Indonesia, as an agrarian country, heavily relies on the plantation sector as a key driver of its national economy. One significant region contributing to this sector is West Aceh Regency, which consists of 12 districts and is renowned for cultivating five main plantation commodities: oil palm, coconut, rubber, coffee, and cocoa. This research aims to develop a plantation crop production prediction system to support efficient resource planning and management in this sector. The system employs Linear Regression and Single Exponential Smoothing (SES) with a smoothing constant (alpha) of 0.2. The system's primary objective is to analyze historical production data at the district level and generate reliable predictions of future production trends. Linear Regression models the relationship between time (independent variable) and production volume (dependent variable), effectively capturing long-term trends. SES complements this by addressing short-term fluctuations, applying a weighted average where recent data carries greater importance. Prediction accuracy is evaluated using the Mean Absolute Percentage Error (MAPE). Findings reveal that Linear Regression consistently achieves high accuracy, with MAPE values below 20% in most districts, particularly for coffee and cocoa. Conversely, SES demonstrates varying results, performing well in some cases, such as coconut production in Arongan Lambalek (MAPE 20%), but poorly in others, such as oil palm in Bubon (MAPE = 91.06%). In comparison, Linear Regression in Bubon yields a more moderate MAPE of 35.16%. The system is integrated into a user-friendly, web-based platform, accessible to stakeholders like farmers, policymakers, and government agencies. By offering actionable insights into production trends, it aids in mitigating risks, optimizing resource allocation, and enhancing plantation management efficiency. This research underscores the importance of predictive analytics in agricultural planning, with potential applications in other agrarian regions.