In recent years, with the rapid development of food science and computer technology, machine learning has been increasingly applied in various fields of the food industry, especially in the detection and optimization of food components, demonstrating its unique advantages. This article took acorn starch as the research object, used machine learning methods to analyze its basic physicochemical properties and material components, and used high-throughput chemical analysis methods, combined with machine learning methods, such as Support Vector Machine (SVM), Random Forest (RF), and Linear Regression (LR), to systematically analyze its components and predict its features. This article conducted detailed chemical analysis of acorn samples through drying, crushing, and extraction of chemical components, using methods such as Gas Chromatography Mass Spectrometry (GC–MS) and Liquid Chromatograph Mass Spectrometer (LC–MS) to obtain massive amounts of data. On this basis, machine learning methods were used to model it and predict its physicochemical properties such as viscosity, solubility, and saccharification kinetics. Random forest performed the best with an accuracy of 0.88, showing high accuracy and being able to better identify the physicochemical properties of acorn starch. Through the implementation of this article, accurate analysis of the physicochemical properties and components of acorn seed starch can be achieved, providing new ideas and methods for food science research.