Corrosion resistance is a critical consideration in the selection of materials for various applications. In this study, we employed a data-driven approach using machine learning techniques and a large dataset of corrosion data to design and test four different low-alloy steels with varying amounts of tin (Sn) microalloying (0.1 wt%, 0.2 wt%, 0.3 wt% and Sn-free) for improved corrosion resistance in Beijing outdoor atmosphere. Using experimental methods such as corrosion morphology and rust layer analysis, X-ray diffraction (XRD), X-ray photoelectron spectroscopy (XPS) and potentiodynamic polarization measurements, we verified that the 0.2 wt% Sn microalloying steel exhibited the best corrosion resistance. Our findings demonstrate the potential of data-driven approaches and machine learning techniques, such as the use of corrosion big data, in the identification and optimization of optimal alloy compositions of corrosion-resistant materials for outdoor environments.