← Back to Publications List

Predicting User Engagement with Online Advertisements: A Comparative Study of Machine Learning Models

Students & Supervisors

Student Authors
Tamal Paul
Bachelor of Science in Computer Science & Engineering, FST
Saptanil Ghose
Bachelor of Science in Computer Science & Engineering, FST
Samiha Hossain
Bachelor of Science in Computer Science & Engineering, FST
Anik Sen
Bachelor of Science in Computer Science & Engineering, FST
Supervisors
Firoz Ahmed
Professor, Faculty, FST

Abstract

As online marketing continues to gain prominence, accu rately predicting user behavior remains a significant challenge due to the complexity of human actions. To enhance advertisement click pre dictions and, by extension, digital marketing strategies, this study uti lizes advanced machine learning (ML) techniques. The dataset undergoes preprocessing steps, including handling missing values, feature scaling, and one-hot encoding. Several classifiers, including Logistic Regression (LR), Random Forest (RF), Support Vector Machine (SVM), XGBoost, LightGBM, Artificial Neural Networks (ANN), and Recurrent Neural Networks (RNN), are evaluated. An ensemble model combining LR, RF, and SVM is developed, achieving superior performance with an accuracy of 98% and an AUCof 0.99. This research contributes to advancing intel ligent ad engagement prediction, providing advertisers with a powerful tool to maximize impact and efficiency in the digital marketplace.

Keywords

MachineLearning Advertisement Ensemble Model Online Marketing Prediction

Publication Details

  • Type of Publication:
  • Conference Name: 3rd International Conference on Big Data, IoT and Machine Learning (BIM 2025)
  • Date of Conference: 25/09/2025 - 25/09/2025
  • Venue: Dhaka International University (DIU)
  • Organizer: Department of CSE and EEE, DIU