण को follow कयता है ।
(A) कथन (1) औय कथन (2) दोनों सहह हैं
(B) कथन (1) औय कथन (2) दोनों गरत हैं
(C) कथन (1) सहह है रेककन कथन (2) गरत है
(D) कथन (2) सहह है रेककन कथन (1) गरत है
(v) Answer :(D) Statement (2) is correct but Statement (1) is
incorrect
(vi) K-means clustering is a technique used to spot clusters of data Chapter-7 1
classes in a dataset and is classified as__________. Page-45
(A) A supervised learning technique
(B) A classification technique

MS-Data Science/844/368 12 P3680844

For more Question Papers, Sample Papers, Notes & Syllabus visit Page 12 of 22

. c s e
m a
se gl

(C) An unsupervised machine learning technique
a
(D) A regression technique
K-भीनस क्रस्टरयॊग (K-means clustering) एक ऐसी तकनीक है
जजसका उऩमोग एक डेटासेट भें डेटा क्रास (data classes) के क्रस्टय
(सभूह) का ऩता रगाने के लरए ककमा जाता है औय इसे इस रूऩ भें
िगीकृत ककमा जाता है __________।
m
(A) एक सऩ m
ु यिाइज्ड रननिंग तकनीक (A supervised learning .co
.co s e m
em
technique)

s
एक िगीकयण तकनीक (A classification technique)
g la
laएक अनसुऩयिाइज्ड भशीन रननिंग तकनीक (An unsupervised
(B)

g a
a machine learning technique)
(C)

(D) एक रय्ቇेशन तकनीक (A regression technique)
(vi) Answer : (C) An unsupervised machine learning technique
5. Answer any 5 out of the given 6 questions. (5x1=5)
ददए गए 6 ्ቚश्नों भें से ककनहहॊ 5 के उ्ቈय दहजजए।
(5x1=5)
m
.co
(i) Which of the following is an important aspect of GDPR Chapter-1 1
legislation ?
e m Page-3
(A) Data multiplication
l as
(B) Right to be forgotten
(C) Mandatory data sharing ag
(D) Unlimited data storage
ननम्नलरखखत भें से कौन सा GDPR कानून का एक भहत्िऩूणष ऩहरू
(aspect) हैं ?
(A) Data multiplication
(B) Right to be forgotten
(C) Mandatory data sharing
m
m Answer : (B)
(D) Unlimited data storage
.co
.co
(i) Right to be forgotten
s e m
s em (ii) (1 mark for correct answer)
l a
g la Statement-1 : Regression trees are used when the dependent ag Chapter-3 1
a variable is categorical.
Statement-2 : A node can have two or more branches in
Page-16

a decision tree.
(A) Both Statement (1) and Statement (2) are correct
(B) Both Statement (1) and Statement (2) are incorrect
(C) Statement (1) is correct but Statement (2) is incorrect
(D) Statement (2) is correct but Statement (1) is incorrect

om .
MS-Data Science/844/368 13 P3680844

.c e m
m
For more Question Papers, Sample Papers, Notes & Syllabus visit
as
Page 13 of 22

कथन (1) : रय्ቇेशन ्቏ह (Regression trees) का उऩमोग तफ ककमा
जाता है जफ डडऩें डेंट िेरयएफर (dependent variable) ्ቦेणीफद्ध
(categorical) होता है ।
कथन (2) : एक डडसीजन ्቏ह भें एक नोड भें दो मा दो से अधधक
शाखाऍ ॊ (branches) हो सकती हैं।
(A) कथन (1) औय कथन (2) दोनों सहह हैं
(B) कथन (1) औय कथन (2) दोनों गरत हैं
(C) कथन (1) सहह है रेककन कथन (2) गरत है
(D) कथन (2) सहह है रेककन कथन (1) गरत है
(ii) Answer : (D) Statement (2) is correct but Statement (1) is
incorrect
(iii) Which of the following is correct for the K-NN algorithm ? Chapter-4 1
(A) It is highly accurate with imbalanced data. Page-24
(B) It is immune to the curse of dimensionality.
(C) It is slow and memory-inefficient.
(D) It is robust to outliers.
K-NN एल्गोरयथभ के लरए ननम्नलरखखत भें से कौन सा सहह है ?
(A) मह असॊतुलरत डेटा (imbalanced data) के साथ अत्मधधक
सटहक (accurate) है ।
(B) मह curse of dimensionality से ्ቚनतय्ቌऺत (immune) है ।
(C) मह धीभा औय भेभोयह-अकुशर (memory-inefficient) है ।
(D) मह आउटरामय के लरए robust है ।
(iii) Answer : (C) It is slow and memory-inefficient.
(iv) The equation for a simple linear regression is of the form Chapter-5 1
y = m*x+b. What do 'm' and 'b' represent in the Page-34
equation.
(A) Slope, Independent Variable
(B) Independent Variable, Intercept
(C) Slope, Intercept
(D) Dependent Variable, Slope
एक सयर रहननमय रय्ቇेशन (simple linear regression) का सभीकयण
y = m*x+b के रूऩ का होता है । सभीकयण भें 'm' और 'b' क्मा
दशाषते हैं ?
(A) Slope इॊडडऩें डेंट िेरयएफर (Independent Variable)
(B) इॊडडऩें डेंट िेरयएफर (Independent Variable) इॊटयसेप्ट
MS-Data Science/844/368 14 P3680844

