An Automated Machine learning (AutoML) approach to regression models in minerals processing with case studies of developing industrial comminution and flotation models

•Automated Machine Learning pipeline develops predictive models from plant data within hours,•Steps include filtering, temporal resolution, feature selection, and neural network architecture optimisation,•Pipeline does not require expert Machine Learning knowledge for model development,•Three case studies with minimal errors of < 3 % for valuables and < 7 % for by-products,•Developed AutoML models always better than Partial Least Squares models.