CS-703-B Data Mining and Warehousing - Dec 2025 Question Paper

Under each question, How to answer lists the points an answer should cover, outlined by CampusPrep from the syllabus. Check the details against your textbook.

1. 7 Marks
   aDefine data warehousing. Explain the architecture of a data warehouse with a suitable diagram.
   How to answer

   • Definition of data warehousing as subject-oriented, integrated, time-variant, non-volatile collection for decision support.
   • Three-tier architecture: data sources, ETL/staging, warehouse, data marts, OLAP/metadata, front-end tools.
   • Explain data flow and components with functions.
   • Neat labelled diagram of architecture.
2. 7 Marks
   bDescribe the techniques used for data preprocessing in data warehousing.
   How to answer

   • Need for preprocessing for quality and integration.
   • Data cleaning: missing values, noisy data.
   • Data integration, transformation, reduction.
   • Discretization and concept hierarchy generation.
3. 7 Marks
   aWhat are the different types of data warehouse schemas? Explain with examples.
   How to answer

   • Star schema: fact table and denormalized dimensions with example.
   • Snowflake schema: normalized dimensions with example.
   • Fact constellation/galaxy schema with example.
   • Comparison and use cases with diagrams.
4. 7 Marks
   bDefine OLAP and Compare different types of OLAP servers.
   How to answer

   • Definition of OLAP for multidimensional analysis.
   • Types: ROLAP, MOLAP, HOLAP with architecture.
   • Comparison on storage, performance, scalability.
   • Examples and suitability.
5. 7 Marks
   aDescribe backup and recovery strategies in data warehouse environments.
   How to answer

   • Need for backup/recovery in large historical warehouses.
   • Full, incremental and differential backups.
   • Recovery strategies, logging, standby and disaster recovery.
   • Testing and operational considerations.
6. 7 Marks
   bExplain the role of Hardware components in Operational Design of Data Warehouse.
   How to answer

   • Role of CPU, memory, storage, I/O and parallelism.
   • RAID, partitioning and indexing support.
   • Network and scalability for ETL and OLAP workload.
   • Hardware sizing for performance and availability.
7. 7 Marks
   aDefine data mining and differentiate it from knowledge discovery in databases.
   How to answer

   • Definition of data mining as extraction of patterns.
   • KDD process steps and data mining as core step.
   • Differences in scope, process and output.
   • Example to illustrate distinction.
8. 7 Marks
   bDescribe similarity measures and their role in clustering and classification.
   How to answer

   • Concept of similarity/distance measures.
   • Euclidean, Manhattan, cosine, Jaccard examples.
   • Role in cluster formation and nearest class assignment.
   • Effect of measure choice on results.
9. 7 Marks
   aDiscuss the key differences between supervised and unsupervised learning with examples.
   How to answer

   • Definitions of supervised with labels vs unsupervised without labels.
   • Comparison on goal, data, training and evaluation.
   • Examples: classification/regression vs clustering/association.
   • Summary table of differences.
10. 7 Marks
    bDescribe the k-Nearest Neighbors (k-NN) algorithm and its role in classification.
    How to answer

    • Principle of lazy instance-based learning and distance.
    • Steps: choose k, compute distances, majority vote.
    • Role in classification with example.
    • Advantages, limitations and choice of k.
11. 7 Marks
    aWhat are rule-based classifiers? Explain how they derive classification rules from data.
    How to answer

    • Definition of rule-based classifiers using IF-THEN rules.
    • Methods: direct from data, sequential covering, RIPPER.
    • Rule pruning, coverage and accuracy measures.
    • Example rule set derivation.
12. 7 Marks
    bDefine probabilistic classifiers and explain how they differ why are they useful in uncertain environments?
    How to answer

    • Definition using posterior probabilities e.g. Naive Bayes.
    • Probabilistic vs deterministic decision and uncertainty handling.
    • Usefulness with noisy, incomplete, overlapping data.
    • Example of probability-based prediction.
13. 7 Marks
    aDefine clustering and explain its importance in unsupervised learning.
    How to answer

    • Definition of clustering as grouping similar objects.
    • Unsupervised nature without labels.
    • Importance: pattern discovery, summarization, preprocessing.
    • Applications with examples.
14. 7 Marks
    bWhat are association rules? Differentiate Apriori and FP-Growth algorithms.
    How to answer

    • Definition of association rules with support and confidence.
    • Apriori: candidate generation and pruning steps.
    • FP-Growth: FP-tree without candidates.
    • Comparison on scans, memory and performance.
15. 14 Marks
    Write short notes on any **two** :

    1. a)OLAP Queries and Operations
    2. b)Summary statistics and Data distributions
    3. c)Multidimensional Data model
    4. d)Neural network-based algorithms
    How to answer

    • Select any two topics from four options.
    • For each: definition, key concepts and operations/types.
    • Diagrams/examples where applicable.
    • Applications and significance.