Abstract: Systems and methods for using machine learning models to predict an outcome of a product test are described. According to certain aspects, an electronic device may generate a machine learning model using training data indicating a set of results of a set of products tested according to a specific product test. The electronic device may access a set of inputs comprising a set of additional results of at least one additional product tested according to a modified product test, and input the set of inputs into the machine learning model. Based on an output of the machine learning model, the electronic device may predict whether the at least one additional product would pass or comply with the original specific product test.