Akademik Veri Yönetim Sistemi
JOURNAL OF POLYTECHNIC-POLITEKNIK DERGISI, 2024 (ESCI)
In e-commerce, predicting click-through rates (CTR) is crucial to anticipating user behavior. User historical data can be used to extract interests and enhance CTR prediction, leading to higher accuracy. In this study, a generative adversarial network (GAN) has been used to tackle the issue of an insufficient dataset for click-through rates. Furthermore, six different machine learning algorithms have been assessed for predicting ad click behavior. For the experimental study, we obtained user demographic and online activity data from Kaggle, along with a binary label indicating ad clicks. To enhance the model's performance, we employed a GAN for data augmentation and generated additional training examples. We compared the machine-learning algorithm's outcomes with and without GAN-based data augmentation to evaluate its predicted accuracy. According to the findings, most algorithms have increased sensitivity and specificity after utilizing GAN to augment the data, indicating that the generated data has improved their ability to accurately distinguish positive and negative events. GAN-based data augmentation boosted all models to varying degrees, according to the findings.