A Survey on the Explainability of Supervised Machine Learning

# A Survey on the Explainability of Supervised Machine Learning > OpenAlex Metadata Hub · https://openalex.org/W3101981467 ## Bibliographic - **DOI:** 10.1613/jair.1.12228 - **Year:** 2021 - **Citations:** 962 - **Open Access:** Yes (diamond) - **License:** cc-by - **Source:** https://jair.org/index.php/jair/article/download/12228/26647 ## Authors - Nadia Burkart - Marco F. Huber ## Abstract Predictions obtained by, e.g., artificial neural networks have a high accuracy but humans often perceive the models as black boxes. Insights about the decision making are mostly opaque for humans. Particularly understanding the decision making in highly sensitive areas such as healthcare or finance, is of paramount importance. The decision-making behind the black boxes requires it to be more transparent, accountable, and understandable for humans. This survey paper provides essential definitions, an overview of the different principles and methodologies of explainable Supervised Machine Learning (SML). We conduct a state-of-the-art survey that reviews past and recent explainable SML approaches and classifies them according to the introduced definitions. Finally, we illustrate principles by means of an explanatory case study and discuss important future directions. ## Keywords Computer science, Machine learning, Artificial intelligence, Supervised learning, Artificial neural network ## Concepts - Computer science - Machine learning - Artificial intelligence - Supervised learning - Artificial neural network --- *Metadata only — full text not imported unless Open Access license permits.*

Bài “A Survey on the Explainability of Supervised Machine Learning” được TradingBase chuyển thành Knowledge Product cho trader — không phải trang đọc abstract OpenAlex. Tóm lược học thuật (đã diễn giải): Predictions obtained by, e.g., artificial neural networks have a high accuracy but humans often perceive the models as black boxes. Insights about the decision making are mostly opaque for humans. Particularly understanding the decision making in highly sensitive areas such as healthcare or finance, is of paramount importance. The decision-making behind the black boxes requires it to be more transparent, accountable, and understandable for humans. This survey paper provides essential definitions, an overview of the different principles and methodologies of explainable Supervised Machine Learning (SML). We conduct a state-of-the-art survey that reviews past and recent explainable SML approaches and classifies them according to the introduced definitions. Finally, we illustrate principles by means of an explanatory case study and discuss important future directions. Phần Trading Insights bên dưới nối nghiên cứu với Forex, vàng, USD, lãi suất và risk regime — để bạn đưa vào journal và playbook. Metadata DOI/OA chỉ là rail tham chiếu; nội dung chính là summary, takeaways và ứng dụng thị trường do Content Factory sinh.