Applying Hybrid Machine Learning for Construction Material Price Prediction and Procurement Cost Optimization

Abstract

Construction material cost is the major component of construction project costs. Among the material cost categories, construction material price fluctuation is the major risk that causes construction cost estimation to be different from actual cost in many countries. In addition, unable to consider the construction material price in construction material procurement cost optimization is uneconomical because may lead to the material being ordered at a period when the price is high. Therefore, a two-staged method for construction material price prediction and a strategic economical construction procurement method is proposed. In the first stage, the Multilayer Perceptron (MLP) is used to predict construction material prices. Then in the second stage, the predicted price of the MLP model was taken as input along with procurement data for the Deep Q Network (DQN) to identify ordering time and quantity at a minimum cost. The application of the proposed method in the Ethiopian construction industry shows that MLP has better performance in predicting cement prices than linear regression. Besides, the DQN algorithm procurement strategy for the nonpolynomial hard problem is < 1% in cost performance than the exact mixed integer linear programming (MILP) method with reasonable solution time. The proposed hybrid model can help construction practitioners to make material-related data-driven decisions.

Keywords

• Construction Material
• DQN
• Machine Learning
• MLP
• Price Prediction
• Procurement Cost Optimization

References

1. Bakhshi, P., & Touran, A. (2014). An overview of budget contingency calculation methods in construction industry. Procedia Engineering, 85, 52–60. https://doi.org/10.1016/j.proeng.2014.10.528.
2. Adaurhere, R. E., Musonda, I., & Okoro, C. S. (2019). Construction contingency determination: A review of processes and techniques. Construction in the 21st Century Conference, April 2022, 11. https://doi.org/10.1007/978-3-030-48465-1
3. Georgy.M and Basily.S. Y. (2008). Using genetic algorithms in optimizing construction material delivery schedules. Constr. Innov., vol. 8, no. 1, pp. 23–45, 2.doi: 10.1108/14714170810846503.
4. Kumar, D. R. (2016). Economic Order Quantity (EOQ). Global Journal of Finance and Economic Management, 5(1), 1–5. https://doi.org/10.4135/9781412950602.n225
5. Fentahun, K. Y. (2020). Determinants of Infrastructure Project Delays and Cost Escalations: The Cases of Federal Road and Railway Construction Projects in Ethiopia. Technology, and Sciences (ASRJETS) American Scientific Research Journal for Engineering, 63(1), 102–136. http://asrjetsjournal.org/
6. Bahamid, R. A., Doh, S. I., & Al-Sharaf, M. A. (2019). Risk factors affecting the construction projects in the developing countries. IOP Conference Series: Earth and Environmental Science, 244(1), 1–4. https://doi.org/10.1088/1755-1315/244/1/012040
7. Amoatey, C. T., Ameyaw, Y. A., Adaku, E., & Famiyeh, S. (2015). Analysing delay causes and effects in Ghanaian state housing construction projects. International Journal of Managing Projects in Business, 8(1), 198–214. www.emeraldinsight.com/1753-8378.htm%0AIJMPB
8. Tang, B. qiu, Han, J., Guo, G. feng, Chen, Y., & Zhang, S. (2019). Building material prices forecasting based on least square support vector machine and improved particle swarm optimization. Architectural Engineering and Design Management, 15(3), 196–212. https://doi.org/10.1080/17452007.2018.155657

