04 Machine Learning - Solution

<p><strong>Learning objective: </strong>In this exercise you will train and evaluate supervised and unsupervised machine learning models.</p><p><strong>Workflow description:</strong></p><p>The same customer transaction data set from the demo is used in this exercise, with some additional features on the loyalty program membership information.</p><ol><li><p>The <strong><em>Loading Customer Data</em></strong> metanode reads the customer information as well as the loyalty program membership information.</p></li><li><p>Training a classification model to predict the membership status (<strong><em>Member</em></strong> or <strong><em>Gold</em></strong>). A decision tree model is trained, and its performance is evaluated. (<strong><em>Activity I</em></strong>)</p></li><li><p>Training a linear regression model to predict the Total spending with the number of purchased items and the loyalty program points. The goodness-of-fit of the trained model is then evaluated. (<strong><em>Activity II</em></strong>)</p></li><li><p>Grouping customers with similar characteristics into clusters by k-Means clustering. Visualizing the resulting clusters. (<strong><em>Activity III</em></strong>)</p></li></ol>