GUG · Third Year B.Tech. Computer Science and Engineering · NEP 2020
Data Mining and Warehousing
STPECCSE506A · Programme Elective I · Semester V · 3 credits · IE 10 + mid-semester 10 + ESE 80
One of the Programme Elective I options.
Unit 1: Data Warehouse Foundations
9 hoursOLTP systems versus data warehouses; three-tier warehouse architecture, the ETL framework and the metadata repository; star, snowflake and fact constellation schemas, fact and dimension tables; roll-up, drill-down, slice, dice and pivot.
Examined in the 80-mark end-semester paper, and in the mid-semester exam if it is taught by then
Unit 2: Data Mining Fundamentals and Pre-processing
9 hoursThe KDD process; data mining functionalities and the types of data mined; data cleaning of missing and noisy values; data integration and correlation analysis; dimensionality and numerosity reduction; min-max and z-score normalisation, discretisation and concept hierarchies.
Examined in the 80-mark end-semester paper, and in the mid-semester exam if it is taught by then
- Data mining and the KDD process
- Data mining functionalities and task primitives
- Data cleaning and integration
- Data reduction and discretisation
- Normalisation and distance measures
Unit 3: Market Basket Analysis
9 hoursFrequent itemsets, support, confidence and lift; the Apriori algorithm, mining association rules and improving Apriori's efficiency; FP-tree construction and mining frequent patterns with FP-growth.
Examined in the 80-mark end-semester paper, and in the mid-semester exam if it is taught by then
- Frequent itemsets and association rules
- Apriori algorithm
- FP-growth algorithm
Unit 4: Introduction to Machine Learning
9 hoursMachine learning and its relation to data mining and AI; the machine learning pipeline; supervised, unsupervised, semi-supervised and reinforcement learning; overfitting and underfitting, the bias-variance trade-off, train/validation/test splits and cross-validation.
Examined in the 80-mark end-semester paper, and in the mid-semester exam if it is taught by then
- Introduction to machine learning
- Types of learning
- Regression basics and the bias–variance trade-off
- Evaluating classifiers: holdout, cross-validation and bootstrap
Unit 5: Supervised and Unsupervised Learning
9 hoursSimple and multiple linear regression, the cost function and gradient descent; logistic regression, the sigmoid and decision boundaries; k-nearest neighbours; k-means clustering and the elbow method; the confusion matrix, accuracy, precision, recall and F1, MAE and RMSE.
Examined in the 80-mark end-semester paper, and in the mid-semester exam if it is taught by then
Unit contents are summarised from the official GUG syllabus . AiCanCode.org is not affiliated with Gondwana University, Gadchiroli.