Binding affinities of metal–ligand complexes are central to a multitude of applications like drug design, chelation therapy, designing reagents for solvent extraction etc. While state-of-the-art molecular modelling approaches are usually employed to gather structural and chemical insights about the metal complexation with ligands, their computational cost and the limited ability to predict metal–ligand stability constants with reasonable accuracy, renders them impractical to screen large chemical spaces. In this context, leveraging vast amounts of experimental data to learn the metal-binding affinities of ligands becomes a promising alternative. Here, we develop a machine learning framework for predicting binding affinities (logK1) of lanthanide cations with several structurally diverse molecular ligands. Six supervised machine learning algorithms—Random Forest (RF), k-Nearest Neighbours (KNN), Support Vector Machines (SVM), Kernel Ridge Regression (KRR), Multi Layered Perceptrons (MLP) and Adaptive Boosting (AdaBoost)—were trained on a dataset comprising thousands of experimental values of logK1 and validated in an external 10-folds cross-validation procedure. This was followed by a thorough feature engineering and feature importance analysis to identify the molecular, metallic and solvent features most relevant to binding affinity prediction, along with an evaluation of performance metrics against the dimensionality of feature space. Having demonstrated the excellent predictive ability of our framework, we utilized the best performing AdaBoost model to predict the logK1 values of lanthanide cations with nearly 71 million compounds present in the PubChem database. Our methodology opens up an opportunity for significantly accelerating screening and design of ligands for various targeted applications, from vast chemical spaces.