RTMNU · Third Year B.Tech Artificial Intelligence · NEP 2020
Data Mining and Warehousing
BAI6T23 · Elective II · Semester VI · 3 credits · College 30 + university 70
One of the Elective II options.
Unit 1: Introduction to Data Mining
6 hoursMotivation for and importance of data mining, kinds of data, functionalities and patterns, interestingness, classification of data mining systems, task primitives, and integration with a database or warehouse.
Examined in the 70-mark end-semester paper
- Data mining and the KDD process
- Data mining functionalities and task primitives
Unit 2: Data Preprocessing and Data Warehousing
8 hoursData sets and attribute values, basic statistical descriptions, visualisation, similarity, quality, cleaning and integration, reduction, transformation and discretisation; data warehouse concepts, data cubes and OLAP, and generalisation by attribute-oriented induction.
Examined in the 70-mark end-semester paper
- Attribute and data types
- Measures of central tendency and spread
- Distance measures: Euclidean, Manhattan, Minkowski and Hamming
- Data cleaning and integration
- Data reduction
- Data warehouse architecture
- Data marts and OLAP cubes
- OLAP operations
- Data generalisation by attribute-oriented induction
Unit 3: Mining Frequent Patterns
6 hoursFrequent patterns, associations and correlations, the Apriori and FP-growth algorithms, mining kinds of association rules and pattern evaluation.
Examined in the 70-mark end-semester paper
- Association rules
- Association rules and Apriori
- FP-growth algorithm
- Correlation analysis and constraint-based association mining
Unit 4: Classification
7 hoursDecision tree induction, Bayes classification, rule-based classification, classification by neural networks, model evaluation and selection, and ensemble methods to improve accuracy.
Examined in the 70-mark end-semester paper
- Classification in BI
- Decision tree learning and overfitting
- Bayesian learning and naive Bayes
- Rule-based classification
- Perceptron and multilayer networks
- Cross-validation and model evaluation
- Bagging and random forests
- Boosting and stacking
Unit 5: Cluster Analysis
6 hoursClustering structures and approaches: partitioning, hierarchical, density-based and grid-based methods, and evaluating clusters.
Examined in the 70-mark end-semester paper
- Clustering in BI
- K-means and choosing k
- K-medoids and K-prototype
- Hierarchical clustering
- DBSCAN
- Grid-based clustering methods
- Evaluating clusters
Unit contents are summarised from the official RTMNU syllabus . AiCanCode.org is not affiliated with Rashtrasant Tukadoji Maharaj Nagpur University (RTMNU).