| Presentation | 2024-03-04 Conversion Prediction in Internet Advertising Using the Law of Diminishing Marginal Utility Keiya Unno, Daichi Iwata, Hiroaki Tanaka, Masato Uchida, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | The importance of Internet advertising in marketing is increasing every year. An advertising agency is using machine learning to predict future advertising effectiveness in order to optimize budget allocation to media for distribution. However, due to the limited information available to the agency, only simple regression can be performed, and the accuracy is inadequate. In a previous study, it was shown that accuracy can be improved by focusing on a more detailed advertising hierarchy and decomposing the forecasts. However, the model did not accurately take into account the law of diminishing marginal utility that exists between advertising cost and advertising effectiveness. Therefore, we take cumulative values as a new preprocessing. We show that this preprocessing successfully incorporates the law of diminishing marginal utility and significantly improves the prediction accuracy. In the evaluation experiments of the previous study, evaluation was conducted on a single advertising hierarchy, but it is also important to conduct evaluation on different hierarchies depending on the purpose. Therefore, in this study, we evaluate model performance at multiple hierarchies. The effectiveness of our method was verified through experiments using actual ad log data. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | Machine Learning / Advertisements on the Internet |
| Paper # | PRMU2023-80 |
| Date of Issue | 2024-02-25 (PRMU) |
| Conference Information | |
| Committee | PRMU / IBISML / IPSJ-CVIM |
|---|---|
| Conference Date | 2024/3/3(2days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | Hiroshima Univ. Higashi-Hiroshima campus |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | |
| Chair | Kunio Kashio(NTT) / Masashi Sugiyama(Univ. of Tokyo) / 日浦 慎作(兵庫県立大) |
| Vice Chair | Takuya Funatomi(NAIST) / Go Irie(Tokyo Univ. of Science) / Toshihiro Kamishima(AIST) / Koji Tsuda(Univ. of Tokyo) |
| Secretary | Takuya Funatomi(Tokyo Inst. of Tech.) / Go Irie(Riken) / Toshihiro Kamishima(NTT) / Koji Tsuda(Hokkaido Univ.) / (名大) |
| Assistant | Kei Shimonishi(Kyoto Univ.) / Kensho Hara(AIST) / Yoshinobu Kawahara(Osaka Univ.) / Taiji Suzuki(Univ.of Tokyo) |
| Paper Information | |
| Registration To | Technical Committee on Pattern Recognition and Media Understanding / Technical Committee on Information-Based Induction Sciences and Machine Learning / Special Interest Group on Computer Vision and Image Media |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | Conversion Prediction in Internet Advertising Using the Law of Diminishing Marginal Utility |
| Sub Title (in English) | |
| Keyword(1) | Machine Learning |
| Keyword(2) | Advertisements on the Internet |
| 1st Author's Name | Keiya Unno |
| 1st Author's Affiliation | Waseda University(Waseda Univ.) |
| 2nd Author's Name | Daichi Iwata |
| 2nd Author's Affiliation | OPT, Inc.(OPT) |
| 3rd Author's Name | Hiroaki Tanaka |
| 3rd Author's Affiliation | OPT, Inc.(OPT) |
| 4th Author's Name | Masato Uchida |
| 4th Author's Affiliation | Waseda University(Waseda Univ.) |
| Date | 2024-03-04 |
| Paper # | PRMU2023-80 |
| Volume (vol) | vol.123 |
| Number (no) | PRMU-409 |
| Page | pp.pp.168-173(PRMU), |
| #Pages | 6 |
| Date of Issue | 2024-02-25 (PRMU) |