IOE PapersTU
PYQs & Syllabus Archive
ENCT 202Bachelor in Computer Engineering · Semester 31 Paper Available

Foundation of Data Science

Past examination question papers and complete curriculum syllabus for Foundation of Data Science (ENCT 202), Bachelor in Computer Engineering Semester 3 under Institute of Engineering (IOE), Tribhuvan University.

Past Question Papers (PDF)

Switch tabs to view different exam papers

3rd-sem_Foundation of Data Science.pdf

IOE Past Examination Paper

Download PDF
Served via fast CDN. Read in full view or download for offline study.
Drive Mirror ↗Direct Download ↓

Document information: This past examination paper is identified as an IOE/TU academic document and was cataloged from a public Google Drive archive. This independent website did not create the examination paper and is not affiliated with TU or IOE.

Rights holders can request correction or removal by emailing subeshgaming@gmail.com with this page URL and supporting details.

Most Frequently Asked Questions

Top recurring IOE board exam questions for Foundation of Data Science with verified mark schemes, formula notation, and recurrence frequency.

Showing 30 of 30 top repeated questions

Introduction to Data Science

4 Questions
#1Repeated 2 Times[5 Marks]Introduction to Data Science
How is a traditional software programmer different from a data scientist? Explain the differences in skill sets (programming, statistics, domain knowledge) and discuss career roles: Data Analyst, Data Engineer, Machine Learning Engineer, and Data Scientist.
Appeared in:2081 Chaitra
#2Repeated 2 Times[4 Marks]Introduction to Data Science
Differentiate between Structured, Semi-Structured (JSON, XML, CSV), and Unstructured data (text, images, audio) with examples. Describe the typical stages of the Data Science Lifecycle.
Appeared in:2081 Chaitra
#3Repeated 2 Times[6 Marks]Introduction to Data Science
Explain the Data Science Lifecycle according to the CRISP-DM methodology: Business Understanding, Data Understanding, Data Preparation, Modeling, Evaluation, and Deployment.
Appeared in:2082 Chaitra2081 Chaitra
#4Repeated 2 Times[6 Marks]Introduction to Data Science
Explain Big Data characteristics through the 5 V's: Volume, Velocity, Variety, Veracity, and Value. Differentiate between Batch Processing and Real-time Stream Processing architectures.
Appeared in:2082 Chaitra2081 Chaitra

Mathematics for Data Science

3 Questions
#1Repeated 2 Times[6 Marks]Mathematics for Data Science
An e-mail filter is designed to separate valid emails from spam. The word "free" occurs in 70% of spam messages and in only 4% of valid messages. Overall, 25% of received messages are spam. Using Bayes' Theorem, determine: (a) The probability that a randomly chosen message contains "free". (b) The probability that the message is spam given that it contains "free". (c) The probability that the message is valid given that it does not contain "free".
Appeared in:2081 Chaitra
#2Repeated 2 Times[4 Marks]Mathematics for Data Science
State the Central Limit Theorem (CLT). Why is it considered foundational in data science, sampling theory, and hypothesis testing? Explain with an example.
Appeared in:2081 Chaitra
#3Repeated 2 Times[6 Marks]Mathematics for Data Science
Explain Hypothesis Testing in data science: Null Hypothesis ($H_0$), Alternative Hypothesis ($H_1$), significance level ($\alpha$), p-value, Type I error, and Type II error. When do we apply two-sample t-test versus z-test?
Appeared in:2082 Chaitra2081 Chaitra

Data Understanding and Preprocessing

5 Questions
#1Repeated 2 Times[4 Marks]Data Understanding and Preprocessing
How do you handle missing values during data preprocessing? Explain Mean/Median imputation, Mode imputation, K-Nearest Neighbors imputation, and dropping strategies with practical examples.
Appeared in:2081 Chaitra
#2Repeated 2 Times[4 Marks]Data Understanding and Preprocessing
Given a sample dataset of numerical attributes, perform data normalization using: (a) Min-Max feature scaling in the range $[0, 1]$, and (b) Z-score standardization ($z = \frac{x - \mu}{\sigma}$). Compare their sensitivity to outliers.
Appeared in:2081 Chaitra
#3Repeated 2 Times[4 Marks]Data Understanding and Preprocessing
Explain Feature Selection techniques: Filter methods (correlation, chi-square), Wrapper methods (forward selection, backward elimination), and Embedded methods (Lasso L1 regularization).
Appeared in:2081 Chaitra
#4Repeated 2 Times[6 Marks]Data Understanding and Preprocessing
What are Outliers in a dataset? Explain the Interquartile Range (IQR) method and Z-score method for detecting outliers. How should outliers be treated in data cleaning?
Appeared in:2082 Chaitra2081 Chaitra
#5Repeated 2 Times[4 Marks]Data Understanding and Preprocessing
What is Categorical Data Encoding? Compare One-Hot Encoding and Label (Ordinal) Encoding. Why does One-Hot Encoding cause the curse of dimensionality on high-cardinality attributes?
Appeared in:2082 Chaitra2081 Chaitra