For more Question Papers, Sample Papers, Notes & Syllabus visit Page 14 of 22

. c s e
m a
se l

(Intercept)
ag
(C) Slope इॊटयसेप्ट (Intercept)
(D) डडऩें डेंट िेरयएफर (Dependent Variable), Slope
(iv) Answer : (C) Slope, Intercept
(v) A simple regression equation has an intercept on the right-hand Chapter-6 1
m
.co
side and an explanatory variable with a/an ___________. Page-40
m
.co
(A) Coefficient
(B) Dependent variable
e m
em
(C) intercept
las
la s
(D) Linear regression
ag
g
एक सयर रय्ቇेशन सभीकयण के दादहने हाथ की ओय एक इॊटयसेप्ट
a
(intercept) औय explanatory variable के साथ एक ___________
होता है ।
(A) Coefficient
(B) डडऩें डेंट िेरयएफर (Dependent variable)
(C) इॊटयसेप्ट (intercept)
(D) रहननमय रय्ቇेशन (Linear regression)
m
(v) Answer : (A) Coefficient
m .co
s e
(vi)
g l a
The K-means Clustering algorithm it first specifies the number
of clusters, K depending on the input. Thereafter how does it
Chapter-7
Page-46
1

initialize the centroids ? a
(A) By Assigning all data points to any one cluster.
(B) By Computing the sum of the squared distance and
assigning to the K clusters.
(C) By Shuffling the data points and then selecting K data
points randomly.
(D) By Using only the labelled data for clusters, K.
K-भीनस क्रस्टरयॊग एल्गोरयथभ के भाभरे भें , मह सफसे ऩहरे इनऩट ु
m
.co
के आधाय ऩय क्रस्टसष (clusters) की सॊख्मा K को ननददष ष्ट
m (specifies) कयता है। इसके फाद मह सें्቏ोइड्स (centroids) को कैसे
m .co s e m
s e (initialize) कयता है ?
l a
g l a agको
(A) सबी डेटा ऩॉइॊट (data points) को ककसी एक क्रस्टय
a assign कयना।
(B) िगष दयू ह (squared distance) के मोग की गणना कयना औय K
कल्स्टसष को assign कयना।
(C) डेटा ऩॉइॊट को शपर (Shuffling) कयना औय कपय randomly K
डेटा ऩॉइॊट का चमन कयना।

om .
MS-Data Science/844/368 15 P3680844

.c e m
m
For more Question Papers, Sample Papers, Notes & Syllabus visit
as
Page 15 of 22

(D) क्रस्टय, K के लरए केिर रेफर ककए गए डेटा (labelled data)
का उऩमोग कयना।
(vi) Answer : (C) By Shuffling the data points and then selecting
k data points randomly.
SECTION – B 30 marks
खण्ड - ख
Answer any 3 cut of the given 5 questions (Question No 6 to 10) (3x2=6)
on Employability Skills in 20-30 words each.
योजगाय कौशर ऩय ददए गए 5 ्ቚश्नों (्ቚश्न सॊख्मा 6 से 10 ) भें से (3x2=6)
ककनहहॊ 3 ्ቚश्नों के उ्ቈय 20-30 शब्दों भें दहजजए।
6. The four skills are :- U-1 Pg-1 2
Listening (0.5x4)
Speaking
Reading
Writing

7. Motivation is derived from the word 'motive'. Thus directing U-2 Pg-24 2
behaviour towards certain motive or goal is the essence of (1x2=2)
motivation.
An individual's motivation may come from within or be inspired
by others or events.
8. A digital presentation can be saved as a file on the computer. U-3 Pg-66 2
(1+1)
This can be opened later, viewed, edited shared with friends and
colleagues and printed.

