Building the next generation of batteries—efficient, compact, and sustainable—relies on discovering new materials with the right set of properties. Metal-organic frameworks (MOFs), a class of crystalline and porous materials, have emerged as promising candidates for battery electrodes due to their potential for electrical conductivity. One key property that influences a MOF’s conductivity is its band gap. However, state-of-the-art density functional theory (DFT) calculations used to compute band gaps are computationally expensive. In this project, our goal was to develop a machine learning model to predict the band gaps of MOFs, helping to rapidly identify promising candidates for future energy storage technologies such as next-generation batteries.