PRE BOARD 2 2024-25

Answer key AI paper 12th SET B

Section A: Objective Type Questions

Q.I. Answer any 4 out of the given 5 questions (1 x 4 = 4 marks)

1. Which of the following is NOT an example of an environmental barrier to

entrepreneurship?
o The answer is (b) Self-doubt. Environmental barriers refer to external factors,
while self-doubt is an internal, psychological factor.
2. What is a crucial aspect of paragraph writing?
o The answer is (a) Ensuring all sentences contribute to the same idea. A key
aspect of good paragraph writing is maintaining a single focus or idea throughout.
3. What is the first step in becoming result-oriented?
o The answer is (a) Setting precise goals. Before one can create an action plan,
goals need to be established.
4. How can a row/column be deleted in a spreadsheet?
o The answer is (b) By right-clicking on the row/column heading and selecting
Delete. While there are other ways, this is the standard method mentioned.
5. Which of the following is a potential benefit of using bamboo for water conservation?
o The answer is (c) Bamboo can be used as manure after 2-3 years. This
indicates a long term sustainable benefit.

Q.II. Answer any 5 out of the given 6 questions (1 x 5 = 5 marks)

1. If there is no pattern in the data, what does the text suggest?

o The answer is (b) Don't apply AI techniques to solve the problem. If data has
no pattern, AI is unlikely to be useful.
2. What is the purpose of breaking a problem into smaller units?
o The answer is (b) To simplify the task before coding. Breaking down problems
makes them easier to manage and code.
3. In time series decomposition, what does "level" refer to?
o The answer is (b) The average value in the series. Level represents the base
value around which the time series fluctuates.
4. What is the typical purpose of a Capstone Project in an academic program?
o The answer is (c) To integrate all learning from the program. A capstone
project allows students to apply everything they've learned.
5. What is the first step in every AI project?
o The answer is (b) Problem Definition. Before you can gather data, the problem
must be well defined.
6. Which of the following questions falls under the category of "Regression" when using AI
techniques?
 o The answer is (b) How much or how many?. Regression is used for predicting
continuous numerical values.

Q.III. Answer any 5 out of the given 6 questions (1 x 5 = 5 marks)

1. What does the document suggest if it is believed that there is no pattern in the data?
o The answer is (b) Do not apply AI techniques to solve the problem. This
reinforces the point from the previous question that AI isn't useful without
patterns.
2. What is the first step in problem decomposition, as outlined in the document?
o The answer is (c) Break the problem into small pieces. Problem decomposition
is about dividing a problem into smaller parts.
3. What is the primary goal of Design Thinking?
o The answer is (b) To provide a solution-based approach to solving problems.
The focus of design thinking is finding practical solutions.
4. A researcher wants to study the association between gender and using a mobile phone.
Data collected for this study will be ______
o The answer is (a) Qualitative data. This type of data is categorical and
descriptive rather than numerical.
5. Which process does NOT come under Capstone Project?
o The answer is (d) Data Gathering. Data gathering is done before a capstone
project is started.
6. Which of the following programming languages is widely regarded as the most popular
for AI development?
o The answer is (c) Python. Python is the most popular language for AI due to its
rich set of libraries.

Q.IV. Answer any 5 out of the given 6 questions (1 x 5 = 5 marks)

1. Techniques like descriptive statistics and visualizations can be applied to datasets after
the original data gathering to analyse the content. To close the gap, additional data
collecting may be required. Identify the stage of this analytic approach.
o The answer is (c) Data Understanding. This stage is all about analyzing and
understanding the data that has been collected.
2. Which of the following is NOT a property of Root Mean Squared Error (RMSE)?
o The answer is (d) It is robust to outliers, meaning extreme values have little
impact on the RMSE. RMSE is sensitive to outliers because of the squaring
process.
3. During Train-Test split evaluation, we usually split the data around between testing and
training stages.
o The answer is (b) 20%-80%. A common train test split is to use 80% of the data
for training and 20% for testing
4. Provides a useful abstract model for thinking about time series generally and for better
understanding problems during time series analysis and forecasting.
o The answer is (a) Decomposition. Time series decomposition helps to understand
the underlying patterns in the series
 5. Which of the following does not come under open languages category used for AI
development platforms?
o The answer is (a) Design. Design is not a programming language, but an
important step in AI development.

Q.V. Answer any 5 out of the given 6 questions (1 x 5 = 5 marks)

1. Match the following: 1. Open Frameworks A. AutoAI 2. Open Languages B. Anaconda

3. Development tools C. Python 4. Productivity-enhancing capabilities D. XGBoost
o The answer is (b) 1-D, 2-C, 3-B, 4-A. This matches open frameworks to
XGBoost, open languages to Python, development tools to Anaconda and
productivity enhancing capabilities to AutoAI.
2. Data Validation for human biases is conducted in phase of AI Model Life Cycle.
o The answer is (b) Data Collection. Bias must be addressed in the early stages
when collecting data
3. Which of the following is a disadvantage of Cross Validation Technique?
o The answer is (c) As we need to train on many training sets, cross-validation
is computationally expensive.. Cross-validation requires multiple training runs,
which can take a lot of computing power and time.
4. If AI techniques are to be applied to a dataset, the data must have a …………
o The answer is (c) Pattern. AI requires underlying patterns in the data to be
effective.
5. When evaluating the performance of a regression model, which metric is commonly used
to measure the average magnitude of errors between predicted and actual values?
o The answer is (d) Root Mean Squared Error (RMSE). RMSE measures the
average magnitude of errors in regression models.
6. Which of the following is NOT listed as a stage in the Foundational Methodology of Data
Science?
o The answer is (d) Public Relations. The foundational steps focus on data
handling and model development.