9. Because (i) It requires specific progression and procedures U-4 Pg-80 2
to be followed
(ii) It also requires skills to digress when required
and yet make the entire activity profitable and
growth oriented
10. Appropriate technology is a smalt scale technology that is U-5 Pg-117 2
environment friendly and suited to local needs. (1+1)
Examples –
(i) Bike powered or hand powered water pumps
(ii) Solar lamps in streetlight
(iii) Solar buildings etc
Answer any 4 out of the given 6 questions(Question No 11 to (4x2=8)
16) in 20 – 30 words each.
ददए गए 6 ्ቚश्नों (्ቚश्न सॊख्मा 11 से 16) भें से ककनहहॊ 4 ्ቚश्नों के उ्ቈय (4x2=8)

MS-Data Science/844/368 16 P3680844

For more Question Papers, Sample Papers, Notes & Syllabus visit Page 16 of 22

. c s e
m a
se l

ag
20-30 शब्दों भें दहजजए।
11. What is data privacy ? Explain why data privacy rules can be Chapter-1 2
violated even if a company stores personal identifiable Page-2
information securely in an encrypted format ?
डेटा गोऩनीमता (data privacy) क्मा है ? सभझाएॉ कक मदद कोई कॊऩनी
व्मजक्तगत ऩहचान मोग्म जानकायह (personal identifiable
m
c o m
information) को एजनिप्टे ड (encrypted) पॉभेट भें सयु ्ቌऺत रूऩ से
m .co
सॊ्ቇहहत कयती.है , तफ बी डेटा गोऩनीमता ननमभों का उल्रॊघन क्मों हो e
m las
सकता हैse g
la : a
?

a g
Answer
Data privacy is the right of any individual to have control over
how his/her personal information is collected and used.
A violation can still occur even if data is stored securely in an
encrypted format because data privacy is not just about secure
data storage; if there is no agreement from the users regarding
the collection of the data itself, it is violation of data privacy
riles.

o m
c
(1 mark for each for each correct part)
12.
m .
Raunak owns a small cafe and wants to understand if there is a Chapter-2 2
s e
correlation between the temperature outside and the number of Page-9
cold drinks sold daily. He haslacollected data for 30 days
a
showing daily temperature and gcold drink sales.
(a) What type of analysis should he use to study this
correlation ?
(b) Name any one graphical method he can use to visualize
this data.
यौनक का एक छोटा सा कैपे (cafe) है औय िह मह सभझना चाहता है
कक फाहय के ताऩभान औय ्ቚनतददन फेचे जाने िारे कोल्ड डरॊक्स की
सॊख्मा के फीच कोई सहसॊफॊध (correlation) है मा नहहॊ। उसने 30 ददनों
m
m का डेटा एक्ቔ ककमा है जजसभें दै ननक ताऩभान औय कोल्ड डरॊक की .co
.co बफिी ददखाई गई है । e m
s e m as
(a) इस सहसॊफॊध का अध्ममन कयने के लरए उसे ककस ्ቚकायglके
g l a विश्रेषण (analysis) का उऩमोग कयना चादहए ?
a
a
(b) इस डेटा को विजुअराइज़ (visualize) कयने के लरए िह जजस
ककसी एक ्ቇाकपकर विधध (graphical method) का उऩमोग कय
सकता है , उसका नाभ फताएॊ।
Answer :
(a) Raunak should use bivariate analysis to study the

om .
MS-Data Science/844/368 17 P3680844

.c e m
m
For more Question Papers, Sample Papers, Notes & Syllabus visit
as
Page 17 of 22

relationship between temperature and cold drink sales.
(b) He can use a scatter plot (or line chart/pair plot) to
visualize the relationship between the two variables.
(1 mark for each for each correct part)
13. Name and explain any one popular method of cross-validation. Chapter-4 2
िॉस िैलरडेशन (cross-validation) की ककसी एक रोकव्ቚम विधध का Page-25
नाभ फताइए औय उसकी व्माख्मा कयें ।
Answer :
One popular method to do cross validation is to use k-fold cross
validation technique.
In this method, we split the data into k different but similar folds
or sets. We then perform k iterations and in each iteration, we
choose one fold as the validation set or test set, and the rest as
training sets.
(1 mark for correctly naming the technique
1 mark for brief explanation)
14. Why are decision trees considered versatile ? Mention any two Chapter-3 2
points. Page-15
डडसीजन ्቏ह (decision Trees) को versatile क्मों भाना जाता है ?
ककनहहॊ दो बफॊदओु ॊ का उल्रेख कयें ।
Answer :
1. They can be used for any kind of problem, whether it is
classification or regression.
2. Unlike linear models, decision trees can map both linear
and non-linear relationships quite well.
(1 mark for mentioning each point )
15. What is Mean Absolute Error (MAE) ? Also explain the process Chapter-5 2
of 'Fitting the line to the data' that MAE. Page-34
Mean Absolute Error (MAE) क्मा है ? MAE का उऩमोग कयके
„डेटा ऩय राइन को कपट कयने‟ (Fitting the line to the data) की
्ቚकिमा की बी व्माख्मा कयें ।
Answer :
Mean Absolute Error (MAE) measures the average magnitude of
the errors in predictions without considering their direction.
The basic objective of linear regression is to try to reduce the
vertical distance between the line of best fit and the data points
to make it minimum. This process is called Fitting the line to the
data.
(1 mark for each for each correct part )
16. Mention any two differences between Supervised Learning and Chapter-7 2
Unsupervised Learning. Page-43,44
सुऩयिाइज्ड रननिंग (Supervised Learning) औय अनसुऩयिाइज्ड
रननिंग (Unsupervised Learning) के फीच ककनहहॊ दो अॊतयों का
MS-Data Science/844/368 18 P3680844

