no code implementations • 31 May 2023 • Kojiro Iizuka, Yoshifumi Seki, Makoto P. Kato
We conducted a service log analysis and showed that sessions with high-quality news article exposure had more ad consumption than those with low-quality news article exposure.
no code implementations • 31 May 2023 • Kojiro Iizuka, Yoshifumi Seki, Makoto P. Kato
The proposed method involves (1) the decomposition of the post-click metric measurement of a ranking into a click model estimation and a post-click metric measurement of each item in the ranking, and (2) interleaving of multiple rankings to produce a single ranking that preferentially exposes items possessing a high population variance.
no code implementations • 2 Apr 2022 • Shunsuke Kitada, Hitoshi Iyatomi, Yoshifumi Seki
To improve the prediction performance for the two different types of discontinuations and for the ad creatives that contribute to sales, we introduce two new techniques: (1) a two-term estimation technique with multi-task learning and (2) a click-through rate-weighting technique for the loss function.
no code implementations • 27 Dec 2020 • Ryosuke Homma, Yoshifumi Seki, Mitsuo Yoshida, Kyoji Umemura
We hypothesize that content with short dwell time is not always low quality and does not always have low user engagement, but is instead related to user interest.
no code implementations • 27 Dec 2020 • Kenshin Sekimoto, Yoshifumi Seki, Mitsuo Yoshida, Kyoji Umemura
Next, we compared RTs and Likes for each category and confirmed that the tendency of categories is different.
no code implementations • 3 Sep 2019 • Takeshi Yoneda, Shunsuke Kozawa, Keisuke Osone, Yukinori Koide, Yosuke Abe, Yoshifumi Seki
Existing studies have not fully discussed system architecture, so a major contribution of this paper is that we demonstrate a system architecture and realize our algorithms and a configuration example implemented on top of Amazon Web Services.
no code implementations • 2 Sep 2019 • Yoshifumi Seki, Mitsuo Yoshida
Then, the bias of keywords between attributes was discovered, keywords with bias in behavior among the attributes were found using parameters of regression analysis.
no code implementations • 23 Aug 2019 • Yoshifumi Seki, Mitsuo Yoshida
We also found a large difference by category in the correlation value between dwell time and length of news page.
1 code implementation • 19 Jul 2019 • Kojiro Iizuka, Takeshi Yoneda, Yoshifumi Seki
We clarify the challenges of applying this method to personalized rankings.
1 code implementation • 17 May 2019 • Shunsuke Kitada, Hitoshi Iyatomi, Yoshifumi Seki
Furthermore, conditional attention focuses attention of each ad creative with the consideration of its genre and target gender, thus improving conversion prediction accuracy.