ACCA7015 Assignment Help
Data Mining & Visualisation Assignment help
You are to analyse a database extract of at least 15000 records and 15 attributes and submit a report
upon the data mining processes used during this analysis. You may use one of the datasets on the UCI
Machine Learning Repository provided or find a suitable dataset elsewhere.
Your submission should include:
• A description of your chosen dataset, include attributes present in the data, the number of
instances, missing values, and other relevant characteristics.
• A discussion of the primary pre-processing of the chosen dataset in order to load it into
WEKA, including any Further pre-processing required by the dataset in order to prepare for
the pattern discovery stage
• A description of the analyses performed on the data. This should be a directed discovery
approach using classification, clustering and association analysis and should include
examples of data selection, model creation and pattern discovery.
• A discussion of any secondary pre-processing performed as the result of an analysis of the
data in order to perform further analyses.
• A discussion of any interesting patterns identified and how they would be reported back in
an appropriate business or scientific context.
• Reflection on the process and its results.
The report should be no more than 4500 words long and should include such graphics as are
appropriate to illustrate your answers.
Marks will be awarded for:
• A data set description (15%)
• Primary and secondary data pre-processing (25%)
• Data analysis (20%)
• Identification and reporting of results (20%)
• Reflection (10%)
• Report writing (10%)