A Comparative Analysis of Machine Learning Models for Time Prediction in Food Delivery Operations

Abstract

Accurate time estimation is crucial for ensuring customer satisfaction and operational efficiency in the growing food delivery sector. This paper focuses on comprehensively analyzing factors affecting food delivery times and assessing the effectiveness of machine learning models in forecasting delivery times. For this purpose, authors incorporated a detailed dataset from a food delivery company of the Kaggle platform, encompassing delivery address, order time, delivery time, weather conditions, traffic intensity, and delivery person's profile information. The study evaluated the effectiveness and performance of various machine learning models such as Linear Regression, Decision Trees, Random Forests, and particularly XGBRegressor, using metrics like MAE, RMSE, and R². The results demonstrate that ensemble methods— XGBRegressor—outperformed models in accurately predicting delivery times. Additionally, a thorough analysis of feature importance uncovered the factors influencing delivery time estimation. This study offers insights into leveraging machine learning techniques to optimize food delivery operations and enhance customer satisfaction. The discoveries can assist food delivery platforms in deploying effective time estimation models and emphasizing factors for predictions

Keywords

• Machine Learning
• Time Estimation
• Feature Importance
• Food Delivery

References

1. [1] Zhao, Y., & Bacao, F. (2020). What factors determining customer continuingly using food delivery apps during 2019 novel coronavirus pandemic period? International Journal of Hospitality Management, 91, 102683. https://doi.org/10.1016/j.ijhm.2020.102683
2. [2] Zhao, B., Tan, H., Zhou, C., & Feng, H. (2023). Optimal delivery time and subsidy for IT-enabled food delivery platforms considering negative externality and social welfare. Industrial Management & Data Systems, 123(5), 1336–1358. https://doi.org/10.1108/IMDS-09-2022-0554
3. [3] Saad, A. T. (2020). Factors affecting online food delivery service in Bangladesh: an empirical study. British Food Journal, 123(2), 535–550. https://doi.org/10.1108/BFJ-05-2020-0449
4. [4] Chu, H., Zhang, W., Bai, P., & Chen, Y. (2023). Data-driven optimization for last-mile delivery. Complex Intell. Syst., 9(3), 2271–2284. https://doi.org/10.1007/s40747-021-00293-1
5. [5] Zhuang, X., Lin, L., Zhang, R., Li, J. (Justin), & He, B. (2021). E-service quality perceptions of millennials and non-millennials on O2O delivery applications. British Food Journal, 123(12), 4116–4134. https://doi.org/10.1108/BFJ-01-2021-0049
6. [6] Yaiprasert, C., & Hidayanto, A. N. (2023). AI-driven ensemble three machine learning to enhance digital marketing strategies in the food delivery business. Intelligent Systems with Applications, 18, 200235. https://doi.org/10.1016/j.iswa.2023.200235
7. [7] Liu, S., He, L., & Shen, Z.-J. M. (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
8. [8] Zhang, M.-X., Wu, J.-Y., Wu, X., & Zheng, Y.-J. (2022). Hybrid evolutionary optimization for takeaway order selection and delivery path planning utilizing habit data. Complex Intell. Syst., 8(6), 4425–4440. https://doi.org/10.1007/s40747-021-00410-0

