Note: This website was automatically translated, so some terms or nuances may not be completely accurate.
Dentsu Inc. Releases New Version of AI TV Ratings Prediction System "SHAREST_RT"
The text of the Dentsu Inc. news release distributed on October 26 is as follows.
October 26, 2018
― Expanding Coverage Area and Improving Accuracy, Now Capable of Predicting Time-Shifted Viewership Ratings ―
Dentsu Inc. (Headquarters: Minato-ku, Tokyo; President: Toshihiro Yamamoto) has developed and released an upgraded version of its AI-powered TV ratings prediction system, "SHAREST_RT(※)" (Share Rest RT). The new system incorporates an expanded coverage area to include the Tokyo, Osaka, and Nagoya regions, support for predicting time-shifted viewing, and an expanded range of target audiences for prediction.
In June 2017, Dentsu jointly developed and launched "SHAREST (beta version)" with Data Artist Inc. (acquired as a subsidiary in February this year), a company with strengths in AI development. This system uses deep learning with training data including historical ratings, program genres, cast information, and online content viewing trends to predict TV ratings one week prior to broadcast.
With the new "SHAREST_RT," we have enhanced the system by expanding the input variables, enabling more stable and accurate predictions of TV ratings for the week preceding broadcast.
This "SHAREST_RT" enables the advanced management of TV commercial assets, which is rapidly expanding. For example, it allows for the optimal allocation of multiple TV commercial assets targeting different audiences based on viewership predictions, ensuring they air during the most suitable programs. This ultimately maximizes advertising effectiveness.
Additionally, the new system incorporates the "RICH FLOW" database infrastructure to enhance prediction accuracy. Moving forward, we will expand this database by feeding in reliably available social media data, weather-related data, various panel data, and more. This will further improve prediction accuracy and diversify the range of measurable indicators.
Traditionally, when allocating commercial materials from multiple brands to advertising slots based on predicted ratings, humans often performed the ratings forecasting, creating a significant operational burden. Automating ratings forecasting with AI is expected to greatly enhance operational efficiency.
Moving forward, we will continue to leverage AI across diverse marketing data related to media, contributing to the creation of new value for our client companies.
※ "RT" stands for Recent Trend
＜"SHAREST" Logo＞
＜"SHAREST_RT" Concept Diagram＞
End
Dentsu Inc. News Release
http://www.dentsu.co.jp/news/release/2018/1026-009630.html
Was this article helpful?
Share this article
