1. COURSE SUMMARY

This module is intended to impart the learners the modern concepts of data mining and data ware housing with good practical skills. The automated extraction of hidden predictive information from databases can be done using the special software tools included in the lab work. Learners will also be trained to be familiar and skilled in existing software.

2. Learning Outcomes

A. Knowledge and Understanding

    Having successfully completed the module, students should be able to demonstrate  knowledge and understanding of:

1. Understand the basic concepts of data mining
2. Preprocess the data for mining applications
3. Have a basic knowledge on data warehouse and OLAP technology
4. Apply the association rules for mining the data
5. Design and deploy appropriate classification techniques
6. Cluster the high dimensional data for better organization of the data and Be able to detect anomalies from data

B. Cognitive/Intellectual skills/Application of Knowledge

     Having successfully completed the module, students should be able to:
     1-select relevant statistical methods for modelling data bases
     2-use data mining principle in development of solutions to specific computing problems involving enormous data
     3-apply knowledge and computing standards of Data warehousing to produce novel designs of software systems and data mining components
     4-critically assess design and research work done by other software professionals
     5-analyse failure in Data warehousing and take preventive measures

C. Communication/ICT/Numeracy/Analytic Techniques/Practical Skills

Having successfully completed the module, students should be able to:
    1-plan, manage conduct and report software research projects in data mining
    2-prepare technical report and deliver technical presentations on software Development/testing using data mining techniques
   3-Develop standards for Data warehousing and data mining software
   4-crtically asses research work done on Data manipulation
   5- Detect Data base failures and devise solutions
   6-demostrate practical applications of data mining

D. General transferable skills

Having successfully completed the module, students should be able to:
    1-Do life-long research on data
    2-Efficiently manage time and human resources in the manipulation of data
    3-Communicate effectively with other skilled data mining professionals/experts
    4-demonstrate numerical skills and problem solving techniques with new research work

3. INDICATIVE CONTENT

Data Mining: Introduction, Data preprocessing, Classification, Decision trees, Bayesian, Rulebased classification, Back propagation, Evaluating, Ensemble, KNN, Clustering, Partitioning, Hierarchical clustering, Density-based methods, Cluster evaluation, Association rule mining, Apriori, FP-growth, Eclat, , Web mining Applications of data mining , Data ,mining softwares. Case studies on WEKA, TANAGRA and similar softwares.

Data Warehousing concept: Definition Operational Data, Common Characteristics of Data Warehouse, Knowledge discovery and Decision Making, Knowledge discovery and Data Mining, Application of Data Warehouse.

Find User Data Access Tools: Data Warehouse Query Tools, Data Modeling Strategy – Star schema, Multi Fact Table Star Schema, Star with the Original Entry Relationship Model, Dimensional Model, OLAP, Relational OLAP, Multidimensional Database, Data Cube presentation of Fact Tables.

Data Warehouse, Architecture and Optimization: 3 Tier Architecture, Components of Warehouse, Classical Data Warehouse, Transportation of Data into the Data Warehouse, Data created in the Data Warehouse, Presentation of Data to End Users, Object Oriented System Architecture Definitions, Object Modeling Techniques. Implementing of the Application Design, Necessity of Data warehouse Metadata, Performance optimization, Data administration techniques.

4. LEARNING AND TEACHING STRATEGY

The module will be delivered through lectures, tutorial/practice sessions and group discussions.
In addition to the taught element, students will be expected to undertake practical case studies and do a mini project.

5. ASSESSMENT STRATEGY

Assessment on the programme is undertaken in accordance with the current Academic Regulations of the Institute.
Assessment Criteria:

•  For the examination setting and marking the UR-CST generic marking criteria will be used.
• For the assessment of the laboratory work, the CE&IT Laboratory assessment criteria will be used
•  For the assignment, criteria will be drawn up appropriate to the topic, based on the UR-CST generic marking criteria

6. STRATEGY FOR FEEDBACK AND STUDENT SUPPORT DURING MODULE

•  Interactive lecturing style, with opportunities for questions, and requirement to work on simple problems.
•  Peer marking of tutorial questions for formative feedback.
• Tutorial classes where students can ask questions and be lead through solutions as required.
•  Marked summative assessments (laboratory report and assignment) handed back to students, with comments.
•  Opportunities to consult lecturer and/or tutorial assistant in office hours.

7. INDICATIVE RESOURCES

• Jiawei Han and Micheline Kamber. (2011). Data Mining: Concepts and Techniques, Third Edition
• Thomas C. Hammergren. (2009).Data Warehousing For Dummies
•  Daniel T. Larose and Chantal D. Larose. (2015).Data Mining and Predictive Analytics
•  Online materials uploaded on the Learning Portal
•  Background Texts (include number in library or URL)
•  Journals8.

8. TEACHING TEAM :

Mrs. ALPHONSINE MUKABUNANI