The number of citizen science (CS) projects has grown significantly in recent years, owing to technological advancements. One important aspect of ensuring the success of a CS project is to consider and address the challenges in this field. Two of the main challenges in CS projects are sustaining participation and improving the quality of contributed data. This research investigates how incorporating Machine Learning (ML) into CS projects can help to address the aforementioned challenges. A biodiversity CS project is implemented to accomplish this, with the goal of collecting and automatically validating location of observations, as well as providing participants with real-time feedback on the likelihood of observing a species in a specific location. The findings indicated that, on the one hand, automatic data filtering simplifies data validation, and on the other, real-time feedback can increase volunteers’ motivation to continue contributing to a CS project.