COURSEWORK ASSIGNMENT

Academic Year 2020/21

Module Code:         BNM861

Module Name:        Data Mining and Web Analytics

Module Leader:       Ali Emrouznejad

Coursework Title:

Application of Data Mining and Web Analytics to Real Data

Task Details/Description:

This assignment focuses on using data mining algorithms to develop a model to solve a typical business problem in a real case study. This assignment has two parts (a group part and an individual part). Please see blackboard for the group names.

Group part (35%)

1. Select a company or industry sector of interest to you. Your first task is to try to gain as much insight as possible into the business goals and explain how data mining can be used to analysis data within the selected company/industry. Explain how data mining could help this case. (5%)

2. Find a source of numerical data for that topic, download a relevant dataset, clean the data and prepare a data quality report. (15%)

3. Use data mining methods presented in the class, visualize the data and prepare a report on descriptive analysis. (15%)

Individual part (35%)

4. Identify a specific problem within this industry that can be addressed using the data mining methods. Use appropriate data mining methods to solve the problem, analyse the results from the data sources and decide whether they are useful for making a business decision and if so what decision or type of decision would you propose. You will need to use various data mining methods in the IBM Modeler software. (35%)

Note:

1. When you decide on your industry/topic, meet with the instructors to have this agreed and to get relevant advice.

2. Coursework submitted must include code and screen shots of the software used as an appendix. You should also upload the software and the dataset to system. The description of the problem, method and analysis should be no more than 3000 words long excluding tables and figures, etc. Screenshots, tables and figures can be included in the appendix.

3. Each student should submit both group and individual parts as one document.

Module Learning Outcomes Assessed:

1. Know the fundamentals of business intelligence and its application to business decision making

2. Demonstrate an understanding of the data and resources available on the web of relevance to business intelligence and be able to access such structured and unstructured data

3. Practice with leading data mining methods and their applications to real-world problems

4. Apply the practical experience and the theoretical insight needed to reveal patterns and valuable information hidden in large data sets;

Presentation Requirements:

Word Count:

Maximum 3000 words excluding tables /figures and appendix.

Font Size: 11

Line Spacing: 1.5

Please submit one PDF per individual, also upload the software and the dataset (s) you used for this coursework

Submission Date & Time:

xxxxxxx 12:00 noon UK time

Assessment Weighting for the Module:

70%

Assessment Criteria