<p>The milk adulteration with cheaper or potentially hazardous substances poses a significant health risk to consumers and results in fatalities which have been reported in several countries, including China and Australia. This study introduced an analytical method for detecting and predicting the adulteration of pasteurized cow milk with coconut milk and corn starch as adulterants by combining voltammetric fingerprints with chemometric analysis. The samples were collected from the local market and analyzed using cyclic voltammetry using a glassy carbon electrode modified with hydroxyl functionalized multi-walled carbon nanotubes (GCE/MWCNT-OH) with potassium chloride (KCl) as the electrolyte. Cow milk and coconut milk samples displayed broad peaks in the anodic potential scan between 0.5 and 0.8&#xa0;V versus Ag/AgCl, attributed to various electroactive species in the milk. However, the corn starch sample was analyzed using similar methods, these peaks were not detected. The distinct voltammetric profiles of cow milk, coconut milk, and corn starch samples were used to detect adulteration by applying chemometric analysis to voltammetric data. The current values recorded at all potentials and at the positive potentials were analyzed using multivariate techniques. Principal component analysis effectively distinguished between cow milk and adulterants. Partial least squares regression analysis was employed to predict the adulteration of cow milk, using electrochemical signal intensities as the predictors or observed value and adulterant concentration levels as the response variable or predicted value. The model demonstrated linearity across the full concentration range from 0 to 100% (v/v) regarding observed versus predicted values. Results showed that combining voltammetric fingerprints and chemometrics analysis could be used to screen potential adulteration practices in dairy products.</p> Graphical Abstract <p></p>