谈金融服务领域的机器学习最佳实践

{"type":"doc","content":[{"type":"paragraph","attrs":{"indent":0,"number":0,"align":null,"origin":null},"content":[{"type":"text","text":"Original URL: "},{"type":"link","attrs":{"href":"https:\/\/aws.amazon.com\/cn\/blogs\/machine-learning\/machine-learning-best-practices-in-financial-services\/","title":"","type":null},"content":[{"type":"text","text":"https:\/\/aws.amazon.com\/cn\/blogs\/machine-learning\/machine-learning-best-practices-in-financial-services\/"}]}]},{"type":"paragraph","attrs":{"indent":0,"number":0,"align":null,"origin":null}},{"type":"paragraph","attrs":{"indent":0,"number":0,"align":null,"origin":null},"content":[{"type":"text","text":"金融服务领域的机器学习最佳实践"}]},{"type":"paragraph","attrs":{"indent":0,"number":0,"align":null,"origin":null}},{"type":"paragraph","attrs":{"indent":0,"number":0,"align":null,"origin":null},"content":[{"type":"text","text":"在最近发布的白皮书《金融服务中的机器学习最佳实践（"},{"type":"link","attrs":{"href":"https:\/\/d1.awsstatic-china.com\/whitepapers\/machine-learning-in-financial-services-on-aws.pdf","title":"","type":null},"content":[{"type":"text","text":"Machine Learning Best Practices in Financial Services"}]},{"type":"text","text":"）》中，我们概述了在构建机器学习（ML）工作流的过程中，金融机构需要关注的安全性与模型治理注意事项。这份白皮书还涵盖了常见的安全性与合规性要素，旨在配合上手"},{"type":"link","attrs":{"href":"https:\/\/www.youtube.com\/watch?v=HlSEUvApDZE","title":"","type":null},"content":[{"type":"text","text":"演示"}]},{"type":"text","text":"与"},{"type":"link","attrs":{"href":"https:\/\/sagemaker-workshop.com\/securityforsysops.html","title":"","type":null},"content":[{"type":"text","text":"研习班"}]},{"type":"text","text":"共同为您介绍端到端的示例。虽然这份白皮书主要着眼于金融服务行业，但其中涉及的身份验证与访问管理、数据与模型安全以及ML实施（MLOps）最佳实践等内容，也同样适用于医疗保健等其他受到严格监管的行业。"}]},{"type":"paragraph","attrs":{"indent":0,"number":0,"align":null,"origin":null}},{"type":"paragraph","attrs":{"indent":0,"number":0,"align":null,"origin":null},"content":[{"type":"text","text":"如下图所示，典型的机器学习工作流中往往涉及多个利益相关方。为了成功管理并运营这类工作流，我们需要推动跨团队协作，将业务相关方、系统运营管理员、数据工程师以及软件\/DevOps工程师纳入这套体系中来。"}]},{"type":"paragraph","attrs":{"indent":0,"number":0,"align":null,"origin":null}},{"type":"image","attrs":{"src":"https:\/\/static001.infoq.cn\/resource\/image\/33\/20\/3317edc40a2c6d11dcfb5301fab98f20.png","alt":null,"title":null,"style":null,"href":null,"fromPaste":true,"pastePass":false}},{"type":"paragraph","attrs":{"indent":0,"number":0,"align":null,"origin":null}},{"type":"paragraph","attrs":{"indent":0,"number":0,"align":null,"origin":null},"content":[{"type":"text","text":"在白皮书中，我们还探讨了各个团队需要关注的核心事项，并通过示例与说明阐述如何使用"},{"type":"link","attrs":{"href":"https:\/\/amazonaws-china.com\/sagemaker","title":"","type":null},"content":[{"type":"text","text":"Amazon SageMaker"}]},{"type":"text","text":"及其他AWS服务实现机器学习工作负载的构建、训练与部署。具体来讲，结合高监管要求背景下客户们提供的真实反馈，我们着重分析了以下主题："}]},{"type":"paragraph","attrs":{"indent":0,"number":0,"align":null,"origin":null}},{"type":"bulletedlist","content":[{"type":"listitem","attrs":{"listStyle":null},"content":[{"type":"paragraph","attrs":{"indent":0,"number":0,"align":null,"origin":null},"content":[{"type":"text","text":"置备一套安全的机器学习环境——具体包括："}]}]}]},{"type":"paragraph","attrs":{"indent":0,"number":0,"align":null,"origin":null},"content":[{"type":"text","text":"\t* 计算与网络隔离——如何在不连接互联网的前提下，将Amazon SageMaker部署在客户的专用网络当中。"}]}]}