Traditional trial-and-error methods are obstacles for large-scale searching of new optoelectronic materials. Here, we introduce a method combining high-throughput ab initio calculations and machine-learning approaches to predict two-dimensional octahedral oxyhalides with improved optoelectronic properties. We develop an effective machine-learning model based on an expansive dataset generated from density functional calculations including the geometric and electronic properties of 300 two-dimensional octahedral oxyhalides. Our model accelerates the screening of potential optoelectronic materials of 5,000 two-dimensional octahedral oxyhalides. The distorted stacked octahedral factors proposed in our model play essential roles in the machine-learning prediction. Several potential two-dimensional optoelectronic octahedral oxyhalides with moderate band gaps, high electron mobilities, and ultrahigh absorbance coefficients are successfully hypothesized. Supporting information Available: The computational methods, gradient boosted regression, model evaluation, initial features with definition, feature reduction, algorithm selection, comparison with various feature combinations, comparison between Machine-learning-predicted and DFT-calculated band gaps, structural details, electronic structures, phonon dispersions, AIMD evolutions, and carrier mobility. (PDF)