Embodiments present a method for fluid type identification from a downhole fluid analysis that uses machine learning techniques that are trained and derived from a computer model using pressure, temperature and downhole optical characteristics of sampled fluid. The method comprises collecting optical spectral data for a downhole fluid; providing the collected optical spectral data to a trained classification module; processing the collected optical spectral data with the trained classification module configured to determine a fluid type classification; and determining a fluid type based upon the classification based upon the trained classification module.