This research paper introduces a comprehensive method for predicting the age at which hens achieve optimal egg production using mixed linear regression models. By combining two distinct linear regression models and machine learning techniques, we aim to enhance the accuracy and reliability of age prediction for maximizing egg-laying efficiency in hens. The mixed linear regression model is built by integrating parameters estimated through ordinary least squares regression. Various models are derived by incorporating components from these two linear regression models, allowing for exploration of different prediction possibilities. Evaluation measures such as the coefficient of determination and residual sum of squares are utilized to assess model performance and identify the most accurate ones for predicting optimal egg production age. To validate the practical utility of the proposed models, authentic egg production data is used for verification. The predictive capabilities of the mixed linear regression models are extensively assessed against this real dataset, enabling selection of the most suitable model for practical application. In summary, this research demonstrates the effectiveness of the mixed linear regression approach in predicting optimal egg production age in hens, offering valuable insights for enhancing efficiency and productivity in poultry farming.