In the realm of drug discovery, accurately predicting LogS – a crucial property influencing a drug's behavior within the body – is paramount. Traditional methods often struggle to capture the complex relationships in chemical data. This study explores the use of deep learning, specifically Feedforward Neural Networks (FNN), for LogS prediction. Through meticulous data preparation and model optimization, our FNN model achieved exceptional performance, with an R-squared (R2) score of 0.994 and a Mean Squared Error (MSE) of 0.024. These results highlight the transformative potential of deep learning techniques in drug discovery, offering unprecedented accuracy and efficiency. By accurately predicting LogS values, researchers can streamline the drug design process, ultimately leading to the development of safer and more effective therapeutics. Our findings underscore the importance of harnessing cutting-edge technologies to address the complex challenges facing modern medicine, heralding a new era of innovation and discovery.