Factor Estimation Using SHAP for Outlier Detection Models for Merchant Marine Onboard Equipment
-
- Oki Iori
- Aoyama Gakuin University
-
- Nishigaki Takahiro
- Aoyama Gakuin University
-
- Onoda Takashi
- Aoyama Gakuin University
Bibliographic Information
- Other Title
-
- 商船搭載機器の外れ値検出モデルに対するSHAPを用いた要因推定
Description
<p>This study targets Equipment Onboard Merchant Ships. In addition, this predictive sign of abnormality is an outlier in the data. This study used SHAP, a method for interpreting outlier detection models, to identify factors. As a result, not only did the interpretation match that of the person in charge of the model at the location of the failure, but the factors at the location of the predictive signs of abnormality detected prior to the failure matched the factors of the failure. This allows us to suggest at an early stage what might be a factor in the future.</p>
Journal
-
- Abstracts of Annual Conference of Japan Society for Management Information
-
Abstracts of Annual Conference of Japan Society for Management Information 202211 (0), 151-154, 2023-01-31
THE JAPAN SOCIETY FOR MANAGEMENT INFORMATION (JASMIN)
- Tweet
Details 詳細情報について
-
- CRID
- 1390857899424867840
-
- Text Lang
- en
-
- Data Source
-
- JaLC
-
- Abstract License Flag
- Disallowed