Understanding customer sentiments expressed in reviews is crucial for businesses to make informed decisions. Aspect-based sentiment analysis (ABSA) plays a vital role in this domain by identifying specific aspects mentioned in reviews along with their associated polarities. This paper addresses the challenge of ABSA using a supervised dataset and proposes a novel model for training and testing. The primary contribution of this study lies in the development of a robust model capable of predicting aspects and their polarities in previously unseen data. By leveraging methods from both machine learning and natural language processing, the proposed model enhances business understanding of customer reviews, thereby improving decision-making efficiency.