<p>The use of seismic attributes for characterization and exploration is crucial. This significance increases with the growing number of attributes being used, developed, or newly derived, regardless of their relation to previous ones. Facies classification heavily depends on these attributes in conjunction with other predictive processes. A key focus of these processes is predicting organic carbon content using seismic data, particularly through the application of seismic attributes. The study of organic carbon content has gained attention from researchers because it provides critical information for identifying source rocks and kerogen-bearing formations, which are vital for future drilling operations. However, achieving high accuracy in facies classification and organic carbon prediction remains challenging due to the complexity of seismic data. In this study, we address this problem by integrating well-established seismic attributes with Hjorth parameters—initially developed for time-series analysis in medical applications, such as EEG signal processing—as novel seismic attributes for enhanced prediction and classification. The Hjorth parameters (activity, mobility, and complexity) capture temporal and spatial variations in seismic data, making them suitable for characterizing complex geological features. Using random forest machine learning models, we achieved a prediction and classification accuracy of up to 93%, significantly outperforming traditional analyses that exclude these parameters. These results demonstrate a reliable and innovative approach for improving source rock identification, offering valuable insights for optimizing future exploration and drilling strategies.</p>