In this research, definite, precision and correct spectrophotometric - chemometric techniques were developed for the drugs containing codeine and acetaminophen. The examined commercial pharmaceutical is Geralgine. The used calibration-prediction methods are partial least squares regression (PLSR) and independent component analysis-artificial neural networks (ICA-ANN). A concentration set including binary mixtures of codeine and acetaminophen formed to 25 different concentrations, were synthetic set prepared in 96% ethanol. The precision and accuracy of the developed method were validated by analyzing synthetic mixture containing the examining drug. Eventually, high recoveries and very low relative standard deviations were found.