Interpretable machine learning-assisted design of Fe-based nanocrystalline alloys with high saturation magnetic induction and low coercivity

•XGBoost performs the best in predicting Bs and Hc among six different ML algorithms.•Association of key features with Bs and Hc of FNAs is revealed.•VEC1 exercises a positive impact on Bs when VEC1 < 0.78, while VEC exercises a negative effect on Hc when VEC < 7.12.•Low prediction errors between experimental and predicted values are obtained.