Teslimat Verileri Kullanılarak Makine Öğrenimi ve Topluluk Öğrenme Modelleri ile Sınıflandırma Performansının Değerlendirilmesi

Year 2025, Issue: PRODUCTIVITY FOR LOGISTICS, 89 - 104, 03.02.2025

İrem Karakaya

https://doi.org/10.51551/verimlilik.1526436

Abstract

Amaç: Bu çalışma, Amazon teslimat verilerini kullanarak çeşitli makine öğrenimi ve topluluk öğrenme modellerinin teslimat sürelerini sınıflandırma performansını değerlendirmeyi amaçlamaktadır. Hızlı teslimatların rekabet avantajı sağlamadaki ve müşteri sadakatini artırmadaki rolü, bu çalışmanın önemini vurgulamaktadır.
Yöntem: Araştırmada, 15 özelliğe sahip 43.739 teslimat kaydından oluşan bir veri seti kullanılmaktadır. Veri ön işleme adımları, eksik değerlerin işlenmesi, kategorik değişkenlerin kodlanması, coğrafi mesafelerin hesaplanması ve verilerin normalleştirilmesini içermektedir. Gelişmiş makine öğrenimi teknikleri (örneğin, KNN, SVM, Lojistik Regresyon) ve topluluk yöntemleri (örneğin, ExtraTrees, AdaBoost), doğruluk, hassasiyet, geri çağırma ve F-skoru gibi metrikler temel alınarak sistematik bir şekilde karşılaştırılmıştır.
Bulgular: Topluluk öğrenme modelleri, özellikle temel model olarak SVM, NB ve LDA ile üst model olarak ET kullanıldığında en yüksek doğruluk (%99.89) ve F-skoru (%99.89) değerlerine ulaşmıştır. Bu sonuçlar, bu tür modellerin lojistik operasyonlarını optimize etme, gecikmeleri azaltma ve müşteri memnuniyetini artırma potansiyelini vurgulamaktadır.
Özgünlük: Bu çalışma, makine ve topluluk öğrenme yöntemlerinin karmaşık lojistik verilerdeki etkinliğini göstererek, lojistik verimliliğin optimize edilmesine ve müşteri memnuniyetinin artırılmasına katkı sağlamaktadır. Ayrıca, karmaşık ve geniş ölçekli lojistik veri yapıları üzerinde topluluk öğrenme yöntemlerinin uygulanmasının literatüre yaptığı katkı açısından benzersizdir. Önerilen çerçeve, gerçek zamanlı tahmin modelleme ve lojistik optimizasyonu için ölçeklenebilir bir çözüm sunmaktadır.

Keywords

Makine Öğrenimi, Topluluk Öğrenme, Lojistik Optimizasyonu, E-Ticaret Lojistiği

Evaluation of Machine Learning and Ensemble Learning Models for Classification Using Delivery Data

Abstract

Purpose: This study aims to evaluate the performance of various machine learning and ensemble learning models in classifying delivery times using Amazon delivery data. Fast deliveries' role in providing a competitive advantage and boosting customer loyalty highlights the importance of this study.
Methodology: The research employs a dataset of 43,739 delivery records with 15 features. Data preprocessing steps include handling missing values, encoding categorical variables, calculating geospatial distances, and normalizing data. Advanced machine learning techniques (e.g., KNN, SVM, Logistic Regression) and ensemble methods (e.g., ExtraTrees, AdaBoost) were systematically compared based on accuracy, precision, recall, and F-score.
Findings: Ensemble learning models, particularly those using SVM, NB, and LDA as base models and ET as the meta model, achieved the highest accuracy (99.89%) and F-score (99.89%). These results underscore the potential of such models to optimize logistics operations, reduce delays, and enhance customer satisfaction.
Originality: This study demonstrates the effectiveness of machine and ensemble learning methods on complex logistics data, contributing to optimizing logistics efficiency and enhancing customer satisfaction. Additionally, the application of ensemble learning methods on complex and large-scale logistics data structures is unique in terms of its contribution to the literature. The proposed framework offers a scalable solution for real-time predictive modeling and logistics optimization.

