Contact dermatitis tremendously impacts the quality of life of suffering patients. Today diagnostic regimes rely on allergy testing, exposure specification, and follow-up visits; however, distinguishing the clinical phenotype of irritant and allergic contact dermatitis remains difficult in some cases. Employing integrative transcriptomic analysis and machine-learning approaches, we aimed to decipher disease-related signature genes to find suitable sets of biomarkers. Random Forest classification identified potential biomarkers to distinguish allergic and irritant contact dermatitis in human skin. Validation experiments and prediction performances on external testing datasets demonstrated potential applicability of the identified biomarker models in the clinic. Capitalizing on this knowledge, novel diagnostic tools can be developed to guide clinical diagnosis of contact allergies.