Thin-film Copper Indium Gallium Selenide (CIGS) solar cell is identified to be one of the promising structures to replace conventional silicon-based solar cell due to its lower cost and reduced thickness. Nevertheless, the impact of layer thickness and doping concentration of a window layer-Zinc oxide (ZnO), a buffer layer-Cadmium sulfide (Cds) and an absorber layer (CIGS) needs to be intelligently controlled for more balanced CIGS solar cell performances. Thus, this paper proposes a newly predictive analytics using a combination of Grey relational analysis (GRA), multiple linear regressions (MLR) and genetic algorithm (GA) to optimize the CIGS solar cell parameters for better device performances. The CIGS solar cell model is developed and simulated using solar cell capacitance simulator (SCAPS). The final results prove that the proposed combinational GRA-MLR-GA model has successfully optimized the CIGS solar cell parameters in which ZnO thickness (TZnO), Cds thickness (TCds), CIGS thickness (TCIGS) and CIGS doping concentration (NaCIGS) are predictively optimized to be 0.03 μm, 0.03 μm, 2.86 μm and 9.937 x1017 cm-3 respectively. The most optimum magnitudes for open circuit voltage (Voc), short circuit current density (Jsc), fill factor (FF), and power conversion efficiency (η) after the predictive analytics are measured at 0.8206 V, 32.419 mA/cm2, 83.23% and 22.14% reciprocally.