Uncertainty in experimental measurements is likely to be incorporated due to various limitations in measurement instruments, experimental procedures, quantity of chemicals, etc. Obtaining the true properties of nanofluids is a difficult task. Hence, the evaluation of the dynamic viscosity and density is strenuous. The present work aims to study the influence of uncertainties in temperature and concentration on density and dynamic viscosity of Graphene nanoparticle/distilled water, multiwall carbon nanotube/distilled water, and alumina/distilled water nanofluids using Gaussian Process Regression (GPR) learning algorithm guided Monte-Carlo simulations. The GPR algorithm is employed to predict the properties of the nanofluids which are then fed to Monte-Carlo simulations to predict the uncertainty. The noise and uncertainties are introduced in the mole fraction and temperature artificially and are validated using the Kolmogorov-Smirnov test and Quantile-Quantile plot. The influence of different noise levels in the data is also carried out.