Predicting Value-at-Risk with Risk-aware Mutual Attention Mechanism

Chien Shuo Wu, Shiou Chi Li, Jen Wei Huang

研究成果: Conference contribution

摘要

Value-at-Risk is a risk measurement method utilized in the capital market to estimate potential losses within a given period. However, the challenge of Value-at-Risk is a tradeoff between proximity and violations. Therefore, there is rare research available on Value-at-Risk prediction. This study utilized an attention-based model called Risk-Aware Mutual Attention Mechanism (RAMAM) to extract information between the global market and a single asset. The RAMAM model incorporated global indices, higher order moments and decomposed signals obtained through Variational Mode Decomposition (VMD) as features to capture relevant information and enable effective risk assessment. In experiments, the proposed model demonstrated significantly lower mean absolute error (MAE).

原文English
主出版物標題Proceedings - 23rd IEEE International Conference on Data Mining Workshops, ICDMW 2023
編輯Jihe Wang, Yi He, Thang N. Dinh, Christan Grant, Meikang Qiu, Witold Pedrycz
發行者IEEE Computer Society
頁面485-489
頁數5
ISBN(電子)9798350381641
DOIs
出版狀態Published - 2023
事件23rd IEEE International Conference on Data Mining Workshops, ICDMW 2023 - Shanghai, China
持續時間: 2023 12月 12023 12月 4

出版系列

名字IEEE International Conference on Data Mining Workshops, ICDMW
ISSN(列印)2375-9232
ISSN(電子)2375-9259

Conference

Conference23rd IEEE International Conference on Data Mining Workshops, ICDMW 2023
國家/地區China
城市Shanghai
期間23-12-0123-12-04

All Science Journal Classification (ASJC) codes

  • 電腦科學應用
  • 軟體

指紋

深入研究「Predicting Value-at-Risk with Risk-aware Mutual Attention Mechanism」主題。共同形成了獨特的指紋。

引用此