9. Patil, A. R., & Pataskar, S. V. (2013). Analyzing Material Management Techniques on Construction Project. International Journal of Engineering and Innovative Technology, 3(4), 96–100.
10. Navon, R., & Berkovich, O. (2006). An automated model for materials management and control. CONSTRUCTION ENGINEERING AND MANAGEMENT, 131(12), 1328–1336. https://doi.org/10.1080/01446190500435671
11. Khondoker, T. H., Hossain, M., & Saha, A. (2024). 4D BIM integrated optimization of construction steel bar procurement plan for limited storage capacity. Construction Innovation, 1471–4175. https://doi.org/10.1108/CI-12-2022-0310
12. Urbanucci, L. (2018). Limits and potentials of Mixed Integer Linear Programming methods for optimization of polygeneration energy systems. Energy Procedia, 148, 1199–1205. https://doi.org/10.1016/j.egypro.2018.08.021
13. Du, J., Li, X., Aran, V. yan S., Hu, Y., & Xue, Y. (2023). Dynamic model averaging-based procurement optimization of prefabricated components Genetic algorithm. Neural Computing and Applications, 6, 1–17. https://doi.org/10.1007/s00521-023-08715-6
14. Kulkarni, A., & Halder, S. (2020). A simulation- based decision-making framework for construction supply chain management (SCM). Asian Journal of Civil Engineering, 21(2), 229–241. https://doi.org/10.1007/s42107-019-00188-0
15. Son, P. V. H., Duy, N. H. C., & Dat, P. T. (2021). Optimization of Construction Material Cost through Logistics Planning Model of Dragonfly Algorithm — Particle Swarm Optimization. KSCE Journal of Civil Engineering, 25(7), 2350–2359. https://doi.org/10.1007/s12205-021-1427-5
16. Becerra, P., Mula, J., & Sanchis, R. (2021). Green supply chain quantitative models for sustainable inventory management: A review. Journal of Cleaner Production, 328, 129544. https://doi.org/10.1016/j.jclepro.2021.129544
17. Akinosho, T. D., Oyedele, L. O., Bilal, M., Ajayi, A. O., Delgado, M. D., Akinade, O. O., & Ahmed, A. A. (2020). Deep learning in the construction industry: A review of present status and future innovations. Journal of Building Engineering, 32, 1–7. https://doi.org/10.1016/j.jobe.2020.101827
18. Akintoye, S. A., & Skitmore, R. M. (1994). A comparative analysis of three macro price forecasting models. Construction Management and Economics, 12(3), 257–270. https://doi.org/10.1080/01446199400000033
19. Hwang, S., Park, M., Lee, H.-S., & Kim, H. (2012). Automated Time-Series Cost Forecasting System for Construction Materials. Journal of Construction Engineering and Management, 138(11), 1259–1269. https://doi.org/10.1061/(asce)co.1943-7862.0000536
20. Shiha, A., Dorra, E. M., & Nassar, K. (2020). Neural Networks Model for Prediction of Construction Material Prices in Egypt Using Macroeconomic Indicators. Journal of Construction Engineering and Management, 146(3), 04020010. https://doi.org/10.1061/(asce)co.1943-7862.0001785
21. Bediako, M., Amankwah, E. O., & Adobor, D. (2015). The impact of macroeconomic indicators on Cement Prices in Ghana. Journal of Scientific Research & Reports, 9(7), 1–6. https://doi.org/10.1108/15265940910980632
22. Ernest, K., Theophilus, A. K., Amoah, P., & Emmanuel, B. B. (2017). Identifying key economic indicators influencing tender price index prediction in the building industry: a case study of Ghana. International Journal of Construction Management, 19(2), 1–7. https://doi.org/10.1080/15623599.2017.138964
23. Afolabi, A. O., & Abimbola, O. (2022). Application of machine learning in cement price prediction through a web-based system. 12(5), 5214–5225. https://doi.org/10.11591/ijece.v12i5.pp5214-5225
24. Dilip, D. K., & Jesna, N. M. (2022). Macroeconomic indicators as potential predictors of construction material prices. Sustainability, Agri, Food and Environmental Research, 10(X), 1–9.
25. Onawumi, A., Oluleye, O., & Adebiyi, K. (2011). An economic order quantity model with shortage price break and inflation. INt. J, Emerg, Sci, 3(2222–4254), 465–477. https://doi.org/10.1063/1.4930642
26. Mahadevan, B. (2015). Operation Management Theory and Practice (3rd ed.). PEARSON.
