Despite the growing importance of affiliate marketing in influencing consumer behavior, existing research has not adequately explored how various affiliate marketing factors affect consumers’ purchasing decisions. The study aims to fill this gap by applying machine learning model to identify the overall profile of customers with purchase intentions, informed by seven independent variables related to affiliate marketing. A decision tree algorithm was applied to classify customers likely to have purchase intention through affiliate marketing. The model exhibited a F1-Score of 0.905 and a Recall of 0.932 which is regarded as good classification accuracy. The decision tree rules and explored to understand the general characteristics of customers who tend to have purchase intention through affiliate marketing strategies. This study shows how marketing professionals can leverage machine learning to make informed decisions and understand their customers.