Designing new single-molecule magnets (SMMs) for magnetocaloric applications is challenging, because there are millions of possibilities, and only a small fraction of these have been experimentally explored. To improve the search for new magnetocaloric SMMs, Holleis et al. turned to machine learning. The team trained machine learning models to establish a relationship between entropy change and SMM descriptors. The models learned to rapidly predict entropy change for hypothetical SMMs by identifying key descriptors of SMM that affect the entropy change, including aspects related to crystal structure and chemistry. This work lays the foundation for accelerating the search and discovery of novel SMMs with tailored magnetocaloric properties.