The primary objective of this research is to present a dependable approach for optimizing daylight and energy consumption in buildings for climate change adaptation. This study focuses on identifying the most influential input parameters affecting daylight and energy consumption in the future climate for urban housing in Malaysia. To achieve this, Radiance and OpenStudio software is employed to assess the daylight level and energy usage of the studied building, respectively. Subsequently, a robust artificial neural network (ANN) model is developed, trained, and tested to simulate daylight and energy consumption in the building. Furthermore, daylight and thermal energy multi-objective optimization is conducted using the Wallacei plugin, which utilizes an NSGA-II algorithm. The key findings indicate that the optimized solution can improve the useful daylight illuminance (UDI-%) level by 14.9% and the cooling energy use intensity (EUI-kWh/m²) can be reduced by 50%. Sensitivity analysis reveals that in the future climate, the glazing transmittance has the most significant impact on daylight performance, while room depth is the most significant for energy consumption. This study demonstrates that the trained ANN model proposed in this research can accurately predict daylight level and energy consumption in the building. The ANN model attained R² scores of 0.955 and 0.997, MAE scores of 1.64 and 3.26, and RMSE scores of 2.23 and 4.52 for UDI and cooling EUI, respectively. The significant difference between the Pareto front solutions produced via simulation-based optimization and ANN model optimization is evaluated using two-tailed Student’s t-tests. The results demonstrate that the P-value of the two models has no significant difference, indicating that the ANN model can produce a similar Pareto front solution to that achieved using the simulation-based optimization. In conclusion, this novel model has the potential to be applied to similar buildings and climates for effectively predicting and optimizing daylight and energy consumption in the future climate.