For more Question Papers, Sample Papers, Notes & Syllabus visit Page 18 of 22

. c s e
m a
se l

ag
उल्रेख कयें ।
Answer :
Supervised Learning Unsupervised Learning
Algorithms are trained using Algorithms are not trained
data that is well-labelled or using data that is classified or
classified labelled.
Uses the trained algorithm to Algorithm discover hidden
m
.co
make predictions on new sets patterns or data groupings,
m
.co m
of data for classification or thereby acting on data
regression problems
m
without human intervention.
s e
s e
Ideal for classification and Ideal for solving real-life
g la
la
regression problems.
g
problems such as exploratory
a
a data analysis, customer
segmentation, and image
recognition
(1 mark for each correct difference) (Any two)
Answer any 3 out of the given 5 questions (Question No 17 to (3x4=12)
21) in 50 – 80 words each.
ददए गए 5 ्ቚश्नों (्ቚश्न सॊख्मा 17 से 21 ) भें से ककनहहॊ 3 ्ቚश्नों के (3x4=12)
उ्ቈय 50-80 शब्दों भें दहजजए।
m
.co
17. Answer the following questions about HIPAA legislation. Chapter-1 1+2+1=4
i. Expand the abbreviation HIPAA. Page-3
ii. State any two objectives of HIPAA.
e m
l as
iii. Give any two examples personal identifiers that HIPAA
protects.
ag
HIPAA कानून (legislation) के फाये भें ननम्नलरखखत ्ቚश्नों के उ्ቈय
दें ।
i. HIPAA सॊ्ቌऺप्त नाभ (abbreviation) को expand कयें ।
ii. HIPAA के ककनहहॊ दो उद्दे श्मों (objectives) को फताएॊ।
iii. personal identifiers के दो उदाहयण दें जजनकी HIPAA सुयऺा
कयता है ।
m
m Answer :
.co
.co e m
i. Health Insurance Portability and Accountability Act

e m (1 mark for correct expansion)
l as
l as ii.
• ag
g
To protect healthcare information from fraud and
a •
theft
Helps to manage personally identifiable information
stored by healthcare and insurance companies.
• Returns control of data to the individuals
(1 mark for each correct objective) (Any two)
iii. Name, Phone numbers, email addresses, geographical
identifiers, fingerprints or retinal prints, social security

om .
MS-Data Science/844/368 19 P3680844

.c e m
m
For more Question Papers, Sample Papers, Notes & Syllabus visit
as
Page 19 of 22

numbers, medical records (any two)
(½ mark for each correct identifier)
18. Explain the concept of Univariate Analysis. Describe its main Chapter-2 4
purpose and list two different statistical and two different Page-8
graphical methods associated with it.
मूननिेरयएट एनालरलसस (Univariate Analysis) की अिधायणा
(concept) की व्माख्मा कयें । इसके भुख्म उद्दे श्म (main purpose) का
िणषन कयें औय इससे जुडी दो अरग-अरग साॊजख्मकीम (statistical)
औय दो अरग-अरग ्ቇाकपकर (graphical) विधधमों को सूचीफद्ध
कयें ।
Answer :
Concept : only one variable analysed, no worry about causes or
relationships
Purpose : Describe the data and find patterns that exist within
it
Statistical Methods : (Mean, mode, median, range, variance,
maximum, minimum, quartiles, standard
deviation – any two)
Graphical Methods : Frequency distribution tables, bar charts,
histograms, frequency polygons, pie
charts - any two )
(1 mark for correct concept)
(1 mark for correct purpose)
(2 mark for correct methods)
19. What is a decision tree ? Explain the steps involved in creating a Chapter-3 4
decision tree. Page-
डडसीजन ्቏ह (decision tree) क्मा है ? डडसीजन ्቏ह फनाने भें शालभर 13,16,17

