OPTIMIZATION-BASED MACHINE LEARNING FOR LATE DELIVERY CLASSIFICATION IN SUPPLY CHAINS: A COMPARISON OF METAHEURISTIC SEARCH STRATEGIES
Özet
Late deliveries raise logistics costs and erode customer trust. Firms therefore try to flag risky orders at the moment they are placed. This chapter treats the choice of input fields for such a model as a bi-objective problem that balances Macro-F1 against the number of fields. Three multi-objective metaheuristics are compared on three open delivery datasets. They are the non-dominated sorting genetic algorithm II (NSGA-II), a binary multi-objective particle swarm optimizer (MOPSO) and a binary multi-objective grey wolf optimizer (MOGWO). Random search, mutual information ranking and recursive feature elimination (RFE) serve as references. DataCo and SynDelay are synthetic or simulated, while Olist is real. All features are restricted to information known at order time, and automatic tests check for leakage. The search methods receive 800 fitness evaluations each, while the two ranking benchmarks need only one evaluation per feature. Ten paired runs are compared with Friedman and Holm-corrected Wilcoxon tests. NSGA-II and MOGWO found the best fronts in search space and did not differ from each other. Both beat random search and RFE on the synthetic data by small margins, and NSGA-II did so on Olist as well. MOPSO with default settings was worse than random search on every dataset. On the real Olist test period no method was significantly better than another, and RFE lost the least value. An earlier run with 240 evaluations showed no significant lead over RFE, so the ranking of search methods depends on the budget. On the synthetic data one or two fields led by the shipping mode matched the Macro-F1 of the full feature set. On Olist the signal was weak. Subsets from the accurate end of the Pareto front transferred well to random forest and logistic regression models. In practice a cheap RFE path is a sensible first step, and a metaheuristic is worth its cost only when it improves on that path on held-out data.
Anahtar Kelimeler: late delivery prediction, supply chain analytics, multi-objective feature selection, metaheuristics, data leakage, machine learning
Konu Alanı: Mühendislik -> Mühendislik (diğer) -> Endüstri Mühendisliği
Al-Tashi, Q., Abdulkadir, S. J., Rais, H. M., Mirjalili, S., & Alhussian, H. (2020). Approaches to multi-objective feature selection: A systematic literature review. IEEE Access, 8, 125076-125096. https://doi.org/10.1109/ACCESS.2020.3007291
Baryannis, G., Dani, S., & Antoniou, G. (2019). Predicting supply chain risks using machine learning: The trade-off between performance and interpretability. Future Generation Computer Systems, 101, 993-1004. https://doi.org/10.1016/j.future.2019.07.059
Baryannis, G., Validi, S., Dani, S., & Antoniou, G. (2019). Supply chain risk management and artificial intelligence: State of the art and future research directions. International Journal of Production Research, 57(7), 2179-2202. https://doi.org/10.1080/00207543.2018.1530476
Bergmeir, C., & Benítez, J. M. (2012). On the use of cross-validation for time series predictor evaluation. Information Sciences, 191, 192-213. https://doi.org/10.1016/j.ins.2011.12.028
Blank, J., & Deb, K. (2020). Pymoo: Multi-objective optimization in Python. IEEE Access, 8, 89497-89509. https://doi.org/10.1109/ACCESS.2020.2990567
Breiman, L. (2001). Random forests. Machine Learning, 45(1), 5-32. https://doi.org/10.1023/A:1010933404324
Brintrup, A., Pak, J., Ratiney, D., Pearce, T., Wichmann, P., Woodall, P., & McFarlane, D. (2020). Supply chain data analytics for predicting supplier disruptions: A case study in complex asset manufacturing. International Journal of Production Research, 58(11), 3330-3341. https://doi.org/10.1080/00207543.2019.1685705
