This study introduces a five-step methodology for implementing machine learning (ML) models in fabricating hole transport layer (HTL) free carbon-based perovskite solar cells (C-PSCs). A comprehensive dataset of 700 data points was curated using SCAPS-1D simulation, varying ETL and perovskite layer thicknesses and bandgaps. Results show that an ANN-based ML model exhibits superior predictive accuracy for C-PSC device parameters (RMSE of 0.028 and R-squared of 0.954), streamlining optimization and providing deeper understanding of parameter interdependence.
