Presentation information

General Session

General Session » J-5 Web intelligence

[4M2-GS-5] Web intelligence: Web intelligence

Fri. Jun 12, 2020 12:00 PM - 1:40 PM Room M (jsai2020online-13)


12:40 PM - 1:00 PM

[4M2-GS-5-03] Click-Through Rate Prediction with Confidence for News Headlines Using Natural Gradient Boosting

〇Yuki Nakamura1, Tomohide Shibata2, Hayato Kobayashi2,3, Nobuyuki Shimizu2, Hiroaki Taguchi2 (1. Keio University, 2. Yahoo Japan Corporation , 3. RIKEN AIP)

Keywords:News Headline, Click-Through Rate Prediction , Natural Gradient Boosting

News headlines in online news services play an important role in expressing the content of news articles and in stimulating users to click article pages. If their click-through rate (CTR) can be predicted, it will be useful as reference information for news editors to refine headlines. However, it is difficult to accurately predict the CTR because it is influenced by many external factors such as timing and popularity of news topics. In this study, we propose a method for predicting the CTR of news headlines with confidence using a regression model called natural gradient boosting (NGBoost) that predicts a distribution. In order to confirm the usefulness of our proposed method, we perform an evaluation experiment using the A/B test log of news headlines and discuss the relationship between confidence and prediction performance.

Authentication for paper PDF access

A password is required to view paper PDFs. If you are a registered participant, please log on the site from Participant Log In.
You could view the PDF with entering the PDF viewing password bellow.