Section B: Subjective Type Questions

Q VI. Answer any 3 out of given 5 questions in 20 – 30 words each on employability skills. (2 x
3 = 6 marks)

1. Differentiate between 'sentence' and 'phrase' with the help of a suitable example.
o A sentence is a complete grammatical unit that includes a subject and a predicate,
expressing a complete thought. Example: "The cat sat on the mat." A phrase is a
group of words that does not contain a subject and predicate, and acts as a single
part of speech. Example: "on the mat."
2. With reference to "Five Factor Model", mention any four parameters that describe an
individual's personality.
o The Five Factor Model includes: Openness, Conscientiousness, Extraversion,
Agreeableness, and Neuroticism. These parameters provide a framework for
understanding personality.
 3. Explain any two advanced features of a spreadsheet.
o Two advanced features are: Pivot tables, which allow for data summarization and
analysis, and macros, which automate repetitive tasks by recording a sequence of
actions.
4. Briefly explain any two qualities that make an entrepreneur successful.
o Two key qualities include: Resilience, the ability to recover from setbacks, and
Adaptability, the willingness to change strategies and direction based on
circumstances.
5. Explain the importance of green jobs in reducing the emission of greenhouse gases.
o Green jobs are in fields that aim to protect the environment and reduce pollution.
They directly help reduce greenhouse gas emissions through tasks such as
renewable energy generation, energy efficiency implementation, and
environmental conservation.

Q VII. Answer any 3 out of the given 5 questions in 30 – 50 words each (3 x 3 = 9 marks)

1. What is a capstone project, and what are its primary objectives?

o A capstone project is a culminating academic assignment that allows students to
apply their skills and knowledge gained throughout their studies. Primary
objectives include integrating learning, demonstrating mastery, and
producing a tangible output.
2. What are the typical steps in an AI project, and what is the significance of the final step?
o Typical steps include: Problem Definition, Data Gathering, Model
Construction, and Deployment. The final step, Deployment, is significant
because it brings the AI model into real-world use and allows for practical
application.
3. Explain whether the Mean Squared Error (MSE) can ever be a negative value. Justify
your answer.
o MSE cannot be negative. MSE is calculated by averaging the squared errors.
Squaring any number, either positive or negative, will always yield a non-
negative result. The average of non-negative values will also be non-negative.
4. Suppose you are embarking on the development of your first app. Formulate a set of
questions that would help you break down this project into manageable components.
o Some questions to ask would be: What are the core functionalities of the app?
What are the user interface requirements? What data is required? What are
the essential features for initial release?. These will help to create a structured
approach.
5. Differentiate between descriptive and predictive models in terms of their purpose and
methodology.
o Descriptive models summarize past data to describe the patterns and features
within it. Predictive models, on the other hand, use past data to forecast future
events or values. Descriptive models focus on understanding existing data, while
predictive models aim at making predictions.
6. Explain the problem decomposition steps.
o Problem decomposition involves breaking down a complex problem into smaller,
more manageable parts. This simplifies the development process. Steps include:
 identifying sub-problems, defining dependencies between sub-problems,
assigning tasks based on sub-problems, and combining the solutions to solve
the overall problem.

Q VIII. Answer any 3 out of the given 5 questions in 50 – 80 words each (4 x 3 = 12 marks)

1. A team is developing a sentiment analyzer. They have collected a large set of text data
with corresponding sentiment labels (positive, negative, neutral). Explain how they
should validate their model, including the train-test split method and the concept of cross-
validation, and why these are important.
o To validate their model, the team should use the train-test split method to divide
the dataset into training and testing sets. The model is trained on the training set
and evaluated on the test set. Cross-validation involves dividing the data into
multiple folds and iterating the training and testing to ensure the model's
performance is stable and generalizable. These techniques are crucial for ensuring
that the model is not overfitting to training data and works on new, unseen data.
2. (a) Discuss the significance of each of the key elements in the process of Data story
telling. (b) Which of the following is a better data story? Give reasons.
o Key elements in data storytelling include: Data, Narrative, and Visuals. The
data must be accurate, relevant, and insightful. The narrative provides context
and meaning. Visuals help in easy understanding and engaging the audience.
Without context and a compelling narrative, even good data can be meaningless.
3. Explain how to decompose a complex problem using the Design Thinking framework.
How does this help in the development process?
o Design Thinking involves several phases, which guide the decomposition of a
problem. These phases include: Empathize, Define, Ideate, Prototype, and
Test. By going through this cycle, a team can identify root issues, brainstorm a
wide range of solutions, build a prototype and test the solution. This is an iterative
process that helps to refine the solution, and it simplifies the development process
by breaking it into steps focused on the user needs, making the process more
efficient and effective.
4. "Explain any four reasons why storytelling is so powerful and cross-cultural?"
o Storytelling is powerful because: it engages emotion, it makes information
memorable, it helps build connections, and transcends cultural boundaries
because it uses universal themes. Stories can be adapted to different cultures by
keeping the key messages while using local and more relevant cultural examples.
5. Beyond fundamental testing concepts, what specific additional considerations are
necessary when testing AI development projects?
o When testing AI projects, it's essential to consider: bias in data, fairness of the
model's predictions, robustness of the model under unusual inputs, and
explainability of the model’s outputs. These considerations ensure that AI
systems work reliably, fairly, and with accountability, and address problems
related to ethics and bias.