مقايسه ميزان اثرات علل اقتصادی و قانونی/نهادی بر مدت زمان کل و دقت مدل های پیش بینی پروژه های ساخت ایران
محورهای موضوعی : مدیریت صنعتی
فرشاد پیمان
1
,
محمد خلیل زاده
2
*
,
ناصر شهسواری پور
3
,
مهدی روانشادنیا
4
1 - دانشجوی دکتری، گروه مهندسی عمران، واحد علوم و تحقیقات، دانشگاه آزاد اسلامی، تهران، ایران.
2 - دانشیار، گروه مهندسی صنایع، واحد علوم و تحقیقات، دانشگاه آزاد اسلامی، تهران، ایران.
3 - استاد، گروه مدیریت صنعتی، دانشگاه ولی عصر (عج)، رفسنجان، ایران.
4 - دانشیار، گروه مهندسی عمران، واحد علوم و تحقیقات، دانشگاه آزاد اسلامی، تهران، ایران.
کلید واژه: برآورد مدتزمان کل و تأخیر, پروژههای ساخت ایران, علل قانونی/نهادی و اقتصادی خارجی, هوش مصنوعی.,
چکیده مقاله :
نوآوری این مقاله، مقایسه رتبه‌بندی پرارجاع‌ترین علل قانونی/نهادی و اقتصادی خارجی تأثیرگذار بر مدتزمان کل و تأخیر پروژههای ساخت با استفاده از 2 روش است: 1. بررسی تحقیقات مروری و پژوهشی بسیار معتبر یا پر ارجاع قبلی (فقط 7 اثر و شروع چاپ از 2020) و 2. تحلیل حساسیت انجام‌شده طبق نتایج تنها مدل پیش‌بینی گروهی- احتمالاتی یعنی تقویت کاهش شیب طبیعی (NGBoost-2020). گروهی بودن به دلیل دقت برآورد خیلی بیشتر نسبت به مدل‌های منفرد پر کاربرد قبلی و احتمالاتی بودن به علت مناسب بودن برای پروژههای تأخیری، پرنوسان، پرریسک و غیرقابل پیش‌بینی به ویژه در شرایط تورمی شدید اخیر ایران، ویژگی‌های بسیار مهمی در کنار هم هستند. ورودی‌های مدل تقویت کاهش شیب طبیعی شامل وجود یا عدم وجود رایج‌ترین (دارای بیشترین فراوانی) و مؤثرترین علل اقتصادی و قانونی/نهادی اثرگذار (بکار رفته به طور همزمان) در هر یک از 65 مدل ارائه‌شده در مطالعات قبلی (فقط 15 مطالعه و شروع چاپ از 2020) و خروجی واقعی آن نیز شامل درصد دقت پیش‌بینی آن مدل قبلی است. مؤثرترین عوامل بر مدتزمان و تأخیرات به هر 2 روش این مقاله به ترتیب، تغییرات مقررات دولتی، نوسانات قیمت، کندی صدور پروانهها، نوسانات نرخ ارز و تورم بدست آمدند. نتیجه دیگر، کسب دقت 83/96 درصدی مدل این مقاله برای مجموعه آزمایشی و نزدیکی بسیار زیادش به دقت 36/94 درصدی مدلی با ورودی‌های فوقالذکر برای تخمین میزان تأخیر پروژههای سدسازی ایران بود؛ که این یعنی اثر بسیار زیاد عوامل مذکور بر تأخیر پروژههای ایران و جهان و دقت برآورد مدلها.
The innovation of this paper is to compare the ranking of the most frequently cited external legal/institutional and economic causes affecting the total duration and delay of construction projects using two methods: Review previous research and review studies (only 7 works- from 2020) and Sensitivity analysis according to the results of the only ensemble-probabilistic prediction model: natural gradient boosting (NGBoost-2020). Being an ensemble due to its much higher estimation accuracy than single models and being probabilistic due to its suitability for delayed and unpredictable projects, especially in Iran's recent severe inflationary conditions, important features are together. The inputs to the NGBoost model include the presence or absence of the most frequent economic and legal/institutional causes (used simultaneously) in each of the 65 models of previous studies (only 15 studies- from 2020). its target also includes the percentage of prediction accuracy of that previous model. The most effective factors on duration (delays) by both methods of this article were found to be changes in government regulations, price fluctuations, slowness in issuing licenses, exchange fluctuations, and inflation, respectively. Another result was that the model of this paper achieved an accuracy of 96.83% for the testing set which was very close to the accuracy of 94.36% of a model with the aforementioned inputs and target of the delay value of Iran's dam construction projects. This means that the aforementioned factors have a huge impact on the delays of projects in Iran, the world, and the estimation accuracy of models.
Duan, T., Avati, A., Ding, D. Y., Thai, K. K., Basu, S., Ng, A. & Schuler, A. (2020). NGBoost: Natural gradient boosting for probabilistic prediction. Proceedings of the 37th International Conference on Machine Learning (ICML), 13-18 July, Online (Virtual): Proceedings of Machine Learning Research (PMLR), 119, 2690-2700. Retrieved 11 December, 2024, from https://proceedings.mlr.press/v119/
Durdyev, S. & Hosseini, M. R. (2020). Causes of delays on construction projects: A comprehensive list. International Journal of Managing Projects in Business, 13(1), 20-46.
Egwim, C. N. (2024). Applied artificial intelligence for delay risk prediction of BIM-based construction projects. Dissertation of Ph.D., United Kingdom, Hertfordshire, University of Hertfordshire.
