| Presentation | 2022-11-17 Improvement of financial machine learning by fine-tuning using multiple time scales Kazuki Amagai, Riku Tanaka, Tomoya Suzuki, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | In asset management businesses such as operating mutual funds, medium or long-term investments are common in terms of operational loads and transaction costs. However, the number of training data are more insufficient for applying machine-learning methodsto longer time-scale investments, which reduces the generalization ability of trained machine-learning models. To solve this problem, we try to perform a data augmentation technique using multiple time-scale data including shorter time-scale data than the target task, and confirm its effectiveness to keep a better generalization ability of trained models even if the target task of machine-learning methods is longer time scale. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | multiple time scale / autoencoder / data augmentation / fine tuning / multi factor model |
| Paper # | CCS2022-47 |
| Date of Issue | 2022-11-10 (CCS) |
| Conference Information | |
| Committee | CCS |
|---|---|
| Conference Date | 2022/11/17(2days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | |
| Chair | Megumi Akai(Hokkaido Univ.) |
| Vice Chair | Hidehiro Nakano(Tokyo City Univ.) / Masaki Aida(TMU) |
| Secretary | Hidehiro Nakano(Shibaura Inst. of Tech.) / Masaki Aida(Mie Univ.) |
| Assistant | Hiroyuki Yasuda(Univ. of Tokyo) / Hiroyasu Ando(Tsukuba Univ.) / Tomoyuki Sasaki(Shonan Inst. of Tech.) / Miki Kobayashi(Rissho Univ.) |
| Paper Information | |
| Registration To | Technical Committee on Complex Communication Sciences |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | Improvement of financial machine learning by fine-tuning using multiple time scales |
| Sub Title (in English) | |
| Keyword(1) | multiple time scale |
| Keyword(2) | autoencoder |
| Keyword(3) | data augmentation |
| Keyword(4) | fine tuning |
| Keyword(5) | multi factor model |
| 1st Author's Name | Kazuki Amagai |
| 1st Author's Affiliation | Ibaraki University(Ibaraki Univ.) |
| 2nd Author's Name | Riku Tanaka |
| 2nd Author's Affiliation | Daiwa Asset Management Co.Ltd.(Daiwa Asset Management) |
| 3rd Author's Name | Tomoya Suzuki |
| 3rd Author's Affiliation | Ibaraki University(Ibaraki Univ.) |
| Date | 2022-11-17 |
| Paper # | CCS2022-47 |
| Volume (vol) | vol.122 |
| Number (no) | CCS-255 |
| Page | pp.pp.19-24(CCS), |
| #Pages | 6 |
| Date of Issue | 2022-11-10 (CCS) |