Chicco, D., & Jurman, G. (2020). The advantages of the Matthews correlation coefficient (MCC) over F1 score and accuracy in binary classification evaluation. BMC Genomics, 21(1), 6. https://doi.org/10.1186/s12864-019-6413-7
Coello Coello, C. A., Pulido, G. T., & Lechuga, M. S. (2004). Handling multiple objectives with particle swarm optimization. IEEE Transactions on Evolutionary Computation, 8(3), 256-279. https://doi.org/10.1109/TEVC.2004.826067
Constante, F., Silva, F., & Pereira, A. (2019). DataCo smart supply chain for big data analysis (Version 5) [Data set]. Mendeley Data. https://doi.org/10.17632/8gx2fvg2k6.5
Deb, K., Pratap, A., Agarwal, S., & Meyarivan, T. (2002). A fast and elitist multiobjective genetic algorithm: NSGA-II. IEEE Transactions on Evolutionary Computation, 6(2), 182-197. https://doi.org/10.1109/4235.996017
Demšar, J. (2006). Statistical comparisons of classifiers over multiple data sets. Journal of Machine Learning Research, 7, 1-30. https://www.jmlr.org/papers/volume7/demsar06a/demsar06a.pdf
Derrac, J., García, S., Molina, D., & Herrera, F. (2011). A practical tutorial on the use of nonparametric statistical tests as a methodology for comparing evolutionary and swarm intelligence algorithms. Swarm and Evolutionary Computation, 1(1), 3-18. https://doi.org/10.1016/j.swevo.2011.02.002
Dwivedi, V. K., Kadian, K., Gardiner, B., Pandey, R., & Lathwal, A. (2025). Supply chain analytics: A performance evaluation of machine learning, statistical, and time-series models. Baltic Journal of Modern Computing, 13(2), 453-485. https://doi.org/10.22364/bjmc.2025.13.2.09
Emary, E., Zawbaa, H. M., & Hassanien, A. E. (2016). Binary grey wolf optimization approaches for feature selection. Neurocomputing, 172, 371-381. https://doi.org/10.1016/j.neucom.2015.06.083
Guyon, I., Weston, J., Barnhill, S., & Vapnik, V. (2002). Gene selection for cancer classification using support vector machines. Machine Learning, 46(1-3), 389-422. https://doi.org/10.1023/A:1012487302797
Holm, S. (1979). A simple sequentially rejective multiple test procedure. Scandinavian Journal of Statistics, 6(2), 65-70. https://www.jstor.org/stable/4615733
Jiao, R., Nguyen, B. H., Xue, B., & Zhang, M. (2024). A survey on evolutionary multiobjective feature selection in classification: Approaches, applications, and challenges. IEEE Transactions on Evolutionary Computation, 28(4), 1156-1176. https://doi.org/10.1109/TEVC.2023.3292527
Kapoor, S., & Narayanan, A. (2023). Leakage and the reproducibility crisis in machine-learning-based science. Patterns, 4(9), 100804. https://doi.org/10.1016/j.patter.2023.100804
Kaufman, S., Rosset, S., Perlich, C., & Stitelman, O. (2012). Leakage in data mining: Formulation, detection, and avoidance. ACM Transactions on Knowledge Discovery from Data, 6(4), 1-21. https://doi.org/10.1145/2382577.2382579
Ke, G., Meng, Q., Finley, T., Wang, T., Chen, W., Ma, W., Ye, Q., & Liu, T.-Y. (2017). LightGBM: A highly efficient gradient boosting decision tree. In Advances in Neural Information Processing Systems 30 (pp. 3146-3154). https://proceedings.neurips.cc/paper_files/paper/2017/file/6449f44a102fde848669bdd9eb6b76fa-Paper.pdf
Kennedy, J., & Eberhart, R. C. (1997). A discrete binary version of the particle swarm algorithm. In 1997 IEEE International Conference on Systems, Man, and Cybernetics (Vol. 5, pp. 4104-4108). IEEE. https://doi.org/10.1109/ICSMC.1997.637339
Kohavi, R., & John, G. H. (1997). Wrappers for feature subset selection. Artificial Intelligence, 97(1-2), 273-324. https://doi.org/10.1016/S0004-3702(97)00043-X
Lipton, Z. C., Elkan, C., & Naryanaswamy, B. (2014). Optimal thresholding of classifiers to maximize F1 measure. In Machine Learning and Knowledge Discovery in Databases (ECML PKDD 2014), Lecture Notes in Computer Science (pp. 225-239). Springer. https://doi.org/10.1007/978-3-662-44851-9_15