Egwim, C. N., Alaka, H., Toriola-Coker, L. O., Balogun, H. & Sunmola, F. (2021). Applied artificial intelligence for predicting construction projects delay. Machine Learning with Applications, 6, 100166.
Elmousalami, H. H. (2020). Artificial intelligence and parametric construction cost estimate modeling: State-of-the-art review. Journal of Construction Engineering and Management, 146(1), 03119008.
Firouzi, F., Esmaeilian, G. & Hezavehi, M. I. (2015). Fuzzy TOPSIS model of economic risk assessment for EPC projects of oil and gas. Journal of Strategic Management in Industrial Systems, 10(32), 55-66. (in persian).
Gondia, A., Siam, A., El-Dakhakhni, W. & Nassar, A. H. (2020). Machine learning algorithms for construction projects delay risk prediction. Journal of Construction Engineering and Management, 146(1), 04019085.
Gurgun, A. P., Koc, K. & Kunkcu, H. (2024). Exploring the adoption of technology against delays in construction projects. Engineering, Construction and Architectural Management, 31(3), 1222-1253.
Gómez-Cabrera, A., Gutierrez-Bucheli, L. & Muñoz, S. (2024). Causes of time and cost overruns in construction projects: A scoping review. International Journal of Construction Management, 24(10), 1107-1125.
Isah, M. A. & Kim, B. S. (2022). Assessment of risk impact on road project using deep neural network. KSCE Journal of Civil Engineering, 26(3), 1014-1023.
Juan, Y. K. & Liou, L. E. (2022). Predicting the schedule and cost performance in public school building projects in Taiwan. Journal of Civil Engineering and Management, 28(1), 51-67.
Khalilzadeh, M., Vasei, M., Seddighizade, D. & Azizian, A. (2015). Identifying the cause-and-effect relationship and ranking the obstacles to achieving the goals of public-private partnership investment projects (Case study: The partnership model of industrial development organizations in Iran). Journal of Strategic Management in Industrial Systems, 10(33), 17-33. (in persian).
Koc, K. (2023). Role of Shapley additive explanations and resampling algorithms for contract failure prediction of public–private partnership projects. Journal of Management in Engineering, 39(5), 04023031.
Lauble, S., Steuer, D. & Haghsheno, S. (2023). A comparative evaluation of decision trees and expert intuition to predict durations in the predesign phase. The 2023 European Conference on Computing in Construction (2023 EC³) and The 40th International CIB W78 Conference, 10–12 July, Heraklion, Crete, Greece: Conseil International du Bâtiment (CIB). Retrieved 11 December, 2024, from https://ec-3.org/publications/conferences/EC32023/papers/EC32023_161.pdf
Mahyari, H. (2007). Important cases of contracting claims. Tadbir Journal, 185, 59-62. (in persian).
Mavi, N. K., Brown, K., Fulford, R. & Goh, M. (2024). Forecasting project success in the construction industry using adaptive neuro-fuzzy inference system. International Journal of Construction Management, 24(14), 1550-1568.
Moghayedi, A. & Windapo, A. (2022). Modelling the uncertainty of cost and time in highway projects. Infrastructure Asset Management, 9(2), 73-88.
Ouansrimeang, S. & Wisaeang, K. (2024). Analyzing the critical delay factors for construction projects in the public sector using relative importance index and machine learning techniques. Journal of Infrastructure, Policy and Development, 8(8), 6208.
Purushothaman, M. B., San Pedro, L. N. R. & Hoseini, A. G. (2024). Construction projects: Interactions of the causes of delays. Smart and Sustainable Built Environment, ahead-of-print(ahead-of-print), doi: 10.1108/SASBE-11-2023-0334.
Sadeghi, V., Bahrampour, A. & Hosseini, S. A. (2023). Identifying the influencing factors of customer churn of Kurdistan Telecommunications Company and presenting a model for predicting churn using machine algorithms. Journal of Strategic Management in Industrial Systems, 18(65), 16-33. (in persian).
Sanni-Anibire, M. O., Zin, R. M. & Olatunji, S. O. (2022a). Causes of delay in the global construction industry: A meta analytical review. International Journal of Construction Management, 22(8), 1395-1407.
Sanni-Anibire, M. O., Zin, R. M. & Olatunji, S. O. (2022b). Machine learning model for delay risk assessment in tall building projects. International Journal of Construction Management, 22(11), 2134-2143.
Selcuk, O., Turkoglu, H., Polat, G. & Hajdu, M. (2022). An integrative literature review on the causes of delays in construction projects: Evidence from developing countries. International Journal of Construction Management, List of Latest Articles, doi: 10.1080/15623599.2022.2135939.
Senthil, J., Muthukannan, M., Urbański, M., Stępień, M. & Kądzielawski, G. (2021). MSCA based deep recurrent neural network for statistics risk management in construction projects. Acta Montanistica Slovaca, 26(3), 481-497.
Shirazi, D. H. & Toosi, H. (2023). Deep multilayer perceptron neural network for the prediction of Iranian dam project delay risks. Journal of Construction Engineering and Management, 149(4), 04023011.
Tariq, J. & Gardezi, S. S. (2023). Study the delays and conflicts for construction projects and their mutual relationship: A review. Ain Shams Engineering Journal, 14(1), 101815.
Yang, R., Feng, J., Tang, J. & Sun, Y. (2024). Risk assessment and classification prediction for water environment treatment PPP projects. Water Science & Technology, 89(5), 1264-1281.
Yaseen, Z. M., Ali, Z. H., Salih, S. Q. & Al-Ansari, N. (2020). Prediction of risk delay in construction projects using a hybrid artificial intelligence model. Sustainability, 12(4), 1514.