Development of an Intelligent Browser-Based E-Commerce Price Tracker: A Review

The dynamic nature of online pricing, influenced by market demand, inventory variations, and promotional campaigns, often challenges both consumers and retailers in determining optimal purchase or pricing strategies. This paper presents an intelligent browser extension designed to automate e-commerce price monitoring, analyze historical data, and forecast future price movements through machine learning techniques. The system integrates ethical data acquisition through automated web extraction and APIs, followed by preprocessing and feature engineering to refine inputs such as discount cycles and product categories. Predictive modeling employs supervised learning algorithms including Random Forest Regressor and time-series regression methods to generate actionable insights with performance validated through Mean Absolute Error (MAE). By visualizing historical trends and providing interpretable “Buy Now” or “Wait” recommendations, the extension enhances decision-making transparency and user trust. Beyond supporting consumers, the framework serves as a practical application of data science and predictive analytics for retailers, analysts, and educators seeking data-driven strategies within the evolving e-commerce ecosystem.