在风险管理至关重要的金融服务领域,我们都看到人工智能和机器学习正在迅速改变格局。事实上,最近的一则
英格兰银行和金融行为监管局的调查 (FCA)透露
72% 的英国金融公司已经在使用或开发 AI/ML 应用程序,而且这种趋势正在以惊人的速度加速,
预计未来三年机器学习应用数量中位数将猛增 3.5 倍. This growth is not surprising – AI/ML models hold the promise of unlocking insights from vast amounts of data, enabling financial organisations
to make smarter, more informed decisions, and enhance their risk management strategies.
The survey’s findings are consistent with observations that I’ve made through my work with UK financial services institutions. Although, I have found that the progression towards AI/ML methodologies is more advanced within Fintech and Challenger Banks that,
unlike the High Street Banks, may not suffer from actual limitations due to legacy systems or perceived limitations relating to their IRB status.
Fintechs and Challenger Banks have typically recruited tech-savvy data scientists with deep understandings of the array of alternative advanced techniques that are available. Meanwhile, major banks still hold a significant advantage in terms of experience
and data. They have decades of experience in building credit models, have established model development standards, and have a thorough understanding of the underlying data.
现在的问题是,支撑传统模型发展的原则是否仍然与新一代人工智能驱动的模型完全相关,而新一代人工智能驱动的模型是以完全不同的数学方式推导的。
模型开发:传统 VS AI/ML
Traditional scorecard development has long adhered to meticulous sample design, ensuring that the applications during the sample window are both stable and reflective of proposals most recently received. It is typical for Population Stability Indices or Characteristics
Stability Indices to be calculated, and for a detailed investigation of any patterns that extend beyond reasonable expectations of seasonal variation. This approach hinges on the notion of a bespoke development sample tailored to the specific population it
serves. The composition or segmental mix and its specificity is seen as a key factor in the suitability of the model development sample.
Interestingly, we often see that AI/ML models exhibit a significant degree of cross-learning. This is where models display stronger performance when the training sample is extended to include additional observations that might not traditionally be considered
directly relevant. For example, we see superior performance from models trained on an expanded sample window versus equivalent models optimised on a period that simply aligns to the independent test sample. This is unlikely to happen using linear models!
Similar findings can be seen when adjacent segments or groups are added to the training samples. Indeed, AI/ML models thrive when developed upon large and diverse data sets. These phenomena will have implications for sample design and choice of exclusions within
model developments of the future, potentially rewriting conventional wisdom.
Similarly, many credit scorecard developments have incorporated segmentation, whereby a model is built for each of a number of sub-populations (eg. Thin File / Thick File, Clean / Dirty). The benefit of this approach is that, by building multiple models, some
non-linearity can be captured. Of course, the choice of segmentation is not always obvious and is unlikely to be optimal, however some performance uplifts are achieved. Given that AI/ML models are built because of their ability to capture non-linearity, there
is limited need for segmented models here, unless there are fundamental differences in data structure. Therefore, AI/ML models are more complex, fewer of them should be required.
Another area of focus within traditional scorecard development is the process of moving from fine-to-coarse classing. Hereby the modeller seeks to effectively divide continuous data into several ordinal groups so that the underlying bad rate shows a logical
progression and is based on sufficient volume to give a reliable result. Advanced methodologies within AI/ML models eliminate the need for fine-to-coarse classing as the grouping is achieved by the underlying methodology, generating smooth response profiles
rather than the step-changes seen as scorecard attribute boundaries are crossed. Furthermore, many training routines now include the option to add constraints to ensure features have a logical impact on the model predictions.
As the wave of AI/ML model development surges in the coming years, a fusion of deep knowledge of underlying credit data and advanced methodology is key. While new challenges arise in this new generation of models, such as unintended bias and explainability,
historical concerns will become less relevant.