9. [9] Madani, B., & Alshraideh, H. (2021). Predicting Consumer Purchasing Decisions in the Online Food Delivery Industry. In Advances in Machine Learning (pp. 103–117). Academy and Industry Research Collaboration Center (AIRCC). https://doi.org/10.5121/csit.2021.111510
10. [10] Maulud, D., & Abdulazeez, A. M. (2020). A Review on Linear Regression Comprehensive in Machine Learning. Journal of Applied Science and Technology Trends, 1(4), Article 4. https://doi.org/10.38094/jastt1457
11. [11] Moghe, R. P., Rathee, S., Nayak, B., & Adusumilli, K. M. (2021, January 2). Machine Learning based Batching Prediction System for Food Delivery. Proceedings of the 3rd ACM India Joint International Conference on Data Science & Management of Data (8th ACM IKDD CODS & 26th COMAD). https://doi.org/10.1145/3430984.3430999
12. [12] Hildebrandt, F. D., & Ulmer, M. W. (2022, July). Supervised Learning for Arrival Time Estimations in Restaurant Meal Delivery. Transportation Science, 56(4), 1058–1084. https://doi.org/10.1287/trsc.2021.1095
13. [13] Zhu, L., Yu, W., Zhou, K., Wang, X., Feng, W., Wang, P., Chen, N., & Lee, P. (2020, August 20). Order Fulfillment Cycle Time Estimation for On-Demand Food Delivery. Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. https://doi.org/10.1145/3394486.3403307
14. [14] Gao, C., Zhang, F., Wu, G., Hu, Q., Ru, Q., Hao, J., He, R., & Sun, Z. (2021, August 14). A Deep Learning Method for Route and Time Prediction in Food Delivery Service. Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining. https://doi.org/10.1145/3447548.3467068
15. [15] Liu, S., He, L., & Max Shen, Z. J. (2021, July). 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
16. [16] Gao, C., Zhang, F., Zhou, Y., Feng, R., Ru, Q., Bian, K., He, R., & Sun, Z. (2022, August 14). Applying Deep Learning Based Probabilistic Forecasting to Food Preparation Time for On-Demand Delivery Service. Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining. https://doi.org/10.1145/3534678.3539035
17. [17] Hughes, S., Moreno, S., Yushimito, W. F., & Huerta-Cánepa, G. (2019, December). Evaluation of machine learning methodologies to predict stop delivery times from GPS data. Transportation Research Part C: Emerging Technologies, 109, 289–304. https://doi.org/10.1016/j.trc.2019.10.018
18. [18] Food Delivery Dataset. (2022, October 1). Kaggle. https://www.kaggle.com/datasets/gauravmalik26/food-delivery-dataset/code
19. [19] Murdoch, W. J., Singh, C. D., Kumbier, K., Abbasi-Asl, R., & Yu, B. (2019). Definitions, methods, and applications in interpretable machine learning. Proceedings of the National Academy of Sciences, 116(44), 22071-22080. https://doi.org/10.1073/pnas.1900654116
20. [20] Breiman, L. (2017). Classification and Regression Trees. Routledge. https://doi.org/10.1201/9781315139470
21. [21] Breiman, L. (2001). Random Forests. Machine Learning, 45(1), 5–32. https://doi.org/10.1023/A:1010933404324
22. [22] Yang, N., Korfiatis, N., Zissis, D., & Spanaki, K. (2023). Incorporating topic membership in review rating prediction from unstructured data: a gradient boosting approach. Annals of Operations Research. https://doi.org/10.1007/s10479-023-05336-z
23. [23] Larose, D. T., & Larose, C. D. (2014). Discovering knowledge in data: an introduction to data mining. John Wiley & Sons
24. [24] Pedregosa et al., (2012). Scikit-learn: Machine Learning in Python. Journal of Machine Learning Research, 12, 2825-2830.
25. [25] Lin, W., Liu, L., Zhao, G., & Jian, Z. (2023). Developing Hybrid DMO-XGBoost and DMO-RF Models for Estimating the Elastic Modulus of Rock. Mathematics, 11(18), Article 3886. https://doi.org/10.3390/math11183886
26. [26] Wang, X., Li, W., & Li, Q. (2021). A New Embedded Estimation Model for Soil Temperature Prediction. Scientific Programming, 2021, Article 5881018. https://doi.org/10.1155/2021/5881018
27. [27] Shahani, N. M., Kamran, M., Zheng, X., & Liu, C. (2022). Predictive modeling of drilling rate index using machine learning approaches: LSTM, simple RNN, and RFA. Petroleum Science and Technology, 40(5), 534–555. https://doi.org/10.1080/10916466.2021.2003386
28. [28] İnaç, H., Ayözen, Y. E., Atalan, A., & Dönmez, C. Ç. (2022). Estimation of Postal Service Delivery Time and Energy Cost with E-Scooter by Machine Learning Algorithms. Applied Sciences, 12(23), Article 12266. https://doi.org/10.3390/app122312266
29. [29] Ceylan, Z. (2021). The impact of COVID-19 on the electricity demand: a case study for Turkey. International Journal of Energy Research, 45(9), 13022–13039. https://doi.org/10.1002/er.6631