Data Analysis

6 Questions
#1Repeated 2 Times[4 Marks]Data Analysis
Explain the Five-Number summary (Minimum, $Q_1$, Median, $Q_3$, Maximum). Draw and label a Box-and-Whisker plot to detect outliers using the Interquartile Range ($1.5 \times \text{IQR}$) rule for a given dataset.
Appeared in:2081 Chaitra
#2Repeated 2 Times[5 Marks]Data Analysis
What are the primary objectives of data visualization in Exploratory Data Analysis (EDA)? Explain the interpretation and use cases of Heatmaps, Correlation matrices, Scatter plots, and Histograms.
Appeared in:2081 Chaitra
#3Repeated 2 Times[5 Marks]Data Analysis
What is the curse of dimensionality? Explain the working principle of Principal Component Analysis (PCA) for unsupervised dimensionality reduction using eigenvectors and eigenvalues.
Appeared in:2081 Chaitra
#4Repeated 2 Times[8 Marks]Data Analysis
What is K-Means clustering? Explain the step-by-step algorithm, centroid update formula, convergence criteria, and the Elbow Method for determining optimal number of clusters ($k$).
Appeared in:2082 Chaitra2081 Chaitra
#5Repeated 2 Times[6 Marks]Data Analysis
Differentiate between Correlation and Causation. Explain Pearson Correlation Coefficient ($r$) and Spearman Rank Correlation ($\rho$). How does a Correlation Heatmap assist in bivariate exploratory analysis?
Appeared in:2082 Chaitra2081 Chaitra
#6Repeated 2 Times[8 Marks]Data Analysis
Explain Principal Component Analysis (PCA) step-by-step: data standardization, Covariance Matrix computation, Eigenvalues and Eigenvectors calculation, and projection onto principal components.
Appeared in:2082 Chaitra2081 Chaitra

Regression and Predictive Modeling

5 Questions
#1Repeated 2 Times[5 Marks]Regression and Predictive Modeling
What is linear regression and how does it support predictive analytics? Formulate the ordinary least squares (OLS) loss function and explain how gradient descent optimizes regression weights.
Appeared in:2081 Chaitra
#2Repeated 2 Times[8 Marks]Regression and Predictive Modeling
Explain Logistic Regression for binary classification. Derive the Sigmoid activation function $\sigma(z) = \frac{1}{1 + e^{-z}}$, odds ratio, and log-odds (logit) formulation. How does Binary Cross-Entropy loss penalize classification errors?
Appeared in:2082 Chaitra2081 Chaitra
#3Repeated 2 Times[8 Marks]Regression and Predictive Modeling
Explain Decision Tree learning algorithm. Describe Information Gain, Shannon Entropy $H(S) = -\sum p_i \log_2 p_i$, and Gini Impurity criteria used by ID3 and CART algorithms to select best splitting attributes with a small numerical example.
Appeared in:2082 Chaitra2081 Chaitra
#4Repeated 2 Times[8 Marks]Regression and Predictive Modeling
What is Overfitting and Underfitting in supervised machine learning? Explain the Bias-Variance Tradeoff and describe regularization techniques: Ridge ($L_2$) and Lasso ($L_1$) regression penalty terms.
Appeared in:2082 Chaitra2081 Chaitra
#5Repeated 2 Times[8 Marks]Regression and Predictive Modeling
Explain Random Forest and Ensemble Learning methods. Compare Bagging (Bootstrap Aggregation) with Boosting (AdaBoost, Gradient Boosting) in terms of variance reduction and model accuracy.
Appeared in:2082 Chaitra2081 Chaitra

Modeling and Validation Processes

4 Questions
#1Repeated 2 Times[5 Marks]Modeling and Validation Processes
Why is K-fold cross validation considered the standard method for validating predictive models? Define training data, validation data, test data, and describe the step-by-step procedure of K-fold cross-validation.
Appeared in:2081 Chaitra
#2Repeated 2 Times[5 Marks]Modeling and Validation Processes
Given a classification test set of 50,000 samples with confusion matrix values: True Positive ($TP$) = 1000, False Positive ($FP$) = 1000, False Negative ($FN$) = 100, and True Negative ($TN$) = 47,900: (a) Calculate Accuracy, Precision, Recall, and F1-score. (b) Explain why Accuracy can be deceptive in highly imbalanced datasets compared to F1-score.
Appeared in:2081 Chaitra
#3Repeated 2 Times[4 Marks]Modeling and Validation Processes
Explain regression evaluation metrics: Mean Absolute Error (MAE), Mean Squared Error (MSE), Root Mean Squared Error (RMSE), and Coefficient of Determination ($R^2$). When is MAE preferred over RMSE?
Appeared in:2081 Chaitra
#4Repeated 2 Times[6 Marks]Modeling and Validation Processes
Explain Receiver Operating Characteristic (ROC) curve and Area Under Curve (AUC). How are True Positive Rate (Sensitivity) and False Positive Rate ($1 - \text{Specificity}$) plotted to compare classifier performance?
Appeared in:2082 Chaitra2081 Chaitra

