FIT3002 Applications of data mining - Semester 1, 2015

In the modern corporate world, data is viewed not only as a necessity for day-to-day operation, it is seen as a critical asset for decision making. However, raw data is of low value. Succinct generalisations are required before data gains high value. Data mining produces knowledge from data, making feasible sophisticated data-driven decision making. This unit will provide students with an understanding of the major components of the data mining process, the various methods and operations for data mining, knowledge of the applications and technical aspects of data mining, and an understanding of the major research issues in this area.

Mode of Delivery

Workload Requirements

Minimum total expected workload equals 12 hours per week comprising:

(a.) Contact hours for on-campus students:

• One 2-hour workshop
• One 2-hour laboratory (for 6 weeks)

(b.) Study schedule for off-campus students:

• Off-campus students generally do not attend lecture and tutorial sessions, however should plan to spend equivalent time working through the relevant resources and participating in discussion groups each week.

(c.) Additional requirements (all students):

• A minimum of 8 hours independent study per week for completing lab and project work, private study and revision.

See also Unit timetable information

Unit Relationships

Prohibitions

CSE3212, GCO3828

Prerequisites

FIT1004 or FIT2010 or equivalent

Chief Examiner

Campus Lecturer

Your feedback to Us

Previous Student Evaluations of this Unit

Based on previous student feedback on the topics on cluster analysis and anomaly detection, additional readings on their application were added to broaden students' knowledge in these areas.

Academic Overview

Learning Outcomes

• explain the motivation of data mining;
• explain why data mining is needed;
• explain the characteristics of major components of the data mining process;
• demonstrate the use of the basic data mining methods;
• analyse case studies to bridge the connection between hands-on experience and real-world applications;
• identify key and emerging application areas;
• use data mining tools to solve data mining problems.

Unit Schedule

*Unit Schedule details will be maintained and communicated to you via your learning system.

Teaching Approach

• Workshops
  This teaching and learning approach provides facilitated learning, exploration and peer learning.
• Laboratory-based classes
  This approach provides practical exploration and peer learning.

Assessment Summary

Examination (3 hours): 50%; In-semester assessment: 50%

Assessment Requirements

Assessment Policy

Assessment Tasks

Participation

Students are assessed on their participations in workshops and online activities in Moodle throughout the semester. This includes presentations and weekly participation in the discussion during the workshops.

This assessment will be made weekly and it is worth 20% of the total assessment.

Two assignment tasks are required to be completed by students in pairs. These assignments are worth 30% of the total assessment.

• Assessment task 1

  Title:

  Assignment 1

  Description:

  This assignment requires students to use the data mining tool WEKA to build a good performing model from a given set of data, and write a report describing the data mining process.

  Weighting:

  15%

  Criteria for assessment:

  • To get a Pass grade, students must perform data preparation/preprocessing, produce several different models and choose the best model, and submit a clearly written report describing the process. 
  • To get a better grade, students must show that they have performed extra data analysis and preprocessing, explored a wide range of different models and describe how the final model is produced and how it can be applied for future predictions.

  Members of a group are expected to contribute equally to the group work. Each member is to submit a peer review form independently to provide their assessment of every member's contribution.  Normally the marks awarded to group members will be the same, however if the peer review indicates an uneven contribution, the marker will investigate and if necessary apportion marks accordingly.

  More detailed criteria will be provided in the sample marksheet on the assignment web page.

  Due date:

  13 April 2015

• Assessment task 2

  Title:

  Assignment 2

  Description:

  This assignment requires students to use the data mining tool WEKA to explore several models and then choose one that will be likely to produce the largest profit within the budgetary constraint for a mass mailing campaign. Students are required to write a report to describe the process and analysis involved.

  Weighting:

  15%

  Criteria for assessment:

  • Must have a clear problem definition section that defines the inputs (and their types: nominal or numeric) and output; evaluation method and performance measure used (train and test using the given data sets and choose model based on profit).
  • Produce several different models.
  • Choose the best model which maximises profit in all parts of the process.
  • A clearly written report which shows the high level process taken.

