What question did this study set out to answer?

To develop an effective sales forecasting model for KOTEM Bondowoso using a hybrid ARIMA and neural network approach.

February 2, 2026Buana Information Technology and Computer Sciences (BIT and CS)0 citationsOpen Access

Arabica Coffee Sales Forecasting Using ARIMA Neural Network (Case Study: KOTEM Bondowoso)

MFMuhammad Ariful Furqon SESaudi EfendiUniversitas Jember YNYanuar NurdiansyahUniversitas Jember

Key Points

To develop an effective sales forecasting model for KOTEM Bondowoso using a hybrid ARIMA and neural network approach.
Analyzed KOTEM sales data from September 2019 to August 2022.
Applied ARIMA for linear and seasonal trend analysis.
Utilized neural networks for capturing non-linear patterns.
Preprocessed data to address non-stationarity through differencing and normalization.
Hybrid model achieved 1.0% MAPE compared to ARIMA's 1.3%.
Better captured sales volatility and seasonal changes.
Provided more reliable forecasts for production scheduling and inventory management.

Abstract

Kopi Tembakau (KOTEM) Bondowoso is a local coffee producer specializing in Arabica ground coffee, sourced directly from nearby farmer cooperatives. A major hurdle they face is accurately forecasting sales, a critical factor for optimizing production and inventory. To tackle this, a hybrid forecasting model blending ARIMA (for linear/seasonal trends) and Neural Networks (for non-linear patterns) was developed. The study analyzed KOTEM’s sales data from September 2019 to August 2022, preprocessed to address non-stationarity via differencing and normalization. Results revealed the hybrid model outperformed standalone ARIMA, achieving a 1.0% MAPE (vs. ARIMA’s 1.3%). It also better captured sales volatility and seasonal shifts, offering more dependable forecasts. ARIMA-NN could significantly enhance KOTEM production scheduling and stock management.

问 AI

Bookmark

View Full Paper