Membrane fouling, a critical issue in membrane performance associated with proteins, is often difficult to analyze due to limited knowledge of contamination scenarios. This study uses a one-dimensional convolutional neural network (ODCNN) to examine the complex relationships among membrane properties, protein characteristics, and operational parameters, aiming to elucidate the dynamics of protein-related contamination. To improve the predictive performance of the deep learning model, we propose a novel strategy that learns numerical and categorical features in sequence. Compared with the other seven conventional models, our results reveal that the ODCNN model shows the best performance, which achieves impressive coefficients of determination, reaching 0.833 for flux and 0.723 for protein rejection, indicating the model’s robustness even when dealing with incomplete information on membrane fouling. To mitigate the issue of insufficient data, we applied the Synthetic Minority Over-Sampling Technique to increase the dataset’s diversity, validating this approach with experimental evidence. To improve the interpretability of the model, we used the Shapley Additive exPlanations method to assess the contribution of various features, which revealed that membrane pore size, protein concentration, transmembrane pressure, and crossflow velocity are key factors influencing both flux and protein retention. We also analyzed the causes and assessed the degree of contamination according to the degree of their influence. By leveraging machine learning techniques to analyze and predict membrane filtration performance, particularly concerning protein fouling, this study demonstrates significant potential for practical applications in environments with limited information. This innovative approach is poised to contribute to ongoing advancements in membrane filtration technology and offers a promising pathway for enhancing the understanding and management of membrane fouling.