Keywords

Machine Learning, Ensemble Learning, Logistics Optimization, E-Commerce Logistics

References

• Ahmad, M.W., Reynolds, J. and Rezgui, Y. (2018). “Predictive Modelling for Solar Thermal Energy Systems: A Comparison of Support Vector Regression, Random Forest, Extra Trees and Regression Trees”, Journal of Cleaner Production, 203, 810-821. https://doi.org/10.1016/j.jclepro.2018.08.207
• Alnahhal, M., Ahrens, D. and Salah, B. (2021). “Dynamic Lead-Time Forecasting Using Machine Learning in a Make-to-Order Supply Chain”, Applied Sciences, 11(21), 10105. https://doi.org/10.3390/app112110105
• Bruni, M.E., Fadda, E., Fedorov, S. and Perboli, G. (2023). “A Machine Learning Optimization Approach for Last-Mile Delivery and Third-Party Logistics”, Computers & Operations Research, 157, 106262. https://doi.org/10.1016/j.cor.2023.106262
• Chu, H., Zhang, W., Bai, P. and Chen, Y. (2023). “Data-Driven Optimization for Last-Mile Delivery”, Complex and Intelligent Systems, 9(3), 2271-2284. https://doi.org/10.1007/s40747-021-00293-1
• Deshmukh, Y., Patil, J., Pawar, P., Pardeshi, P. and Patil, H. (2024). “E-Commerce Product Delivery Analysis”, IRE Journals, 7(12), 177-181.
• Dyreson, C.E. and Snodgrass, R.T. (1993). “Timestamp Semantics and Representation”, Information Systems 18(3), 143-166. https://doi.org/10.1016/0306-4379(93)90034-X
• Erkmen, O.E., Nigiz, E., Z. Sarı, Z.D., Arlı, H.Ş. and Akay, M.F. (2022). “Delivery Time Prediction Using Support Vector Machine Combined with Look-Back Approach”, International Joint Conference on Engineering, Science and Artificial Intelligence‐IJCESAI 2022, 33-38.
• Eskandaripour, H. and Boldsaikhan, E. (2023). “Last-Mile Drone Delivery: Past, Present, and Future”, Drones, 7(2), 77. https://doi.org/10.3390/drones7020077
• Gallant, S.I. (1990). “Perceptron-Based Learning Algorithms”, IEEE Transactions on Neural Networks, 1(2), 179-191.
• Ghojogh, B., and Crowley, M. (2019). “Linear and Quadratic Discriminant Analysis: Tutorial”, arXiv:1906.02590. https://doi.org/10.48550/arXiv.1906.02590
• Gore, S., Mishra, P.K. and Gore, S. (2023). “Improvisation of Food Delivery Business by Leveraging Ensemble Learning with Various Algorithms”, International Conference on Self Sustainable Artificial Intelligence Systems, ICSSAS 2023, 221-229. https://doi.org/10.1109/ICSSAS57918.2023.10331669
• Guo, G., Wang, H., Bell, D., Bi, Y. and Greer, K. (2003). “KNN Model-Based Approach in Classification”, On The Move to Meaningful Internet Systems 2003: CoopIS, DOA, and ODBASE. OTM 2003. Lecture Notes in Computer Science, (Editors: R. Meersman, Z. Tari, D.C. Schmidt), 2888, Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3- 540-39964-3_62
• He, J., Ding, L., Jiang, L., and Ma, L. (2014). “Kernel Ridge Regression Classification”, Proceedings of the International Joint Conference on Neural Networks, 2263-2267. https://doi.org/10.1109/IJCNN.2014.6889396
• Jelodar, H., Wang, Y., Yuan, C., Feng, X., Jiang, X., Li, Y. and Zhao, L. (2019). “Latent Dirichlet Allocation (LDA) and Topic Modeling: Models, Applications, a Survey”, Multimedia Tools and Applications, 78(11), 15169-15211. https://doi.org/10.1007/s11042-018-6894-4
• Karakaya, A., Ulu, A. and Akleylek, S. (2022a). “GOALALERT: A Novel Real-Time Technical Team Alert Approach Using Machine Learning on an IoT-Based System in Sports”, Microprocessors and Microsystems, 93, 104606. https://doi.org/10.1016/j.micpro.2022.104606
• Kazan, S. and Karakoca, H. (2019). “Makine Öğrenmesi İle Ürün Kategorisi Sınıflandırma”, Sakarya University Journal of Computer and Information Sciences, 2(1), 18-27. https://doi.org/10.35377/saucis.02.01.523139
