Open Access Open Access  Restricted Access Subscription Access

SMART PRICE FORECASTING AND TREND ANALYSIS SYSTEM

Veam Dheeraj Reddy, PIDUGU RAJESH

Abstract


E-commerce platforms witness constant and unpredictable price fluctuations that make it difficult for consumers to identify the right moment to purchase a product. This paper presents the Smart Price Forecasting and Trend Analysis System, a full-stack web application that automates product price tracking and generates data-driven purchase recommendations using the AutoRegressive Integrated Moving Average (ARIMA) time-series model. The system scrapes real-time product prices from platforms such as Amazon and Flipkart using BeautifulSoup4, stores historical pricing records in MongoDB, and applies ARIMA(5,1,0) to produce a 30-day forward price forecast. The React.js frontend presents the forecast through interactive Chart.js visualizations and issues clear Buy Now or Wait recommendations based on predicted price trends. Experimental results confirm that the system accurately identifies short-term price movements and provides actionable consumer guidance, validating the effectiveness of statistical machine learning models for real-world e-commerce price intelligence applications.

Full Text:

PDF

References


H. Bakir, G. Chniti, and H. Zaher, "E-Commerce Price Forecasting Using LSTM Neural Networks," International Journal of Machine Learning and Computing, vol. 8, no. 2, pp. 169–174, 2018. https://www.researchgate.net/publication/325686014

S. Carta, A. Corriga, A. S. Podda, and D. R. Recupero, "Forecasting E-Commerce Products Prices by Combining ARIMA and Machine Learning Models," Future Internet, vol. 11, no. 1, 2018. https://www.mdpi.com/1999-5903/11/1/5

K. Bandara, C. Bergmeir, and H. Hewamalage, "Sales Demand Forecast in E-commerce using Long Short-Term Memory Neural Networks," Proc. Int. Conf. Advanced Analytics, 2019. https://arxiv.org/abs/1901.04028

H. Bakir and G. Chniti, "E-commerce Time Series Forecasting using LSTM," ACM Int. Conf. Data Science, 2018. https://dl.acm.org/doi/10.1145/3175684.3175695

D. Kobiela, "Comparison of ARIMA and LSTM Models for Time Series Forecasting," Procedia Computer Science, 2022. https://www.sciencedirect.com/science/article/pii/S1877050922013382

E. Handy, M. Korczak, and P. Szymanski, "Product-level Sales Prediction in E-commerce using LSTM," Procedia Computer Science, 2025. https://www.sciencedirect.com/science/article/pii/S1877050925026894

A. Abudureyimu, Y. Zhang, H. Wang, and Z. Chen, "Design of E-commerce Product Price Prediction Model using Improved GANs," Scientific Reports, 2025. https://www.nature.com/articles/s41598-025-10767-8

H. Wu, X. Li, and J. Zhang, "Predicting E-commerce Product Prices through Machine Learning Techniques," Journal of Retail Analytics, 2024. https://pmc.ncbi.nlm.nih.gov/articles/PMC11622893

B. M. Henrique, V. A. Sobreiro, and H. Kimura, "Stock Price Prediction using Support Vector Regression," Expert Systems with Applications, vol. 115, pp. 362–375, 2018. https://www.sciencedirect.com/science/article/pii/S2405918818300060

B. K. Meher, S. Dehuri, and S. K. Nayak, "Comparative Study of ARIMA, Random Forest and LSTM Models for Price Forecasting," Applied Soft Computing, 2024. https://www.sciencedirect.com/science/article/pii/S2199853123002822


Refbacks

  • There are currently no refbacks.