The article discusses the use of modern modeling methods to optimize technological processes in the production of bakery products. The main goal of the research is to develop mathematical models that will improve baking parameters and ensure high quality of finished products. The key factors influencing the quality of baked goods, in particular temperature, humidity, baking time and dough composition, are analyzed. A variety of approaches are used to model baking processes, including linear and polynomial regression models, partial least squares, decision trees, and ensemble methods. The choice of these methods is justified by their ability to efficiently process categorical and numerical data, as well as to take into account complex relationships between process parameters. The study provides a comparative analysis of models using R2 and MSE metrics, which allows us to assess the accuracy and reliability of predictions. Particular attention is paid to the issues of coding categorical variables, in particular the use of Label Encoding, and its impact on modeling results. The results of the study demonstrate that the use of the proposed models in the control process can improve the quality of baked goods, providing optimal baking conditions.