Ethics and Recent Trends

3 Questions
#1Repeated 2 Times[4 Marks]Ethics and Recent Trends
Explain the key principles of the General Data Protection Regulation (GDPR). Discuss data privacy, user consent, algorithmic bias, and ethical considerations in deploying data science systems.
Appeared in:2081 Chaitra
#2Repeated 2 Times[6 Marks]Ethics and Recent Trends
Write short notes on: (a) Generative AI and Foundation Models in data science, (b) K-Means clustering algorithm, (c) ROC-AUC curve analysis.
Appeared in:2081 Chaitra
#3Repeated 2 Times[6 Marks]Ethics and Recent Trends
Discuss Data Ethics, Algorithmic Bias, and Fairness in AI/Data Science. How can historical bias in training datasets lead to unfair discrimination in automated loan approvals and hiring systems?
Appeared in:2082 Chaitra2081 Chaitra

Curriculum Syllabus & Course Topics

Sourced from TU curriculum portal
Full Syllabus (PDF)
Chapter-wise Units & Micro-Syllabus Topics (7 Units)

  1. 1. Introduction to Data Science

    • 1.1Overview of data science
    • 1.2Jargons of data science
    • 1.3Modern data ecosystem
    • 1.4Data science lifecycle
    • 1.5Trends, markets and applications of data science
    • 1.6Tools and technologies in data science
    • 1.7Data scientist and their roles

  2. 2. Mathematics for Data Science

    • 2.1Introduction to linear algebra for data science
    • 2.2Vectors, matrices and matrix factorization
    • 2.3Gradient descent for optimization
    • 2.4Introduction to probability and random variable
    • 2.5Probability distributions: Normal, Bernoulli, Binomial, Poisson
    • 2.6Descriptive and inferential statistics
    • 2.7Central limit theorem and sample distribution concepts
    • 2.8Normal approximation; hypothesis testing procedures: Tests about the mean of a normal population
    • 2.9The t-test, Z-tests for differences between two populations means, the two- sample t-test, confidence interval for mean of normal population
    • 2.10ANOVA

  3. 3. Data Understanding and Preprocessing

    • 3.1Types of data: Structured, unstructured, semi-structured
    • 3.2Data preprocessing requirements
    • 3.3Data sources and collection methods
    • 3.4Data cleaning and preparation
    • 3.5Data wrangling and associated tools
    • 3.6Data enrichment, validation and publishing
    • 3.7Data transformation and normalization
    • 3.8Dimensionality reduction linear factor model, principal component analysis (PCA)

  4. 4. Data Analysis

    • 4.1Data analytics: Descriptive, diagnostic, predictive and prescriptive analytics
    • 4.2Exploratory data analysis using descriptive statistics
    • 4.3Data visualization
    • 4.4Data visualization techniques
    • 4.5Principles of effective data visualization
    • 4.6Feature engineering and other aspects of data manipulation

  5. 5. Regression and Predictive Modeling

    • 5.1Empirical models, simple linear regression, MLE and least square estimator
    • 5.2Multiple linear regression, matrix approach to multiple linear regression, polynomial regression models, categorical regressors, indicator variables, selection of variables and model building
    • 5.3Logistic regression

  6. 6. Modeling and Validation Processes

    • 6.1Introduction to machine learning
    • 6.2Introduction to supervised, unsupervised and reinforcement learning
    • 6.3Modeling process, training /validating model, cross validation methods, predicting new observations interpretation
    • 6.4Measures for model performance and evaluation: Classification accuracy, confusion matrix, sensitivity, specificity, precision, recall, F-score, ROC curve, clustering performance measures, other measures

  7. 7. Ethics and Recent Trends

    • 7.1Ethical considerations in data science
    • 7.2Data privacy regulations
    • 7.3Responsible data usage
    • 7.4The five Cs
    • 7.5Future trends

Examination Scheme & Marks Distribution

Evaluation Structure

  • Final Board Theory Exam: 60 Marks (Pass mark: 24)
  • Internal Assessment: 40 Marks (Pass mark: 16)
  • Practical / Lab Exam: 25 or 50 Marks (Continuous lab evaluation + viva, where applicable)

* This is the general current IOE 60/40 scheme; verify course-specific details in the syllabus above.

Exam Preparation Guidelines

  • Review the available past examination paper to understand question styling, typical derivation topics, and marks allocation.
  • Cross-reference key answers with official syllabus units, standard textbooks, and lecture notes.
  • Structure answers with labeled diagrams, concise bullet points, and highlight final answers in numerical solutions.

Frequently Asked Questions (Foundation of Data Science)

Q: How can I download Foundation of Data Science past question papers?

You can preview or download the Foundation of Data Science question papers (PDF) directly using the built-in viewer on this page with zero redirects or paywalls.

Q: What is the pass mark for Foundation of Data Science?

The general current scheme is a 60-mark final theory exam and a 40-mark internal assessment, with pass marks of 24 and 16. Verify the course-specific syllabus above.

Q: Where can I find the complete syllabus for this subject?

The available chapter-wise syllabus and topic breakdown is indexed in the Syllabus section above, with links to the curriculum PDF source.

Authentic IOE Past Papers
Free Direct PDF Download
Curriculum Syllabus & Marking Scheme