arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2511.17954q-fin.RMcs.LG
收藏

一种用于风险建模中空间嵌入的多视角对比学习框架

A multi-view contrastive learning framework for spatial embeddings in risk modelling

KU Leuven(鲁汶大学);University of Toronto(多伦多大学);University of Amsterdam(阿姆斯特丹大学)

Freek Holvoet, Christopher Blier-Wong, Katrien Antonio

AI总结:

本文提出了一种多视角对比学习框架,用于生成空间嵌入以提升风险建模的预测精度和可解释性。

摘要:

在保险中,将受气候、天气和人口因素影响的空间信息纳入考虑,对于提高承保精度和增强风险管理至关重要。然而,空间数据通常无结构、高维且难以整合到预测模型中。嵌入方法需要将空间数据转换为有意义的表示以用于建模任务。我们提出了一种新颖的多视角对比学习框架,用于生成结合多个空间数据源信息的空间嵌入。为了训练模型,我们构建了一个空间数据集,将欧洲的卫星图像和OpenStreetMap特征合并。该框架通过基于坐标的编码对这些空间视图进行对齐,生成低维嵌入,能够捕捉空间结构和上下文相似性。一旦训练完成,模型可以直接从纬度-经度对生成嵌入,使任何具有坐标的数据库都能获得有意义的空间特征,而无需访问原始空间输入。在法国房地产价格案例研究中,我们比较了使用原始坐标训练的模型与使用我们生成的空间嵌入作为输入的模型。嵌入在通用线性、加法和提升模型中均一致提高了预测精度,同时提供了可解释的空间效应,并展示了对未见过区域的可迁移性。

英文摘要:

Incorporating spatial information, particularly when related to climate, weather, and demographic factors, is crucial for improving underwriting precision and enhancing risk management in insurance. However, spatial data are often unstructured, high-dimensional, and difficult to integrate into predictive models. Embedding methods are needed to convert spatial data into meaningful representations for modelling tasks. We propose a novel multi-view contrastive learning framework for generating spatial embeddings that combine information from multiple spatial data sources. To train the model, we construct a spatial dataset that merges satellite imagery and OpenStreetMap features across Europe. The framework aligns these spatial views with coordinate-based encodings, producing low-dimensional embeddings that capture both spatial structure and contextual similarity. Once trained, the model generates embeddings directly from latitude-longitude pairs, enabling any dataset with coordinates to be enriched with meaningful spatial features without requiring access to the original spatial inputs. In a case study on French real estate prices, we compare models trained on raw coordinates against those using our spatial embeddings as inputs. The embeddings consistently improve predictive accuracy across generalised linear, additive, and boosting models, while providing post-hoc explainable spatial effects and demonstrating generalisation of the fitted spatial effects to regions without training observations. A second case study on flood claim counts across Belgian postal codes confirms that the embeddings improve territorial risk classification in an insurance context.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