企业财经领域落地AI怎么落地

A pro-innovation approach to AI regulationo Consider how tools for trustworthy AI like assurance techniques and technical standards can support regulatory compliance.o Engage proactively and collaboratively with government’s monitoring and evaluation of the framework.41A pro-innovation approach to AI regulationCase Study 3.7:What this means for businessesA fictional company,“AI Fairness Insurance Limited”,has delayed the deployment of a new AI application as–under the current patchwork of relevant regulatory requirements–it has been challenging to identify appropriate compliance actions for AI-driven insurance products.Following implementation of the UK’s new pro-innovation framework to regulate AI,we could expect to see joint guidance produced collaboratively by the Information Commissioner’s Office(ICO),Equality and Human Rights Commission(EHRC),Financial Conduct Authority(FCA)and other relevant regulatory authorities.This would provide greater clarity on the regulatory requirements relevant to AI as well as guidance on how to satisfy those requirements in the context of insurance and consumer-facing financial services.Under the proposed regulatory framework,AI Fairness Insurance Limited could be supported by new or updated guidance issued by regulators to address the AI regulatory principles.The company may also be able to follow joint regulatory guidance,issued as a result of collaboration between regulators,and use a set of tools provided by regulators,such as template risk assessments and transparency measures,and relevant technical standards(e.g.international standards for transparency and bias mitigation).The collaboration between regulators and focus on practical implementation measures will guide the responsible deployment of AI Fairness Insurance Limited’s AI product by making it easier for the company to navigate the regulatory landscape and address specific risks such as discrimination.

1.19.AI is already delivering major advances and efficiencies in many areas.AI quietly automates aspects of our everyday activities,from systems that monitor traffic to make our commutes smoother,17 to those that detect fraud in our bank accounts.18 AI has revolutionised large-scale safety-critical practices in industry,like controlling the process of nuclear fusion.19 And it has also been used to accelerate scientific advancements,such as the discovery of new medicine20 or the technologies we need to tackle climate change.212.20.But this is just the beginning.AI can be used in a huge variety of settings and has the extraordinary potential to transform our society and economy.22 It could have as much impact as electricity or the internet,and has been identified as one of five critical technologies in the UK Science and Technology Framework.23 As AI becomes more powerful,and as innovators explore new ways to use it,we will see more applications of AI emerge.As a result,AI has a huge potential to drive growth24 and create jobs.25 It will support people to carry out their existing jobs,by helping to improve workforce efficiency and workplace safety.26 To remain world leaders in AI,attract global talent and create high-skilled jobs in the UK,we must create a regulatory environment where such innovation can thrive.3.21.Technological advances like large language models(LLMs)are an indication of the transformative developments yet to come.27 LLMs provide substantial opportunities to transform the economy and society.For example,LLMs can automate the process of writing code and17 Transport apps like Google Maps,and CityMapper,use AI.18 Artificial Intelligence in Banking Industry:A Review on Fraud Detection,Credit Management,and Document Processing,ResearchBerg Review of Science and Technology,2018.19 Accelerating fusion science through learned plasma control,Deepmind,2022;Magnetic control of tokamak plasmas through deep reinforcement learning,Degrave et al.,2022.20

也就是说，需要注意的是，生成式AI在这里的输出当前仍有局限性，特别是在需要判断或精确答案的领域，这常常是财务团队所需的。生成式AI模型在计算方面持续改进，但目前尚不能完全依赖于其准确性，或者至少需要人工审查。随着模型的快速改进、额外的训练数据和与数学模块的整合能力，它的使用将展现新的可能性。–Seema Amble挑战在这五个趋势中，新进入者和现有参与者在将生成式AI的未来变为现实时面临两个主要的挑战。1.使用金融数据训练LLMs：LLMs目前是在互联网上训练的。金融服务用例将需要使用特定于用例的金融数据来微调这些模型。新进入者可能会开始使用公开的公司财务数据、监管文件和其他易于获取的公开金融数据来优化他们的模型，然后最终在随着时间的推移使用他们自己收集的数据。现有的参与者，如银行或具有金融服务业务的大型平台（例如，Lyft），可以利用他们现有和专有的数据，这可能会给他们带来初步的优势。然而，现有的金融服务公司在接受大型平台转变时往往过于保守。在我们看来，这给了无拖累的新进入者竞争优势。2.模型输出准确性：考虑到金融问题的答案可能对个人、公司和社会产生的影响，这些新的AI模型需要尽可能准确。它们不能产生幻觉或编造错误但听起来自信的答案来回应关于个人税收或财务状况的关键问题，它们需要比流行文化查询或通用高中作文的大致答案更准确。一开始，人类经常会作为AI生成答案的最终验证环节。生成式AI的出现对金融服务公司来说是一个巨大的平台变革，有潜力催生个性化客户解决方案、更加成本高效的运营、更好的合规和改进的风险管理，以及更具动态的预测和报告。现有参与者和初创公司将争夺我们上面概述的两个关键挑战的掌控权。虽然我们还不知道谁将最终胜出，但我们已经知道有一个明确的赢家：未来金融服务的消费者。