Guerbet alcohol (GA) is β-branched primary alcohol having excellent physiochemical properties like lower pour point (PP) and higher kinematic viscosity (KV) in comparison to linear alcohol. Although different aspects of the synthesis of GA, such as methods of synthesis, catalytic systems, and reaction conditions, have been studied, but statistical modeling and optimization of the synthesis of GA have not been carried out. In the present work, the optimization of the synthesis of GA using a mixture of lauryl and myristyl alcohol was carried out with the aid of response surface methodology (RSM) considering the conversion of the reaction, PP and KV at 40˚C & 100˚C as dependent variables. The optimal reaction conditions were temperature, pressure, and time of 220˚C, 300 mbar, and 10 hours respectively. The optimum conversion was 99.141%, including dimer yield of 81.755%, PP of -3˚C, KV at 40˚C & 100˚C of 34.12 cSt & 7.22 cSt, respectively. The results obtained by the RSM were then authenticated, applying artificial neural networks (ANN) generated with the help of MATLAB. The ability of the generated model to predict the response variables was validated by less than 5% error for almost all the models, confirming the statistical significance. Also, the tribological potential for linear Ginol-12,14 (FA) and synthesized branched GA as lubricant additive was evaluated by determining its physiochemical, thermal and tribological properties.