- SEO 支持的内容和 PR 分发。 今天得到放大。
- PlatoData.Network 垂直生成人工智能。 赋予自己力量。 访问这里。
- 柏拉图爱流。 Web3 智能。 知识放大。 访问这里。
- 柏拉图ESG。 碳, 清洁科技, 能源, 环境, 太阳能, 废物管理。 访问这里。
- 柏拉图健康。 生物技术和临床试验情报。 访问这里。
- Sumber: https://www.finextra.com/blogposting/25517/risk-model-development–the-next-generation?utm_medium=rssfinextra&utm_source=finextrablogs
- :具有
- :是
- :不是
- :在哪里
- a
- 对,能力--
- 加速
- 实现
- 实际
- 加
- 添加
- 额外
- 坚持
- 邻
- 高级
- 优点
- AI供电
- AI / ML
- 对齐
- 所有类型
- 已经
- 替代
- 尽管
- 时刻
- 量
- an
- 和
- 任何
- 应用领域
- 的途径
- 保健
- 国家 / 地区
- 出现
- 排列
- 人造的
- 人工智能
- 人工智能和机器学习
- AS
- At
- 可使用
- 坏
- 银行
- 英国央行
- 银行
- 基于
- BE
- 因为
- 成为
- 得益
- 不啻
- 超越
- 偏见
- 都
- 边界
- 建筑物
- 建
- by
- 计算
- CAN
- 捕获
- 捕获
- 挑战者
- 挑战银行
- 挑战
- 特点
- 选择
- 清洁
- CO
- 未来
- 完全
- 复杂
- 写作
- 关注
- 进行
- 考虑
- 一贯
- 约束
- 连续
- 常规
- 课程
- 信用
- 交叉
- data
- 数据集
- 几十年
- 决定
- 深
- 学位
- 派生
- 设计
- 详细
- 发达
- 发展
- 研发支持
- 发展
- 差异
- 不同
- 直接
- 屏 显:
- 不同
- 分
- 两
- ,我们将参加
- 每
- 只
- 消除
- 使
- 英国
- 提高
- 确保
- 保证
- 成熟
- 例子
- 展览
- 扩大
- 期望
- 体验
- 可解释性
- 延长
- 扩展
- 事实
- 因素
- FCA
- 特征
- 少
- 文件
- 金融
- 金融行为
- 金融服务
- 发现
- Finextra
- fintech
- 企业
- 专注焦点
- 针对
- 发现
- 止
- 根本
- 此外
- 聚变
- 未来
- 发电
- 代
- 给
- 特定
- 组的
- 事业发展
- 发生
- 有
- 相关信息
- 高
- 铰链
- 历史的
- 举行
- 但是
- HTTPS
- i
- 影响力故事
- 启示
- in
- 包括
- 成立
- 独立
- 指数
- 通知
- 可行的洞见
- 机构
- 房源搜索
- 成
- 调查
- IT
- 它的
- JPG
- 键
- 关键因素
- 知识
- 景观
- 大
- 学习
- 遗产
- 减
- 限制
- 有限
- 合乎逻辑的
- 长
- 机
- 机器学习
- 制成
- 主要
- 使
- 颠覆性技术
- 许多
- 数学
- 可能..
- 与此同时
- 方法
- 研究方法
- 细致
- 可能
- 混合
- ML
- 模型
- 模型
- 更多
- 最先进的
- 移动
- 多
- my
- 需求
- 全新
- 下页
- 概念
- 现在
- 数
- 意见
- 明显
- of
- 经常
- on
- 最佳
- 优化
- 附加选项
- or
- 组织
- 步伐
- 最重要的
- 模式
- 感知
- 性能
- 期间
- 柏拉图
- 柏拉图数据智能
- 柏拉图数据
- 人口
- 可能
- 预测
- 原则
- 过程
- 简介
- 级数
- 预计
- 承诺
- 建议
- 题
- 急速
- 率
- 宁
- 合理
- 收到
- 最近
- 最近
- 相应
- 可靠
- 留
- 必须
- 响应
- 导致
- 揭密
- 重写
- 风险
- 变更管理
- 科学家
- 记分卡
- 季节性
- 看到
- 寻求
- 看到
- 分割
- 中模板
- 服务
- 特色服务
- 套数
- 几个
- 应该
- 作品
- 显著
- 只是
- 平步青云
- 聪明
- 光滑
- So
- 一些
- 具体的
- 特异性
- 稳定性
- 稳定
- 标准
- Status
- 仍
- 策略
- 街头
- 强
- 结构体
- 这样
- 足够
- 适应性
- 优于
- 潮
- 奇怪
- 调查
- 产品
- 量身定制
- 技术
- 条款
- test
- 比
- 这
- 未来
- 景观
- 世界
- 其
- 他们
- 那里。
- 因此
- 博曼
- 他们
- Free Introduction
- 三
- 兴旺
- 通过
- 时
- 至
- 向
- 传统
- 传统
- 熟练
- 产品培训
- 转型
- 趋势
- 普遍
- 一般
- Uk
- 相关
- 支撑
- 理解
- 不像
- 不会
- 解锁
- 上
- 运用
- 广阔
- Ve
- 与
- 体积
- vs
- 波
- 方法..
- we
- ,尤其是
- 是否
- 这
- 而
- 全
- 将
- 窗口
- 智慧
- 中
- 工作
- 世界
- 年
- 和风网