IMPORTANT: If you get a limit violation error, your analysis is incorrect. Look
IMPORTANT: If you get a limit violation error, your analysis is incorrect. Look at your data carefully and think what should be included in your Data Range. Reopen the Excel file and start over.
Please adjust Data Range in the pop-up window, even if you selected the range correctly in Excel.
Please complete the problems using Excel, answer the questions asked in Word, then submit both files.
Excel worksheets contains a set of receipt data for a bakery where each row represents a different customer’s purchase. For each row, a 1 indicates they purchased that product and a 0 means they did not. In total, there are 50 different products the bakery sells, and the owner is interested in determining any association rules in the purchase patterns of their customers.
Complete an Association Rule analysis (AR analysis) on the following data using a minimum confidence percentage of 75% and a minimum support of 10.
Answer the following questions:
How many rules did Association Rule analysis found?
Pick any one of the resultant rules developed by your analysis and explain each of the columns in the output using that rule as an example.
Select the 5 rules you would recommend to the bakery owner and explain your reasoning.
Please upload the completed EXCEL workbook which shows your association rule analysis worksheets and you can type your answers to the questions in the some worksheet. In other words, your AR analysis worksheets and your answers should be in the same EXCEL file. Upload one EXCEL file to Canvas.
-answer to the first question is incorrect. Two rules is the wrong answer. You should get well over 30 rules. Because of this error, all your answers (Question 2 and 3) are also incorrect. When you first click on Association Rules in Excel Data Science add-in, it will give you a popup window. Make sure you enter the correct data range in the “Data range” field. You should exclude column A from the analysis because it is not useful for this analysis and you will select all other columns and all rows. You should manually type in the data range values in this field and make sure you anchor ($) the rows and the columns in this data field ie enter $B$1:$AY$401.
– In this same window, please make sure the radio button next to “Data in binary matrix format” is selected. THIS IS IMPORTANT. If you don’t do this, you will get incorrect results.
– Also, in the same window, please enter the values for Minimum support and minimum confidence that are given in the homework 2 problem statement.
– When you run the AR analysis in Excel, you will automatically get a new worksheet called “AR_output”. Please save this file. I need to see this in the Excel file that you email me.
-Please read the 3 questions in the homework carefully and answer the 3 questions in a new worksheet in the same Excel file, or you can email me a Word document with your answers to the 3 questions. You will need to explain the different terms such as confidence, lift ratio, etc.
Leave a Reply