The analysis of the various factors associated with the prediction of the coefficient of performance in the vapor compression refrigeration system is quite complex, requiring the use of several equations and more time, resulting in the development of better predictions and more precise findings. In this area, research mainly concentrates on a new methodology that has not yet been put into practice: adaptive neuro-fuzzy interface system (ANFIS). It correctly estimates the R600a vapor compression refrigerator performance, cooling effect, and energy needed by the compressor. The equipment uses Al<inf>2</inf>O<inf>3</inf>/SiO<inf>2</inf> nanolubricants. In comparison with experimental results, the ANFIS anticipated refrigeration effect of 215 W resulted in 0.4 g/L of Al<inf>2</inf>O<inf>3</inf>/SiO<inf>2</inf> hybrid nanolubricants and 70 g of R600a refrigerant mass charges. ANFIS's forecast led to a 100 W decrease in compressor effect. In comparison with ANN estimates, the maximum COP value of 3.5 projected by ANFIS was attained. In comparison with experimental findings, the ANFIS model projected a training error value of 0.29901, which is extremely low. From the findings, it can be shown that the ANFIS estimated values produced more accurate results when compared to ANN estimation, which were a better suitable approach for the prediction of COP parameters when compared to experimental outputs and consumed roughly 45 less energy. © 2025 Elsevier B.V., All rights reserved.