Estimating Future Financial Development of Urban Areas for Deploying Bank Branches: A Local-Regional Interpretable Model

Abstract

Financial forecasting is an important task for urban development. In this article, we propose a novel deep learning framework to predict the future financial potential of urban spaces. To be more precise, our target is to infer the number of financial institutions in the future for any arbitrary location with environmental and geographical data. We propose a novel local-regional model, the L ocal-Regional I nterpretable M ulti- A ttention (LIMA) model, which considers multiple aspects of a location—the place itself and its surroundings. Besides, our model offers three kinds of interpretability, providing a superior way for decision makers to understand how the model determines the prediction: critical rules learned from the tree-based module, surrounding locations that are highly correlated with the prediction, and critical regional features. Our module not only takes advantage of a tree-based model, which can effectively extract cross features, but also leverages convolutional neural networks to obtain more complex and inclusive features around the target location. Experimental results on real-world datasets demonstrate the superiority of our proposed LIMA model against existing state-of-the-art methods. The LIMA model has been deployed as a web system for assisting one of the largest bank companies in Taiwan to select locations for building new branches in major cities since 2020.