Improving the explainability of Random Forest classifier - user centered approach
Improving the explainability of Random Forest classifier - user centered approach
复制标题
提高随机森林分类器的可解释性 - 以用户为中心的方法
DOI：
--
复制
发表时间：
2018
期刊：
影响因子：
--
通讯作者：
Arthur Vigil
中科院分区：
文献类型：
--
作者：
D. Petkovic;R. Altman;Mike Wong;Arthur Vigil
机器学习（ML）方法现在正在影响有关患者护理、新医疗方法、药物开发的重大决策，它们的使用和重要性在所有领域都在迅速增加。然而，这些ML方法本质上是复杂的，通常难以理解和解释，从而导致其采用和验证的障碍。我们的工作（RFEX）的重点是通过开发易于解释的解释性摘要报告来提高随机森林（RF）分类器的可解释性，作为提高（通常是非专家）用户的可解释性的一种方式。RFEX已在斯坦福大学FEATURE数据上实现并进行了广泛测试，其中RF的任务是根据电化学签名（特征）预测3D分子中的功能位点。在开发RFEX方法时，我们采用以用户为中心的方法，通过与感兴趣的从业者讨论收集的可解释性问题和要求来驱动。我们与13名专家和非专家用户进行了正式的可用性测试，以验证RFEX的有用性。RFEX可解释性报告和用户反馈的分析表明，它在显著提高FEATURE数据RF分类的可解释性和用户信心方面是有用的。值得注意的是，RFEX摘要报告很容易揭示，当使用所有480个特征时，只需要很少的（取决于模型，从2-6个）排名靠前的特征就可以达到90%或更高的准确率。
Machine Learning (ML) methods are now influencing major decisions about patient care, new medical methods, drug development and their use and importance are rapidly increasing in all areas. However, these ML methods are inherently complex and often difficult to understand and explain resulting in barriers to their adoption and validation. Our work (RFEX) focuses on enhancing Random Forest (RF) classifier explainability by developing easy to interpret explainability summary reports from trained RF classifiers as a way to improve the explainability for (often non-expert) users. RFEX is implemented and extensively tested on Stanford FEATURE data where RF is tasked with predicting functional sites in 3D molecules based on their electrochemical signatures (features). In developing RFEX method we apply user-centered approach driven by explainability questions and requirements collected by discussions with interested practitioners. We performed formal usability testing with 13 expert and non-expert users to verify RFEX usefulness. Analysis of RFEX explainability report and user feedback indicates its usefulness in significantly increasing explainability and user confidence in RF classification on FEATURE data. Notably, RFEX summary reports easily reveal that one needs very few (from 2-6 depending on a model) top ranked features to achieve 90% or better of the accuracy when all 480 features are used.