Mirjalili, S., Mirjalili, S. M., & Lewis, A. (2014). Grey wolf optimizer. Advances in Engineering Software, 69, 46-61. https://doi.org/10.1016/j.advengsoft.2013.12.007
Mirjalili, S., Saremi, S., Mirjalili, S. M., & Coelho, L. S. (2016). Multi-objective grey wolf optimizer: A novel algorithm for multi-criterion optimization. Expert Systems with Applications, 47, 106-119. https://doi.org/10.1016/j.eswa.2015.10.039
Olist. (2018). Brazilian e-commerce public dataset by Olist [Data set]. Kaggle. https://www.kaggle.com/datasets/olistbr/brazilian-ecommerce
Raquel, C. R., & Naval, P. C., Jr. (2005). An effective use of crowding distance in multiobjective particle swarm optimization. In Proceedings of the 7th Annual Conference on Genetic and Evolutionary Computation (GECCO 2005) (pp. 257-264). ACM. https://doi.org/10.1145/1068009.1068047
Saito, T., & Rehmsmeier, M. (2015). The precision-recall plot is more informative than the ROC plot when evaluating binary classifiers on imbalanced datasets. PLOS ONE, 10(3), e0118432. https://doi.org/10.1371/journal.pone.0118432
Salari, N., Liu, S., & Shen, Z.-J. M. (2022). Real-time delivery time forecasting and promising in online retailing: When will your package arrive? Manufacturing & Service Operations Management, 24(3), 1421-1436. https://doi.org/10.1287/msom.2022.1081
Shwartz-Ziv, R., & Armon, A. (2022). Tabular data: Deep learning is not all you need. Information Fusion, 81, 84-90. https://doi.org/10.1016/j.inffus.2021.11.011
Steinberg, F., Burggräf, P., Wagner, J., Heinbach, B., Saßmannshausen, T., & Brintrup, A. (2023). A novel machine learning model for predicting late supplier deliveries of low-volume-high-variety products with application in a German machinery industry. Supply Chain Analytics, 1, 100003. https://doi.org/10.1016/j.sca.2023.100003
Sultana, N., Moosa, A. M., Faisal, S. M. F., & Chowdhury, T. N. (2025). Machine learning models for optimizing online order fulfillment: Forecasting lead time and late delivery risk. Journal of Optimization and Supply Chain Management, 2(2), 70-81. https://doi.org/10.22034/ISS.2025.9373.1049
Vargha, A., & Delaney, H. D. (2000). A critique and improvement of the CL common language effect size statistics of McGraw and Wong. Journal of Educational and Behavioral Statistics, 25(2), 101-132. https://doi.org/10.3102/10769986025002101
Wolpert, D. H., & Macready, W. G. (1997). No free lunch theorems for optimization. IEEE Transactions on Evolutionary Computation, 1(1), 67-82. https://doi.org/10.1109/4235.585893
Xu, L., Long, Y., & Brintrup, A. (2025). SynDelay: A synthetic dataset for delivery delay prediction (arXiv:2509.05325) [Preprint]. arXiv. https://doi.org/10.48550/arXiv.2509.05325
Xue, B., Zhang, M., & Browne, W. N. (2013). Particle swarm optimization for feature selection in classification: A multi-objective approach. IEEE Transactions on Cybernetics, 43(6), 1656-1671. https://doi.org/10.1109/TSMCB.2012.2227469
Xue, B., Zhang, M., Browne, W. N., & Yao, X. (2016). A survey on evolutionary computation approaches to feature selection. IEEE Transactions on Evolutionary Computation, 20(4), 606-626. https://doi.org/10.1109/TEVC.2015.2504420
Zitzler, E., & Thiele, L. (1999). Multiobjective evolutionary algorithms: A comparative case study and the strength Pareto approach. IEEE Transactions on Evolutionary Computation, 3(4), 257-271. https://doi.org/10.1109/4235.797969
Erol, B. (2026). OPTIMIZATION-BASED MACHINE LEARNING FOR LATE DELIVERY CLASSIFICATION IN SUPPLY CHAINS: A COMPARISON OF METAHEURISTIC SEARCH STRATEGIES. In EROĞLU, Y. (Ed.), Optimization and Strategic Decision Models in Industrial Engineering (pp. -). Vizetek Yayıncılık. https://doi.org/10.54637/vizetek.9786253825010
| Kitap: |
| Yayınevi:
Vizetek Yayıncılık |