Causal inference is a permanent challenge topic in statistics, data science, and many other applied fields. Existing machine learning methods often focus on the correlations in the data and ignore the causality. With the increase in application requirements, their drawbacks have gradually begun to appear. In this talk, we summarize our work of applying causal techniques and ideas to solve practical problems in bank business in recent years. In credit risk management, we bring causality into predictive modeling and propose a novel stable scorecard model. In business marketing, we propose causal inference based single-branch ensemble trees for uplift modeling. This method has already been applied to online personal loans in a national financial holdings group in China. These works have been reported on Credit Scoring and Credit Control Conference XVII (CSCC) and AI for Web Advertising Workshop AAAI 2023.