This paper introduces a novel personalized recommendation model called Stacked Noise Reduction Auto Encoder–OCEAN (SDAE-OCEAN), which integrates the OCEAN personality model with deep learning techniques to enhance recommendation accuracy. The OCEAN model captures five personality traits: openness, conscientiousness, extroversion, agreeableness, and neuroticism. The proposed model uses a stacked denoising autoencoder (SDAE) to reduce the dimensionality of user and item feature matrices, extracting deeper information. The user's OCEAN personality matrix is then integrated with the reduced user feature matrix to form a comprehensive user feature matrix. This matrix is combined with the item feature matrix to generate a comprehensive feature matrix, which is used for rating prediction via multiple linear regression. The model's performance is evaluated using RMSE and MAE, showing improved recommendation accuracy compared to traditional methods. The results indicate that incorporating the OCEAN personality model enhances the model's ability to provide personalized recommendations. The study also highlights the importance of considering user personality traits in recommendation systems to improve personalization and user satisfaction. The model's effectiveness is validated through experiments on real-world data, demonstrating its potential for application in personalized recommendation systems.This paper introduces a novel personalized recommendation model called Stacked Noise Reduction Auto Encoder–OCEAN (SDAE-OCEAN), which integrates the OCEAN personality model with deep learning techniques to enhance recommendation accuracy. The OCEAN model captures five personality traits: openness, conscientiousness, extroversion, agreeableness, and neuroticism. The proposed model uses a stacked denoising autoencoder (SDAE) to reduce the dimensionality of user and item feature matrices, extracting deeper information. The user's OCEAN personality matrix is then integrated with the reduced user feature matrix to form a comprehensive user feature matrix. This matrix is combined with the item feature matrix to generate a comprehensive feature matrix, which is used for rating prediction via multiple linear regression. The model's performance is evaluated using RMSE and MAE, showing improved recommendation accuracy compared to traditional methods. The results indicate that incorporating the OCEAN personality model enhances the model's ability to provide personalized recommendations. The study also highlights the importance of considering user personality traits in recommendation systems to improve personalization and user satisfaction. The model's effectiveness is validated through experiments on real-world data, demonstrating its potential for application in personalized recommendation systems.