This site uses different types of cookies, including analytics and functional cookies (its own and from other sites). To change your cookie settings or find out more, click here. If you continue browsing our website, you accept these cookies.
I would like to do a cluster analysis (K-centroids) to identify the customer profiles for each of my three stores. However, only three of the attributes are numeric (Member sales amount, No. of member transaction, member sales quantity). Would it be possible to turn the other ones, such as merchandising category, gender , into numeric values for my analysis? Attached please find the transaction data with basic demographics. Thanks!
Yes - take those values, and have individual summarise tools for each dimension, gender for example. Then, take a recordID and name it the dimenion but ID, gender_id for example. Then, join that back onto the main dataset and replace the text with the ID value and use that in the clustering. Then, afterwards re-join the ID to get text value back.