A Review of Demand Forecasting Models for Indian Coffee Exports: Bridging Gaps and Opportunities

Abstract

Accurate demand forecasting is crucial for Indian coffee exports, given the sector's vulnerability to market volatility, shifting consumer preferences, and global trade dynamics. While traditional models like ARIMA are widely used, they struggle to address the nonlinear complexities and external factors such as climate variability and trade policies. This review critically synthesizes forecasting methodologies for Indian coffee exports, evaluating their strengths, limitations, and gaps. A systematic review of studies published between 2004 and 2024 was conducted, using databases like Scopus, Springer, and Elsevier, with a focus on relevance to coffee demand forecasting. Findings reveal that while traditional statistical models are effective for linear trends and seasonality, they fail to capture the dynamic nature of the market. Machine learning and hybrid models provide improved accuracy but face scalability and computational challenges. This review highlights gaps in integrating real-time data and domain-specific factors, offering insights for refining forecasting approaches and addressing emerging challenges in the field.