User satisfaction is essential for the success of software projects. In fact, even when the budget and the schedule of a project are in control, user dissatisfaction may still lead the project to failure. However, the satisfaction of a user is only part of the success recipe, since a strong competition can also detract users more easily from a software product/service. Users’ churn is the jargon used to denote when a user decides to change from a product/service to those offered by the competitors. In this study, we empirically investigate the relationship between the issues that are present in a software project and the users’ churn. For this purpose, we investigate a new dataset provided by the alternativeto.net platform. Alternativeto.net has a unique feature that allows users to recommend alternatives for a specific software product. The recommendation of alternatives can signal the intention to switch from one software product to another. Through our empirical study, we observe that (i) the intention to change software is tightly associated to the issues that are present in these software; (ii) we can use deep learning models to predict the rate of potential churn that will occur for a software; (iii) the longer the issue takes to be fixed, the higher the chances of users’ churn; and (iv) issues within more general software modules are more likely to be associated with users’ churn. Our study can provide more insights on the prioritization of issues that need to be fixed by considering the probability of users’ churn.