Scientists at Lawrence Berkeley National Laboratory (Berkeley Lab) have developed a data-driven approach to optimize chiral 2D metal halide perovskites (MHPs) for spin-based optoelectronics. A new study published in the journal *Matter* offers a roadmap to solve a reproducibility problem where reported performance values for nominally the same material vary by more than two orders of magnitude across different laboratories. Scientist Carolin Sutter-Fella and her team at Berkeley Lab’s Molecular Foundry showed how systematically tuning fabrication process “knobs”—such as solvent choice, annealing temperature, and film thickness—can reliably improve the material’s chiroptical properties. For the study, first author Raphael Moral prepared thin films from single-crystal precursor solutions and used X-ray techniques at the Advanced Light Source to unveil the material’s crystallization process. Moral and co-first author Maher Alghalayini used statistical tools, including correlation analysis and machine-learning methods supported by Berkeley Lab’s Center for Advanced Mathematics for Energy Research Applications (CAMERA), to identify and model parameters. The framework revealed that solvent choice is the single most important factor, where films made with acetonitrile produced the strongest and most consistent chiroptical signals.