Ecommerce Price Tracking and Reporting
KANDI KISHORE YADAV 1, (Student), KOKKU DEEPAK YADAV(Student)1, KODUMURU NAVANEETH1(Student), KODI AJAY KUMAR REDDY(Student)
1Department of Computer Science and Engineering, Bharath Institute of Higher Education and Research (BIHER) at Tambaram, Chennai 600073, India
Corresponding author: Mrs. S.K. UMA MAHESHWARI
ABSTRACT Amazon’s dynamic pricing ecosystem presents challenges and opportunities for businesses and individuals aiming to optimize purchasing decisions, manage inventory costs, and maintain competitive pricing. This study explores advanced methodologies and technologies for monitoring Amazon prices, focusing on automation, data collection, and analysis. Key technologies include web scraping frameworks such as BeautifulSoup, Selenium, and Playwright; APIs like the Amazon Product Advertising API; and data storage solutions using SQL, NoSQL databases, or cloud services. The research delves Into algorithms utilized in price monitoring, including web scraping parsers, data cleaning pipelines, and machine learning models like Linear Regression for trend analysis, Time Series Forecasting (ARIMA, Prophet) for predicting price fluctuations, and Clustering Algorithms (K-Means, DBSCAN) for grouping price patterns across categories. Additionally, NLP algorithms assist in extracting contextual information from product descriptions, while Anomaly Detection Models flag irregular pricing behavior. The study also evaluates the integration of real-time monitoring systems via streaming technologies such as Apache Kafka and alert systems using cloud-based notification services. Ethical and legal considerations are addressed to ensure compliance with Amazon’s terms of service. The findings highlight how leveraging these technologies and algorithms can empower businesses to enhance profitability and enable consumers to make informed purchasing decisions in a competitive e-commerce landscape.
INDEX TERMS E-commerce, Price Tracking, Web Scraping, Market Analytics, Price Forecasting
