The exponential rise in e-commerce has revolutionized online shopping with unprecedented choices in products and platforms such as Amazon and Flipkart for consumers but also posing difficulties through dynamic pricing and information overload. Consumers end up finding it difficult to spot optimal buying opportunities because current tools do not possess the capability to offer real-time price projections and qualitative product information concurrently, missing out on savings and ill-informed purchasing decision. This study fills in the gaps by improving a mobile app that can educate and empower consumers with full-price tracking and decision-making assistance, using semantic analysis and the ETS (Error, Trend, Seasonality) model to offer an effective, two-for-one solution. The app built using a Flutter frontend for cross-platform use, a Dart API backend for streamlined data handling, and Firebase for real-time data synchronization, brings together semantic analysis with ETS forecasting. Semantic analysis works on unstructured text data, including product reviews and descriptions, to produce sentiment-driven summaries and recommendations, while ETS works on historical price data using the likes of Et = Yt − Yt (additive error) for random changes, Tt = α(Yt − St − m) + (1 − α)(Tt − 1 + Bt − 1) for long-run trends, St = β(Yt − Tt) + (1 − β)St − m for cyclical patterns, and Y^t + h = (Tt + hBt)St + h − m for future price forecasts This two-tailed approach supports features like visualization of price trends, user-personalized alerts, and sentiment-driven insights. Testing against 15 months of data for 100 products illustrated ETS got a Mean Absolute Percentage Error (MAPE) of 8.2% when forecasting decreases in price in a 7-day window at 90% accuracy, as semantic analysis added 25% improvement in relevance of recommendations through identification of issues of quality (e.g., “Price going down, yet review comments reflect durability problems”). Other improvements involve price monitoring across multiple countries, enabling regional sales within India. With the combination of quantitative price prediction with qualitative product knowledge, this solution greatly improves consumer choice, providing a scalable, efficient system that minimizes processing delay by 30% over isolated approaches. Emerging work will investigate automated buy triggers, increased platform coverage, and support from external economic indicators such as inflation rates, ensuring an improved, cheaper, and consumer-driven e-commerce journey.