| Presentation | 2018-10-19 Price Prediction of Used Cars at Auto Auction by Deep Learning Hiromichi Sakurai, Daiki Kudo, Eriko Hasegawa, Rikozou Shimoyama, Ryosuke Fukunishi, Hiroki Mayuzumi, Tomoya Suzuki, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | Dealers of used cars have to predict future auction prices when buying used cars. However, it is very difficult to predict them because each condition of used cars is completely different such as mileage, model year, body color, etc. Moreover, these conditions are nonlinearly affected by each other and their number is not small. Therefore, the deep learning approach might be useful to reduce the curse of dimensionalityand to learn the nonlinear relationship among conditions. For this purpose, we used the stacked auto-encoder as a pre-training step for reducing the dimension of explanatory variables, and then predicted the auction price after one month to compose a used-car assessment system. To verify the usefulness of our prediction method, we performed some prediction tests using the real auto-auction price data, and confirmed better prediction performance especially in newer-model cars. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | Deep learning / Business intelligence / Data science |
| Paper # | CAS2018-50,NLP2018-85 |
| Date of Issue | 2018-10-11 (CAS, NLP) |
| Conference Information | |
| Committee | CAS / NLP |
|---|---|
| Conference Date | 2018/10/18(2days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | Tohoku Univ. |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | Mathematical modeling, numerical simulation etc. |
| Chair | Hideaki Okazaki(Shonan Inst. of Tech.) / Norikazu Takahashi(Okayama Univ.) |
| Vice Chair | Taizo Yamawaki(Hitachi) / Hiroaki Kurokawa(Tokyo Univ. of Tech.) |
| Secretary | Taizo Yamawaki(Shonan Inst. of Tech.) / Hiroaki Kurokawa(Hitachi) |
| Assistant | Motoi Yamaguchi(Renesas Electronics) / Masayuki Kimura(Kyoto Univ.) / Yutaka Shimada(Saitama Univ.) |
| Paper Information | |
| Registration To | Technical Committee on Circuits and Systems / Technical Committee on Nonlinear Problems |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | Price Prediction of Used Cars at Auto Auction by Deep Learning |
| Sub Title (in English) | |
| Keyword(1) | Deep learning |
| Keyword(2) | Business intelligence |
| Keyword(3) | Data science |
| 1st Author's Name | Hiromichi Sakurai |
| 1st Author's Affiliation | Ibaraki University(Ibaraki Univ.) |
| 2nd Author's Name | Daiki Kudo |
| 2nd Author's Affiliation | Ibaraki University(Ibaraki Univ.) |
| 3rd Author's Name | Eriko Hasegawa |
| 3rd Author's Affiliation | PROTO CORPORATION(PROTO) |
| 4th Author's Name | Rikozou Shimoyama |
| 4th Author's Affiliation | PROTO CORPORATION(PROTO) |
| 5th Author's Name | Ryosuke Fukunishi |
| 5th Author's Affiliation | PROTO CORPORATION(PROTO) |
| 6th Author's Name | Hiroki Mayuzumi |
| 6th Author's Affiliation | PROTO CORPORATION(PROTO) |
| 7th Author's Name | Tomoya Suzuki |
| 7th Author's Affiliation | Ibaraki University(Ibaraki Univ.) |
| Date | 2018-10-19 |
| Paper # | CAS2018-50,NLP2018-85 |
| Volume (vol) | vol.118 |
| Number (no) | CAS-242,NLP-243 |
| Page | pp.pp.69-74(CAS), pp.69-74(NLP), |
| #Pages | 6 |
| Date of Issue | 2018-10-11 (CAS, NLP) |