Data Handling and Business Intelligence
“Students should explore the use of excel to assess and analyse the problem and to investigate what WEKA can do for them”.
“The data analytics company you work for has been approached by ‘We Sell Things’ an online retailer operating in Canada. Over the past few years they have noticed a reduction in profits and are not sure why this should be the case”.
Therefore, you are writing a report to the MD of We Sell Things analysing the spreadsheet they have provided you.
The report will be in the form of a word document with screenshots from your Excel spreadsheet in part 1 and from WEKA in part 2. These files/workings then need to be put into a zip file with your report and uploaded to TurnitIn/Moodle.
You are using real data, from an actual company, so there may be no obvious, easy solutions (as is the case in the real world).
Part 1
Your analysis of the data will try and highlight any areas/categories where there maybe problems in terms of profitability e.g. geographic areas, product areas or distribution areas etc. Using the skills that you have learnt from Excel you should be able to show these less profitable areas/categories and highlight them as areas that the company needs to investigate further.
The question suggests as a bear minimum you demonstrate the use of IF, LOOKUP, PIVOT TABLES, charts and graphs in your analysis i.e. using them with the data from the question. More advanced students may want to add other commands.
You will have to use PIVOT TABLE as the spreadsheet is so large.
You will also need to critically evaluate the strengths of using Excel for pre-processing the data, analysing the data and visualising the data. This will be based on your own experience of using EXCEL as well as consulting textbooks.
Part 2
Use the same data set to explain the data mining approaches that might be employed to find out more about customers using more sophisticated environment such as WEKA.
Also you will need to evaluate the strengths of using WEKA as a data analysis tool (in comparison with Excel) this will be again based partly on self-reflection and partly on reading around the subject.
Higher marks will be given to students who can give clear examples of how using the data set WEKA can do for them.
