The objective of this investigation was to construct an artificial neural network (ANN) prediction model for chemicals like anthocyanin, titratable acidity, total solids soluble (TSS),vitamin C, titratable/TSS, and overall carotenoids levels of peach fruit employing surface color quantities, single fruit mass, liquid quantity, and sphericity percentage. In the initial hidden layer, an ANN framework with 6 inputs and fifteen neurons was built to predict 6 chemical compositional variables.Sensitivity testing found that liquid quantity was the most essential factor for determining titratable acidity,vitamin C, and titratable/TSS acidity. Furthermore, sphericity contributes 23.7% to anthocyanin and 24.0% to the overall carotenoids. Also, the color on TSS prediction had the largest contributing proportion of 20.8% when contrasted to the other characteristics. Chroma accounted for all parameters at varying levels ranging from 5.2 to 19.3%. Also, fruit mass attributed to every parameter at varying rates ranging from 16.6 to 23.4%. The ANN prediction approach represents a viable instrument for predicting the chemical compositional values of peach fruits at certain intended limits.