• S. Amirtharaj
• K. Shiva Varshini

In today’s dynamic e-commerce world, consumers are faced with difference in product prices across multiple platforms, so there is a need for creating automated price comparison tools for making the user purchase more reliable. This paper presents a comprehensive system that extracts and compares product prices from various e-commerce platforms, specifically Amazon and Flipkart. To further enhance decision-making capabilities, the system includes advanced machine learning (ML) techniques for forecasting future price trends. By enabling predictive insights, users are empowered to make informed decisions regarding optimal purchasing times. The study investigates and compares the performance of several regression-based ML models including Linear Regression, Decision Tree Regressor, Random Forest Regressor, and XGBoost based on their accuracy and predictive reliability. The experimental evaluations of these models demonstrate that the integration of predictive analytics into price comparison systems significantly enhance user decision-making, leading to smarter, data-driven shopping experiences.

Price Comparison, Web Scraping, Machine Learning, Price Forecasting, E-commerce Intelligence, XGBoost, Random Forest

"EVALUATION OF MACHINE LEARNING BASED PREDICTION SYSTEMS FOR COMPARING ONLINE PRODUCT PRICES", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.12, Issue 4, page no.l408-l413, April-2025, Available :http://www.jetir.org/papers/JETIR2504B49.pdf

"EVALUATION OF MACHINE LEARNING BASED PREDICTION SYSTEMS FOR COMPARING ONLINE PRODUCT PRICES", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.12, Issue 4, page no. ppl408-l413, April-2025, Available at : http://www.jetir.org/papers/JETIR2504B49.pdf