Predicting Consumer Purchasing Behavior Using SVM and Random Forest Classification Methods

Consumer purchasing behavior is vital for online retailers, marketers, and customer relationship managers. This study explores two popular machine learning techniques—Support Vector Machine (SVM) and Random Forest—to predict purchasing intent based on a dataset of customer demographics and behavioral attributes. Using preprocessing, exploratory analysis, model tuning, and evaluation, we compare the performance of these algorithms in binary classification. Experimental results show that while both methods perform well, Random Forest demonstrates superior accuracy, robustness, and feature importance interpretability.