Ansari Saleh Ahmar, Eva Boj del Val
Accurate import forecasting remains a critical challenge for emerging economies where trade volatility complicates policy planning. This study introduces HybridSutte (HySutte), a novel hybrid forecasting methodology integrating five components: selective outlier handling via median absolute deviation, trend-residual decomposition, enhanced α-Sutte forecasting, pattern matching, and adaptive weight optimization. Using Indonesian monthly import data (January 2021–December 2024), we evaluate HySutte against trigonometric seasonality, Box-Cox transformation, ARMA errors, trend and seasonal components (TBATS), and error, trend, seasonal (ETS) models. Performance is assessed using root mean square error (RMSE), mean absolute error (MAE), and mean absolute percentage error (MAPE), supplemented by robustness testing and economic impact analysis. On test data, HySutte reduces RMSE by 28.1% compared to TBATS and 47.3% compared to ETS, while achieving superior outlier robustness and the lowest total economic costs through an optimal balance between inventory holding and stockout penalties. Sensitivity analysis confirms these advantages hold across alternative cost structures. These findings offer methodological contributions to forecasting literature while providing practical tools for policymakers navigating economic uncertainty in emerging markets. © The Author(s), under exclusive licence to Springer Nature Switzerland AG 2026.
Department of Statistics, Faculty of Mathematics and Natural Sciences, Universitas Negeri Makassar, Makassar, Indonesia; Department of Economics, Financial, and Actuarial Mathematics, Universitat de Barcelona, Barcelona, Spain
