JSAI2020

Presentation information

International Session

International Session » E-2 Machine learning

[2K5-ES-2] Machine learning: Multimedia

Wed. Jun 10, 2020 3:50 PM - 5:30 PM Room K (jsai2020online-11)

Chair: Hiroki Shibata (Tokyo Metropolitan University)

5:10 PM - 5:30 PM

[2K5-ES-2-05] Realization of video creative for View Through Rate prediction

〇Tsogtbayar Nanzaddorj1,2 (1. Dentsu Inc., 2. Data Artist Inc.)

Keywords:prediction, convolutional neural network, video through rate, digital marketing

With an increase in usage of social network and various online services, Digital Marketing is getting popular for businesses to reach customers. One of the challenge to reach as many as potential customers, and turn them to use their services or let them buy their product. VTR or View Through Rate is an indicator that shows how efficient the strategy was for a creative. This work is to find what features of video result to higher VTR. It is said that first few seconds of a video are important for VTR result. Data is based on Facebook creative videos and VTR value.

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.

Password