• Khiari, J., and Olaverri-Monreal, C. (2020). “Boosting Algorithms for Delivery Time Prediction in Transportation Logistics”, IEEE International Conference on Data Mining Workshops, ICDMW 2020, 251-258. https://doi.org/10.1109/ICDMW51313.2020.00043
• Lochbrunner, M., and Witschel, H.F. (2022). “Combining Machine Learning with Human Knowledge for Delivery Time Estimations”, CEUR Workshop Proceedings, 3121.
• Patro, S. and Sahu, K.K. (2015). “Normalization: A Preprocessing Stage.” ArXiv Preprint ArXiv:1503.06462. Polikar, R. (2012). “Ensemble Learning”, Ensemble Machine Learning: Methods and Applications, (Editors: C. Zhang and Y. Ma), 1-34, Springer, New York.
• Reddy, B.H., and Karthikeyan, P. R. (2022). “Classification of Fire and Smoke Images Using Decision Tree Algorithm in Comparison with Logistic Regression to Measure Accuracy, Precision, Recall, F-Score.” 14th International Conference on Mathematics, Actuarial Science, Computer Science and Statistics (MACS). 1-5, IEEE.
• Rokoss, A., Syberg, M., Tomidei, L., Hülsing, C., Deuse, J. and Schmidt, M. (2024). “Case Study on Delivery Time Determination Using a Machine Learning Approach in Small Batch Production Companies”, Journal of Intelligent Manufacturing, 35, 3937-3958. https://doi.org/10.1007/s10845-023-02290-2
• Sagi, O., and Rokach, L. (2018). “Ensemble Learning: A Survey”, WIRES Data Mining and Knowledge Discovery, 8(4), 1-18. https://doi.org/10.1002/widm.1249
• Salari, N., Liu, S. and Max Shen, Z-J. (2022). “Real-Time Delivery Time Forecasting and Promising in Online Retailing: When Will Your Package Arrive?”, Manufacturing and Service Operations Management, 24(3), 1421-1436. https://doi.org/10.1287/msom.2022.1081
• Sharma, A., and Paliwal, K.K. (2010). “Improved Nearest Centroid Classifier with Shrunken Distance Measure for Null LDA Method on Cancer Classification Problem”, Electronics Letters, 46(18), 1251-1252. https://doi.org/10.1049/el.2010.1927
• Sheng L., He, L., and Max Shen, Z-J. (2021). “On-Time Last-Mile Delivery: Order Assignment with Travel-Time Predictors”, Management Science, 67(7), 4095-4119. https://doi.org/10.1287/mnsc.2020.3741
• Tsang, Y.P., Wu, C-H., Lam, H.Y., Choy, K.L. and Ho, G.T.S. (2021). “Integrating Internet of Things and Multi- Temperature Delivery Planning for Perishable Food E-Commerce Logistics: A Model and Application”, International Journal of Production Research, 59(5), 1534-1556.
• Tsolaki, K., Vafeiadis, T., Nizamis, A., Ioannidis, D. and Tzovaras, D. (2023). “Utilizing Machine Learning on Freight Transportation and Logistics Applications: A Review”, ICT Express, 9(3), 284-295.
• Željko, V. (2021). “Classification Model Evaluation Metrics”, International Journal of Advanced Computer Science and Applications, 12(6), 599-606. https://doi.org/10.14569/IJACSA.2021.0120670
• Wang, H. and Hu, D. (2005). “Comparison of SVM and LS-SVM for Regression”, 2005 International Conference on Neural Networks and Brain, 279-283. https://doi.org/10.1109/ICNNB.2005.1614615
• Winarno, E., Hadikurniawati, W. And Rosso, R.N. (2017). “Location Based Service for Presence System Using Haversine Method”, 2017 International Conference on Innovative and Creative Information Technology (ICITech), Salatiga, Indonesia, 1-4. https://doi.org/10.1109/INNOCIT.2017.8319153
• Yüce T. and Kabak M. (2021). “Makine Öğrenmesi Algoritmaları Ile Detay Üretim Alanları İçin İş Merkezi Kırılımında Üretim Süresi Tahminleme”, Erciyes Üniversitesi Fen Bilimleri Enstitüsü Fen Bilimleri Dergisi,37(1), 47-60.
• Zaghloul, M., Barakat, S. and Rezk, A. (2024). “Predicting E-Commerce Customer Satisfaction: Traditional Machine Learning vs. Deep Learning Approaches”, Journal of Retailing and Consumer Services, 79, 103865. https://doi.org/10.1016/j.jretconser.2024.103865