Abstract:
This study focuses on predicting online shopper buying intentions through the application
of prominent machine learning algorithms. The algorithms considered for analysis include
Support Vector Machine (SVM), Random Forest (RF), k-Nearest Neighbors (KNN), Naive
Bayes (NVC), and Logistic Regression (LR). The research follows a systematic approach
involving data collection, preprocessing, feature selection/engineering, data splitting, model
training, hyperparameter tuning, model evaluation, and comparison. The performance of
each algorithm is assessed using appropriate evaluation metrics, such as accuracy, precision,
recall, F1-score, and ROC-AUC. The selected algorithm is determined based on its ability to
generalize effectively to unseen data and provide accurate predictions. The study underscores
the significance of algorithm choice, feature quality, and model monitoring for real-world
deployment, emphasizing a continuous improvement cycle to enhance predictive capabilities
over time.
