Published since 1923
DOI: 10.33622/0869-7019
Russian Science Citation Index (RSCI) на платформе Web of Science


  • INFORMATION SYSTEMS IN CONSTRUCTION
  • Big Data Technology To Improve The Reliability Of Solutions When Choosing A Contractor
  • UDC 004.62:004.85 DOI: 10.33622/0869-7019.2019.10.65-70
    Nikolay A. IVANOV, e-mail: IvanovNA@mgsu.ru
    Moscow State University of Civil Engineering (National Research University), Yaroslavskoe Shosse, 26, Moscow 129337, Russian Federation
    Marina L. VALPETERS, e-mail: mvalpeters@gmail.com
    SAS Institute, ul. Stanislavskogo, 21, str.1, Moscow 109004, Russian Federation
    Ivan A. KIREEV, e-mail: ivkireev@yandex.ru
    AO Raiffeisenbank, ul. Troitskaya, 17, str. 1, Moscow 129090, Russian Federation
    Abstract. Considering current economic situation, the level of competition among different companies is great. In order to gain a higher position in the ratings, to attract more new customers, to predict the demand for products, and finally to protect themselves from wrong decisions, companies are increasingly turning to big data analytics. In the sphere of construction an opportunity to foresee the probability of contract implementation before its conclusion is always relevant. The higher the probability, the more attractive the contractor and lower the risks of the customer. Developing the topic of applicability of machine learning methods to the problem of determining the probability of successful completion of the contract, the authors are experimenting with a set of analyzed indicators assessing the impact of each of them on the decision on the possibility of contract failure. The article considers in detail the stages of data preparation for modeling, direct modeling and analysis of the results obtained. The authors tested the adequacy of the models on actual data and set the metrics by which it is possible to customize and improve the models for the needs of a particular organization. The prognostic models with a predictive power, based on machine learning algorithms, such as logistic regression, decision tree, random forest, developed by the authors, have the potential for practical use in construction organizations at the stage of contract conclusion.
    Key words: Big Data, machine learning, risk management, contract, construction, random forest, logistic regression, Python, data analysis.
  • REFERENCES
    1. Hilbert M. Big Data for development: a review of promises and challenges. Development Police Review (DPR), 2016, no. 34(1), pp. 135-174. DOI: 10.1111/dpr.12142.
    2. Konikov A. I. Study of a number of aspects of using Big Data technology in construction. Byulleten stroitel'noj tekhniki, 2019, no. 2, pp. 28-29. (In Russian).
    3. Gnevanov M., Ivanov N. Application of technologies "Big Data" in urban planning. Promyshlennoe i grazhdanskoe stroitelstvo, 2018, no. 4, pp. 83-87. (In Russian).
    4. Konikov A., Konikov G. Big Data is a powerful tool for environmental improvements in the construction business. IOP Conf. Ser.: Earth Environ. Sci., 2017, vol. 90, pp. 012184. DOI: 10.1088/1755-1315/90/1/012184.
    5. Valpeters M., Kireev I., Ivanov N. Application of machine learning methods in big data analytics at management of contracts in the construction industry. MATEC Web of Conferences, 2018, no. 170, art. no. 01106. DOI:10.1051/matecconf/201817001106.
    6. Ivanov N. A., Valpeters M. L., Kireev I. A."Вig Data" and machine learning when managing default contract risks in construction industry. Promyshlennoe i grazhdanskoe stroitel'stvo, 2019, no. 5, pp. 81-87. DOI: 10.33622/0869-7019.2019.05.81-87. (In Russian).
    7. Vakhrina A. Y., Vogt О. А. IT for health care. Price determination. Vrach I informacionnye technologii, 2016, no. 3, pp. 6-18. (In Russian).
    8. Available at: http://zakupki.gov.ru (accessed 28.01.2019). (In Russian).
    9. Available at: /ru.wikipedia.org/wiki/Otkrytye_ dannye (accessed 28.01.2019). (In Russian).
    10. Staroverov V. V. On open data. International Journal of Open Information Technologies, 2016, vol. 4, no. 10, pp. 62-68.
    11. McKinney W. Python i analiz dannykh [Python for data analysis]. Мoscow, DМК Press Publ., 2015. 482 p. (In Russian).
    12. Available at: http://statistica.ru/theory/lognormalnoe-raspredelenie/ (accessed 28.01.2019). (In Russian).
    13. Available at: https://habr.com/ru/company/ods/blog/326418/ (accessed 03.02.2019). (In Russian).
  • For citation: Ivanov N. A., Valpeters M. L., Kireev I. A. Big Data Technology to Improve the Reliability of Solutions when Choosing a Contractor. Promyshlennoe i grazhdanskoe stroitel'stvo [Industrial and Civil Engineering], 2019, no. 10, pp. 65-70. (In Russian). DOI: 10.33622/0869-7019.2019.10.65-70.

BACK