  Members of a group are expected to contributed equally to the group work. Each member is to submit a peer review form independently to provide their assessment of every member's contribution.  Normally the marks awarded to group members will be the same, however if the peer review indicates an uneven contribution, the marker will investigate and if necessary apportion marks accordingly.

  More detailed criteria will be provided in the sample marksheet on the assignment web page.

  Due date:

  11 May 2015

• Assessment task 3

  Title:

  Weekly participation assessment

  Description:

  Students are required to participate in workshops and online activities in Moodle throughout the semester. For on-campus students this includes presentations and weekly participation in the discussions in the workshops. Off-campus students are required to do similar activities online.

  Weighting:

  20%

  Criteria for assessment:

  This is an individual assessment and assessed on participation rather than correctness.

  Due date:

  Weekly

Examinations

• Examination 1

  Weighting:

  50%

  Length:

  3 hours

  Type (open/closed book):

  Closed book

  Electronic devices allowed in the exam:

  None

Learning resources

Reading list

1. Kennedy, R.L., Lee, Y. Roy, B.V., Reed, C.D. & Lippman, R.P., Solving Data Mining Problems through Pattern Recognition, Prentice Hall, 1998.

2. Cabena, P., Hadjinian, P., Stadler, R., Verhees, J. & Zanasi, A., Discovering Data Mining: from concept to implementation, Prentice Hall, 1997.

3. Berry, J.A.M. & Linoff, G. Data Mining Techniques for Marketing, Sales, and Customer Support, John Wiley & Sons, 1997.

4. Tan, P-N, Steinbach, M. & Kumar, V. Introduction to Data Mining, Addison Wesley, 2006.

5. Han, J., Kamber & Pei, J. M. Data Mining: Concepts and Techniques, Morgan Kaufmann, Third Edition, 2011.

6. Dunham, M.H., Data Mining: Introductory and Advance Topics, Pearson Education, 2003.

7. Groth, R., Data Mining: Building competitive advantage, Prentice Hall, 2000.

8. Berson,. A., Smith, S. & Thearling, K., Building Data Mining Applications for CRM, McGraw Hill. 2000.

9. Berry, J.A.M. & Linoff, G. Mastering Data Mining: The Art and Science of Customer Relationship Management, John Wiley & Sons, 2000.

10. Mena, J. Data Mining Your Website. Digital Press, 1999.

11. Westphal, C. & Blaxton, T. Data Mining Solutions, John Wiley & Sons, 1998.

12. Quinlan, J.R. C4.5: Program for Machine Learning, Morgan Kaufmann, 1993.

13. Fayyad, U.M., Piatetsky-Shapiro, G., Smyth, P. & Uthurusamy, R. Advances in Knowledge Discovery and Data Mining, AAAI Press/MIT Press, 1996.

14. Vasant Dhar. Data Science and Prediction, Communications of the ACM, Vol. 56, No. 12, December 2013, pages 64-73.

Feedback to you

• Informal feedback on progress in labs/tutes
• Graded assignments with comments
• Other: Solutions to review questions and assignments

Extensions and penalties

Returning assignments

Assignment submission

Online submission

All assessments must be submitted electronically via the Moodle site for this unit, and must include a signed coversheet for each assessment item.

Required Resources

1. Software Title: WEKA, version 3.6 (http://www.cs.waikato.ac.nz/ml/weka/downloading.html)
2. Magnum OPUS version 4.6 (http://www.giwebb.com/downloads.html)

Prescribed text(s)

Witten, I.H., Frank, E. & Hall, M.A.. (2011). Data Mining: Practical Machine Learning Tools and Techniques. (3rd Edition) Morgan Kaufmann Publishers.

Other Information

Policies

Graduate Attributes Policy

Student Charter

Student services

Monash University Library

Disability Liaison Unit