EXPLAINABLE FORECASTING OF APPAREL AND FOOTWEAR TRADE VALUES: FEATURE ATTRIBUTION IN A LEAKAGE-SAFE TIME-BASED FRAMEWORK
DOI:
https://doi.org/10.47701/t4gg6j55Keywords:
Explainable AI, Trade Forecasting, SHAP, Permutation Importance, Time-Based EvaluationAbstract
Accurate trade-value forecasts are increasingly required to be not only precise but also interpretable, so that model outputs can be audite d before informing trade and logistics decisions. This study extends a previously validated leakage-safe forecasting framework for Indonesia's apparel and footwear commodities (HS 61, HS 62, HS 63, and HS 64) by adding formal feature attribution to the best-performing model. Monthly trade values from Statistics Indonesia (BPS) covering January 2017 to March 2026 were modeled using nineteen predictors spanning historical lags, rolling statistics, calendar-seasonal signals, and exogenous variables, under a strict chronological train-validation-test protocol. Random Forest, the strongest model in the prior comparison with a holdout MAPE of 22.7746 percent, ahead of Extra Trees Regression at 22.9469 percent and SARIMA at 28.9794 percent, is interpreted using permutation importance and SHapley Additive exPlanations (SHAP). Attribution results show that contribute most to out-of-sample predictions, while exogenous variables. The framework demonstrates that accuracy and transparency can be obtained jointly on official trade statistics.
References
Abdullah, M. (2024). Explainable deep learning model for stock price forecasting using textual analysis. Expert Systems with Applications. https://doi.org/10.1016/j.eswa.2024.123740
Allen, S., Ziegel, J., & Ginsbourger, D. (2024). Assessing the calibration of multivariate probabilistic forecasts. Quarterly Journal of the Royal Meteorological Society. https://doi.org/10.1002/qj.4647
Ardiyanto, M., Irawan, R. D., & Yudhianto, K. A. (2025). Implementation and optimization of saliency mapping algorithms in convolutional neural networks to enhance transparency in pneumonia diagnosis. In Proceedings of the International Conference on Science and Health Technology (pp. 490-500).
Arndt, C., Diao, X., Dorosh, P., Pauw, K., & Thurlow, J. (2023). The Ukraine war and rising commodity prices: Implications for developing countries. Global Food Security, 36, 100680. https://doi.org/10.1016/j.gfs.2023.100680
Breiman, L. (2001). Random forests. Machine Learning, 45(1), 5-32. https://doi.org/10.1023/A:1010933404324
Celik, O., Altinsoy, E., & Suliman, A. (2025). Hybrid forecasting for agricultural commodity prices: Statistical learning and interpretable machine learning evidence. Borsa Istanbul Review. https://doi.org/10.1016/j.bir.2025.04.003
Chen, H., Zhang, Y., & Liu, Q. (2025). Explainable machine learning methods for predicting building energy consumption. Scientific Reports. https://doi.org/10.1038/s41598-025-27285-2
Chowdhury, I., Kun, Z., & Boako, G. (2025). Geopolitical risk and energy market tail risk forecasting. Journal of Commodity Markets, 25, 100334. https://doi.org/10.1016/j.jcomm.2025.100334
Hothorn, T., Barbanti, L., & Siegfried, S. (2023). Probabilistic time series forecasts with autoregressive transformation models. Statistics and Computing. https://doi.org/10.1007/s11222-023-10212-8
Hyndman, R. J., & Athanasopoulos, G. (2021). Forecasting: Principles and practice (3rd ed.). OTexts.
Irawan, R. D., Ardiyanto, M., Buwono, R. I., & Nastiti, F. E. (2026). Perbandingan kinerja model forecasting nilai perdagangan komoditas HS pada evaluasi time-based. JURIKOM (Jurnal Riset Komputer), 13(3), 1129-1140. https://doi.org/10.30865/jurikom.v13i3.9843
Jo, W., & Kim, H. (2023). Neural additive time-series models: Explainable deep learning for time series forecasting. Expert Systems with Applications, 223, 119954. https://doi.org/10.1016/j.eswa.2023.119954
Lin, F., Li, X., & Jia, N. (2023). The impact of Russia-Ukraine conflict on global food security. Global Food Security, 36, 100661. https://doi.org/10.1016/j.gfs.2022.100661
Lundberg, S. M., & Lee, S.-I. (2017). A unified approach to interpreting model predictions. In Advances in Neural Information Processing Systems 30 (pp. 4765-4774). Curran Associates.
Molnar, C. (2025). Interpretable machine learning: A guide for making black box models explainable (3rd ed.).
Neubauer, A., Brandt, S., & Kriegel, M. (2025). Explainable multi-step heating load forecasting: Using SHAP values and temporal attention mechanisms for enhanced interpretability. Energy and AI, 20, 100480. https://doi.org/10.1016/j.egyai.2025.100480
Schlembach, F., Smirnov, E., & Koprinska, I. (2025). Conformal multistep-ahead multivariate time-series forecasting. Machine Learning, 114, 165. https://doi.org/10.1007/s10994-024-06722-9
Schosser, J., Fedorova, M., & Lange, T. (2024). Beyond point forecasts: Uncertainty quantification in tensor extrapolation for relational time series data. Journal of Business Analytics. https://doi.org/10.1080/23737484.2024.2329171
Shajalal, M., Boden, A., & Stevens, G. (2024). ForecastExplainer: Explainable household energy demand forecasting by approximating Shapley values using DeepLIFT. Technological Forecasting and Social Change, 206, 123588. https://doi.org/10.1016/j.techfore.2024.123588
Song, X., Deng, L., & Wang, H. (2024). Deep learning-based time series forecasting: A comprehensive review. Artificial Intelligence Review. https://doi.org/10.1007/s10462-024-10989-8
Turbe, H., Bjelogrlic, M., & Lovis, C. (2023). Evaluation and explanation of deep learning-based time series forecasting models. Nature Machine Intelligence. https://doi.org/10.1038/s42256-023-00724-9
Wang, P., Chen, K., & Yao, L. (2024a). Interval time series forecasting: A systematic literature review. Journal of Forecasting. https://doi.org/10.1002/for.3024
Wang, N., Shao, W., & Song, D. (2024b). Carbon trading price forecasting with a new explainable machine learning approach. Technological Forecasting and Social Change, 200, 123178. https://doi.org/10.1016/j.techfore.2024.123178
Wu, X., & Wang, J. (2024). Wind speed forecasting using Temporal Fusion Transformers and SHAP. Energy Reports, 10, 5213-5224. https://doi.org/10.1016/j.egyr.2023.12.073
