Accurate prediction of spot colors is one of the important technologies in the field of packaging and printing. In order to obtain more accurate spot color formulas and improve the accuracy of spot color matching, a spot color formula prediction method combining least squares method and enhanced longicorn whisker search algorithm was proposed, and absorbance was used to solve the problem of spot color formula prediction. Studied the spectral model of high transmittance PET film and constructed an absorption spectral mechanism model; We proposed an enhanced longicorn whisker search algorithm, which introduces mutation probability terms and direction correction terms on the basis of traditional longicorn whisker search algorithms to improve the search ability and convergence speed of the algorithm; Optimize the color gamut space using the least squares method, reduce the search dimension of the primary color, and improve the optimization efficiency. The proposed enhanced longicorn whisker search algorithm is applied to solve the proportion of each primary color, predict the spot color formula, and compare it with traditional longicorn whisker algorithm, particle swarm algorithm, and ant colony algorithm to verify the effectiveness and superiority of the proposed method in spot color prediction. The research results show that the proposed method has higher accuracy compared to the existing three methods. The color difference between the original spot color and the predicted spot color is less than 3, and 90% of the color difference is less than 1, while 40% of the color difference is less than 0.1. The proposed method has a significant effect on improving the color matching accuracy of spot color inks and can accurately predict spot color formulas.