चयणों की व्माख्मा कयें ।
Answer :
A decision tree is a diagrammatic representation of a decision-
making process with a tree-like structure. Each internal node
represents a question, branches show possible outcomes, and
leaf nodes indicate class labels or results.
Steps for creating decision tree
• Define the main objective and place it at the root of the
tree
• Draw branches for each possible decision and add leaf
nodes to show results.
• Calculate the probability of success for each decision
using data or past projects.
(1 mark for correct definition)
(1 mark for each correct step)
20. (a) A health researcher wants to predict a patient's blood Chapter-6 4
MS-Data Science/844/368 20 P3680844

For more Question Papers, Sample Papers, Notes & Syllabus visit Page 20 of 22

. c s e
m a
se gl

a
pressure based on four factors : age, weight, Page-40-42
cholesterol level, and daily exercise
duration .
Identify and define the most suitable regression model to
analyse the relationship. Explain why this model is
appropriate for this scenario.
(b) Rudhra started her business six months back. Her income
m
.co
has increased exponentially (5 times) every month. Which
m
.co
type of regression can be used to predict her income in the
seventh month ?
e m
(a)
e m
एक स्िास््म शोधकताष (health researcher) चाय कायकों: आमु
las
l as िजन कोरेस््቏ॉर स्तय ag
ag (cholesterol level) औय दैननक व्मामाभ की अिधध
(age), (weight),

(daily exercise duration) के आधाय ऩय एक
भयहज के यक्तचाऩ (blood pressure) को predict कयना चाहता
है । इस सॊफॊध का विश्रेषण कयने के लरए सफसे उऩमक्
ु त
रय्ቇेशन भॉडर (regression model) की ऩहचान कयें औय उसे
ऩरयबावषत कयें । सभझाएॉ कक मह भॉडर इस ऩरयदृश्म
(scenario) के लरए क्मों उऩमक्
ु त है ? o m
c
. शरूु ककमा था। उसकी
m
(b) रु्ቖ ने छह भहहने ऩहरे अऩना व्मिसाम
e ा) िद्धध हई है। सातिें
आम भें हय भहहने exponential a s
(5 गन
l ु ृ ु
भहहॊने भें उसकी आम को a
g
(predict) कयने के लरए ककस ्ቚकाय के
रय्ቇेशन (regression) का उऩमोग ककमा जा सकता है ?
Answer :
(a) Multiple Linear Regression Model. It is a statistical
method that models the relationship between one
dependent variable and two or more independent
variables by fitting a linear equation to the observed
data. It is appropriate for this scenario as there is one
m
m .co
dependent variable (blood pressure) and multiple

.co m
independent variables (age, weight, cholesterol level,

m
and daily exercise duration)
s e
s e l a
ag
(1 mark for identification and 1 mark for valid definition.)

g l a (1 mark for suitable explanation)
a (b) Non-Linear Regression
21. Explain the role of Unsupervised Learning in the following real- Chapter-7 4
world applications : Page-44
i. Recommendation engines
ii. Anomaly detection
iii. Medical images

om .
MS-Data Science/844/368 21 P3680844

.c e m
m
For more Question Papers, Sample Papers, Notes & Syllabus visit
as
Page 21 of 22

iv. News categorization
ननम्नलरखखत िास्तविक-दनु नमा के अन्ቚ
ु मोगों (real-world
applications) भे अनसऩ
ु यिाइज्ड रननिंग (Unsupervised Learning)
की बलू भका (role) की व्माख्मा कयें ।
i. ये कभें डश
े न इॊजन (Recommendation engines)
ii. अनोभरह डडटे क्शन (Anomaly detection)
iii. भेडडकर इभेजजॊग (Medical imaging)
iv. नमज़ ू िगीकयण (News categorization)
Answer :
i. Recommendation Engines : Helps predict products a
customer is likely to buy by analysing past purchase
behaviour and discovering trends.
ii. Medical imaging : Assists in image detection,
classification, and segmentation for faster and accurate
diagnosis.
iii. Anomaly detection : Identifies unusual data points in
large datasets to detect fraud or security breaches.
iv. News categorization : Categorizes news articles into
sections like sports, entertainment, and international news.
(1 mark for each correct part )
-oOo -

MS-Data Science/844/368 22 P3680844

For more Question Papers, Sample Papers, Notes & Syllabus visit Page 22 of 22