Traditional recommender systems often provide recommendations in the form of black-box models, making it challenging for users and developers to understand the reasons and decision-making processes behind these recommendations. This leads to reduced trust, user satisfaction, and potential issues related to privacy and fairness. To address these challenges, explainable recommender systems aim to enhance user trust in recommendations and provide a deeper understanding of personalized suggestions. These systems employ various techniques, including rule-based explanations, model interpretability techniques, and user interface design, to elucidate the reasons and basis for recommendations. In doing so, users gain a better understanding of why they receive specific recommendations, which leads to greater acceptance and adoption of these recommendations.
E-commerce Platforms, Financial Services, Social Media, Content Recommendations
| 氏名 | コース | 研究室 | 役職/学年 |
|---|---|---|---|
| Yu Yi | 社会情報学コース | 伊藤孝行研究室 | 博士3回生 |