What question did this study set out to answer?

The study aims to improve machine learning model performance for predicting click-through rates in digital advertising.

February 2, 2026Chaos and fractals.Open Access

Ad-Click Prediction Enhanced by Nonlinear Dynamics-Inspired Feature Extraction and Ensemble Optimization

View Full Paper

Ask AI

Bookmark

Authors

Ensemble Models Enhance Click-Through Rate Predictions in Digital Advertising, suggesting improved accuracy.

The study aims to improve machine learning model performance for predicting click-through rates in digital advertising.
Applied logistic regression as a baseline model using the Click-Through Rate Prediction dataset from Kaggle.
Used nonlinear dynamics-inspired feature extraction techniques involving TF-IDF and Word2Vec embeddings.
Implemented hyperparameter optimization techniques to refine model performance.
Constructed ensemble architectures with logistic regression, XGBoost, random forest, and support vector machine classifiers.
Achieved an F1-score of 0.8694 with the optimized ensemble model.
Demonstrated a 12.7% improvement in prediction accuracy over the baseline logistic regression model.

Çağ et al. (2026) studied this question.

View Full Paper

Ask AI

Bookmark