This study aims to design a data mining model for predicting customer satisfaction and identifying critical drivers of product quality perception in food industry companies located in Shahrood, using data mining techniques. This applied research was conducted as a survey-case study within a representative food processing company in the region. The statistical population included all customers providing feedback over the last year (approximately 300 records). The necessary data were extracted from online review platforms, direct feedback forms, and sales transaction records. Key variables investigated included product attributes (taste, packaging, freshness), service quality, and demographic features. The Random Forest and Support Vector Machine algorithms were utilized in a Python environment for data analysis. The results demonstrated that the Random Forest algorithm performed superiorly with an accuracy of 89.2% compared to the Support Vector Machine with an accuracy of 84.5%. The most significant factors influencing customer satisfaction were found to be product freshness and packaging integrity . The proposed model can predict customer satisfaction levels with acceptable accuracy and provide food company managers with actionable insights for strategic quality planning and targeted marketing efforts.