In this manuscript, we present B-AMA (Basic dAta-driven Models for All), a simple, flexible, and entirely Python-based protocol for applying data-driven models (DDMs) in hydrology. The protocol, which is open-source and freely available for academic and non-commercial purposes, has been designed to enable early-career scientists with a basic programming background to develop DDMs while ensuring no steps are overlooked during implementation.

B-AMA incorporates data splitting, forcing selection, hyperparameter optimization, and performance metric computation. A Jupyter notebook with a practical workflow is provided to guide users in utilizing the protocol, while visualization tools facilitate efficient investigation and communication of results. We tested B-AMA in four hydrological applications to explore the applicability of DDMs across different temporal resolutions, lengths of time series, and autocorrelations. B-AMA demonstrated high accuracy and reasonable computational times, making the protocol ideal for educational purposes and for developing data-driven forecasts of hydrological time series.