This is a required assignment that counts towards programme completion. [50 points] Learning outcome addressed: 2. Segment customers using the three Ws (who, what and why). 3. Use machine learning to segment customers. To complete this activity, respond to ONE of the following prompts. If you are interested in the analytics portion of this module, the ‘Analytics path’ will be of more interest. If you feel uncomfortable with the k-means algorithm and R tutorial, the ‘Non-analytics’ path may be more suitable. Analytics path:You will analyse data from 40 respondents who rated their perceived importance of a number of shop and product attributes when buying office equipment. You should use cluster analysis to find clusters of observations – in this case, clusters of respondents. These clusters will have different profiles (e.g. one cluster may attach importance to price and return policy; the other may attach importance to a variety of choice and quality of service). Please download the following file for this exercise. Required activity 135_Analytics Path (pdf) The variables in the data set include: respondent_id: identifies each unique respondent. variety_of_choice: rates the level of perceived importance of each choice. electronics and furniture: identify the frequency of purchasing electronic products and furniture, respectively. quality_of_service, low_prices and return_policy: rates the level of perceived importance of service quality, low price and return policy, respectively. professional: a dummy variable that takes a value of 1 if the respondent is a professional and 0 otherwise. income: the annual income (in thousands) per respondent. age: the age per respondent. All rating variables (i.e. all variables except respondent_id) range between 1 and 9, with 1 being the lowest and 9 being the highest. Apply the average silhouette method to help the organisation segment its respondents. Your submissions should answer the following questions: What is the optimal number of clusters using each method? How do you describe different clusters of respondents (as informed by the variables available in the data set)? What marketing strategies (e.g. targeting) did you come up with for this organisation in order to improve future business performance and customer satisfaction? Non-analytics path: Select an organisation of your choice and explore its potential segments. You can use one or a combination of art-based or traditional segmentation approaches (e.g. psychographic segmentation, job-based segmentation or demographic segmentation) to segment the customers of your chosen organisation. Your submission should include: The name of the organisation you selected. A description of the technique or techniques you used. A description of the variables you will use for your segmentation. An explanation of why you selected the techniques and variables you did. A discussion of how you might be able to apply k-means clustering to supplement your art-based segmentation. Please note that you can replace your submission with a new copy until the submission deadline. To do this, you will need to delete your previous submission. You will not be able to retrieve older versions once you submit a new version of your assignment. So, the last version of the submission will cou https://realpython.com/k-means-clustering-python/
The post K-Means Clustering in Python: A Practical Guide first appeared on COMPLIANT PAPERS.