Fusion Enhanced Click-Through-Rate Prediction Füzyon Güçlendirmeli Tiklama Orani Tahmini

Bayraktar M., Gökce F. C., Aksu D., Altingövde I. S., Karagöz P., Toroslu I. H.

31st IEEE Conference on Signal Processing and Communications Applications, SIU 2023, İstanbul, Türkiye, 5 - 08 Temmuz 2023 identifier identifier

  • Yayın Türü: Bildiri / Tam Metin Bildiri
  • Doi Numarası: 10.1109/siu59756.2023.10223844
  • Basıldığı Şehir: İstanbul
  • Basıldığı Ülke: Türkiye
  • Anahtar Kelimeler: Click-Through Rate (CTR), Fusion, Online advertising, Ranking
  • Orta Doğu Teknik Üniversitesi Adresli: Evet

Özet

In this study, the effects of combining multiple models to increase the accuracy of Click-Through Rate (CTR) prediction, which is a critical task in online advertising, product marketing, and recommendation systems, have been examined. Traditional CTR prediction methods use a single model developed for this purpose and therefore cannot capture some complex relationships. In this study, the aim is to increase the accuracy of CTR prediction in terms of different metrics by combining multiple models using the ranx library. The experimental results show that the proposed method achieve better results than CTR prediction models based on a single model used in previous studies. These results indicate that the development of different and new combination methods could also be beneficial.