27. Zhang, X., Xiong, R., & Tao, S. (2019). Research on Model Algorithms of Supply Chain of Material Scheduling with Elastic Variables in Construction Site for Giant Projects. Advances in Intelligent Systems and Computing, 929(2019), 805–812. https://doi.org/10.1007/978-3-030-15740-1_106
28. Ashuri, B., Shahandashti, S. M., & Lu, J. (2012). Empirical tests for identifying leading indicators of ENR Construction Cost Index. Construction Management and Economics, 30(11), 917–927. https://doi.org/10.1080/01446193.2012.72870
29. Musarat, M. A., Alaloul, W. S., & Liew, M. S. (2021). Impact of inflation rate on construction projects budget: A review. Ain Shams Engineering Journal, 12(1), 407–414. https://doi.org/10.1016/j.asej.2020.04.009
30. Granger, C. W. J. (1969). Investigating Causal Relations by Econometric Models and Cross-spectral Methods. Econometrica, 37(3), 424–438. https://doi.org/10.2307/1912791
31. Parmezan, A. R. S., Souza, V. M. A., & Batista, G. E. A. P. A. (2019). Evaluation of statistical and machine learning models for time series prediction: Identifying the state-of-the-art and the best conditions for the use of each model. Information Sciences, 484, 302–337. https://doi.org/10.1016/j.ins.2019.01.076
32. Haykin, S. (2005). Neural Networks - A Comprehensive Foundation - Simon Haykin.pdf (Second). PEARSON.
33. Bhanja, S., & Das, A. (2018). Impact of Data Normalization on Deep Neural Network for Time Series Forecasting. 5–10. http://arxiv.org/abs/1812.05519
34. Yu, T., & Zhu, H. (2020). Hyper-Parameter Optimization : A Review of Algorithms (pp. 1–56).
35. Smith, L. N. (2016). A disciplined approach to neural network hyper-parameters: part 1 – learning rate, batch size, momentum, and weight decay. US Naval Research Laboratory Technical Report, 5510(026), 1–21.
36. Jason, B. (2018). Deep learning for time series forecasting: Predict the Future with MLPs, CNNs and LSTMs in Python. In Ml (v1.4, Vol. 1, Issue 1). Machine Learning Mastery.
37. Brownlee, J. (2018). What is the Difference Between a Batch and an Epoch in a Neural Network ?
38. Sharma, S., & Sharma, S. (2020). Activation functions in neural networks. 4(12), 310–316.
39. Uzair, M., & Jamil, N. (2020). Effects of Hidden Layers on the Efficiency of Neural networks. Proceedings - 2020 23rd IEEE International Multi-Topic Conference, INMIC 2020, 1–6. https://doi.org/10.1109/INMIC50486.2020.9318195
40. Shaft, I., Ahmad, J., Shah, S. I., & Kashif, F. M. (2006). Impact of varying neurons and hidden layers in neural network architecture for a time frequency application. 10th IEEE International Multitopic Conference 2006, INMIC, 188–193. https://doi.org/10.1109/INMIC.2006.358160
41. Steurer, M., Hill, R. J., & Pfeifer, N. (2021). Metrics for evaluating the performance of machine learning based automated valuation models. Journal of Property Research, 38(2), 99–129. https://doi.org/10.1080/09599916.2020.1858937
42. Giannoccaro, I., & Pontrandolfo, P. (2002). Inventory management in supply chains: A reinforcement learning approach. International Journal of Production Economics, 78(2), 153–161. https://doi.org/10.1016/S0925-5273(00)00156-0
43. Sutton, R. S., & Barto, A. G. (2018). Reinforcement Learning: An Introduction (2nd ed.). MIT press. http://incompleteideas.net/book/
44. Winder, P. (2020). Reinforcement Learning Industrial Applications of Intelligent Agents (First). O’Reilly Media.
45. Mnih, V., Kavukcuoglu, K., Silver, D., Rusu, A. A., Veness, J., Bellemare, M. G., Graves, A., Riedmiller, M., Fidjeland, A. K., Ostrovski, G., Petersen, S., Beattie, C., Sadik, A., Antonoglou, I., King, H., Kumaran, D., Wierstra, D., Legg, S., & Hassabis, D. (2015). Human-level control through deep reinforcement learning. Nature, 518(7540), 529–533. https://doi.org/10.1038/nature14236
46. Li, Y. (2017). Deep reinforcement learning: An overview. (pp. 1–85). arXiv preprint arXiv:1701.07274.
47. Santos, H. G., & Toffolo, T. A. M. (2020). Mixed Integer Linear Programming with Python. COINOR Computational Infrastructure for Operations Research.