Abstract
Accurately forecasting project end dates is an incredibly valuable and equally challenging task. In recent years it has gained added attention from the machine learning community. However, state of the art methods both in academia and in industry still rely on expert opinions and Monte-Carlo simulations. In this paper, we formulate the problem of activity duration forecasting as a classification task using a domain specific binning strategy. Our experiments on a data set of real construction projects suggest that our proposed method offers several orders of magnitude improvement over more traditional approaches where activity duration forecasting is treated as a regression task. Our results suggest that posing the forecasting problem as a classification task with carefully designed classes is crucial for high quality forecasts both at an activity and a project levels.
Supported by nPlan.
J. Gante—For contributions made while employed at nPlan.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
Notes
- 1.
2.977 million of 5.693 million (or \(52.3\%\)) activities in our database have completed exactly on time.
- 2.
References
Agarap, A.F.: Deep learning using rectified linear units (relu). arXiv preprint arXiv:1803.08375 (2018)
Bhandari, S., Molenaar, K.R.: Using debiasing strategies to manage cognitive biases in construction risk management: recommendations for practice and future research. Pract. Period. Struct. Design Constr. 25(4), 04020033 (2020)
Bishop, C.M.: Pattern Recognition and Machine Learning. Springer, Heidelberg (2006)
Culakova, N., et al.: How to calibrate your neural network classifier: getting true probabilities from a classification model. In: Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining (2020)
Malcolm, D.G., Roseboom, J.H., Clark, C.E., Fazar, W.: Application of a technique for research and development program evaluation. Oper. Res. 7(5), 646–669 (1959)
Dubois, D., Fargier, H., Fortemps, P.: Fuzzy scheduling: modelling flexible constraints vs. coping with incomplete knowledge. Eur. J. Oper. Res. 147(2), 231–252 (2003)
Egwim, C.N., et al.: Applied artificial intelligence for predicting construction projects delay. Mach. Learn. Appl. 6, 100166 (2021)
Fazar, W.: Program evaluation and review technique. Am. Stat. 13(2), 10 (1959)
Fiori, C., Kovaka, M.: Defining megaprojects: learning from construction at the edge of experience. In: Construction Research Congress 2005: Broadening Perspectives (2005)
Flyvbjerg, B., Bruzelius, N., Rothengatter, W.: An Anatomy of Ambition: Megaprojects and Risk. Cambridge University Press, Cambridge (2003)
Gal, Y., Ghahramani, Z.: Dropout as a bayesian approximation: representing model uncertainty in deep learning. In: International Conference on Machine Learning. PMLR (2016)
Gneiting, T., Raftery, A.E.: Strictly proper scoring rules, prediction, and estimation. J. Am. Stat. Assoc. 102(477), 359–378 (2007)
Gneiting, T., Katzfuss, M.: Probabilistic forecasting. Ann. Rev. Stat. Appl. 1, 125–151 (2014)
Guo, C., et al.: On calibration of modern neural networks. In: International Conference on Machine Learning. PMLR (2017)
Guo, X., et al.: On the class imbalance problem. In: 2008 Fourth International Conference on Natural Computation, vol. 4. IEEE (2008)
Hahn, E.D.: Mixture densities for project management activity times: a robust approach to PERT. Eur. J. Oper. Res. 188(2), 450–459 (2008)
Hong, Y., et al.: Determining construction method patterns to automate and optimise scheduling-a graph-based approach. In: European Conference on Computing in Construction (2021). https://doi.org/10.17863/CAM.Vol.68385
Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. In: International Conference on Machine Learning. PMLR (2015)
Japkowicz, N., Stephen, S.: The class imbalance problem: a systematic study. Intell. Data Anal. 6, 429–449 (2002)
Jiao, X., et al.: Tinybert: distilling bert for natural language understanding. arXiv preprint arXiv:1909.10351 (2019)
Jolliffe, I.T., Stephenson, D.B. (eds.): Forecast Verification: A Practitioner’s Guide in Atmospheric Science. John Wiley & Sons, Hoboken (2012)
Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)
Lakshminarayanan, B., Pritzel, A., Blundell, C.: Simple and scalable predictive uncertainty estimation using deep ensembles. In: Advances in Neural Information Processing Systems, vol. 30 (2017)
Mahdi, M.N., et al.: Software project management using machine learning technique-a review. Appl. Sci. 11(11), 5183 (2021)
Mahmoodzadeh, A., Mohammadi, M., Daraei, A., Farid Hama Ali, H., Ismail Abdullah, A., Kameran Al-Salihi, N.: Forecasting tunnel geology, construction time and costs using machine learning methods. Neural Comput. Appl. 33(1), 321–348 (2020). https://doi.org/10.1007/s00521-020-05006-2
Mahmoodzadeh, A., et al.: Predicting construction time and cost of tunnels using Markov chain model considering opinions of experts. Tunnel. Undergr. Space Technol. 116, 104109 (2021)
Maravas, A., Pantouvakis, J.-P.: Project cash flow analysis in the presence of uncertainty in activity duration and cost. Int. J. Proj. Manag. 30(3), 374–384 (2012)
Mosca, A., Magoulas, G.D.: Boosted residual networks. In: Boracchi, G., Iliadis, L., Jayne, C., Likas, A. (eds.) EANN 2017. CCIS, vol. 744, pp. 137–148. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-65172-9_12
Petropoulos, F., et al.: Forecasting: theory and practice. Int. J. Forecast. (2022)
Popescu, M.-C., et al.: Multilayer perceptron and neural networks. WSEAS Trans. Circ. Syst. 8(7), 579–588 (2009)
Raftery, A.E.: Use and communication of probabilistic forecasts. Stat. Anal. Data Mining ASA Data Sci. J. 9(6), 397–410 (2016)
Van Slyke, R.M.: Letter to the editor-monte carlo methods and the PERT problem. Oper. Res. 11(5), 839–860 (1963)
Sanderson, J.: Risk, uncertainty and governance in megaprojects: a critical discussion of alternative explanations. Int. J. Proj. Manag. 30(4), 432–443 (2012)
Srivastava, N., et al.: Dropout: a simple way to prevent neural networks from overfitting. J. Mach. Learn. Res. 15(1), 1929–1958 (2014)
Taleb, N.N.: The Black Swan: The Impact of the Highly Improbable, vol. 2. Random house (2)007
Wu, Z., et al.: A comprehensive survey on graph neural networks. IEEE Trans. Neural Netw. Learn. Syst. 32(1), 4–24 (2020)
Zheng, H., et al.: Improving deep neural networks using softplus units. In: 2015 International Joint Conference on Neural Networks (IJCNN). IEEE (2015)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 Springer Nature Switzerland AG
About this paper
Cite this paper
Zachares, P., Hovhannisyan, V., Ledezma, C., Gante, J., Mosca, A. (2022). On Forecasting Project Activity Durations with Neural Networks. In: Iliadis, L., Jayne, C., Tefas, A., Pimenidis, E. (eds) Engineering Applications of Neural Networks. EANN 2022. Communications in Computer and Information Science, vol 1600. Springer, Cham. https://doi.org/10.1007/978-3-031-08223-8_9
Download citation
DOI: https://doi.org/10.1007/978-3-031-08223-8_9
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-08222-1
Online ISBN: 978-3-031-08223-8
eBook Packages: Computer ScienceComputer Science (R0)