Disease and trait-associated variants represent a tiny minority of all known genetic variation, and therefore there is necessarily an imbalance between the small set of available disease-associated and the much larger set of non-deleterious genomic variation, especially in non-coding regulatory regions of human genome. Machine Learning (ML) methods for predicting disease-associated non-coding variants are faced with a chicken and egg problem - such variants cannot be easily found without ML, but ML cannot begin to be effective until a sufficient number of instances have been found. Most of state-of-the-art ML-based methods do not adopt specific imbalance-aware learning techniques to deal with imbalanced data that naturally arise in several genome-wide variant scoring problems, thus resulting in a significant reduction of sensitivity and precision. We present a novel method that adopts imbalance-aware learning strategies based on resampling techniques and a hyper-ensemble approach that outperforms state-of-the-art methods in two different contexts: the prediction of non-coding variants associated with Mendelian and with complex diseases. We show that imbalance-aware ML is a key issue for the design of robust and accurate prediction algorithms and we provide a method and an easy-to-use software tool that can be effectively applied to this challenging prediction task.