• Neeraj Pareek
• Ayushi Gill
• Hitiksha Manoti
• Alina Banu

Horticultural price forecasting in India is confronted with climate variability, policy shifts, and disintegrated supply chains. This paper introduces BloomNet, a comprehensive and AI-based hybrid forecasting framework to stabilize farm markets. By integrating ARIMA's excellence in linear trend forecasting with LSTM's capacity to forecast complex, non-linear patterns, BloomNet successfully predicts prices of 22 critical agri-horticultural commodities—like onions, tomatoes, potatoes, and pulses—with an average accuracy of 89%. The model makes use of current data from Agmarknet, IMD weather forecasts, and e-NAM trading platforms, with the outcome of reducing Mean Absolute Error (MAE) by 30% from standalone conventional models. Also, empirical analysis reveals a 25–34% increase in RMSE for SARIMA and Prophet models, particularly for very volatile crops. To support greater accessibility and reach, BloomNet has a farmer-friendly mobile platform that support informed decision-making by farmers, traders, and policymakers. The convergence of historical prices, crop production, weather conditions, and economic data in the system makes it an effective tool for counteracting price volatility and enhancing agricultural resilience.

Agricultural Economics, Hybrid ML, Price Volatility, Explainable AI, Supply Chain Optimization

"BloomNet: An AI-Based Forecasting System for Stabilizing Agri-Horticultural Prices", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.12, Issue 6, page no.414-423, June-2025, Available :http://www.jetir.org/papers/JETIRGW06069.pdf

"BloomNet: An AI-Based Forecasting System for Stabilizing Agri-Horticultural Prices", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.12, Issue 6, page no. pp414-423, June-2025, Available at : http://www.jetir.org/papers/JETIRGW06069.pdf