Application of machine learning technology to analyze the probability of winning a tender for a project
https://doi.org/10.15514/ISPRAS-2020-32(2)-3
Abstract
The possibility of using machine learning technology to solve the problem of project analysis in order to support the decision to participate in the tender for the implementation of the project is substantiated and shown using a specific example. The approaches are described and the process of solving the problem of binary classification of projects using libraries of the Python language is shown. Attention is paid to the problem of choosing an algorithm for constructing a membership function, the problem of generating and analyzing input data, and evaluating the accuracy of a solution. It is shown that for the considered problem the best solution is provided by the logistic regression algorithm.
About the Authors
Nikita Borisovich KULTIN
Peter the Great Saint-Petersburg Polytechnic University
Russian Federation
Candidate of technical sciences, associate professor of the department of management
Russian Federation
Candidate of technical sciences, associate professor of the department of management
Danila Nikitich KULTIN
Peter the Great Saint-Petersburg Polytechnic University
Russian Federation
PhD student at the Institute of Information Technology and Management
Russian Federation
PhD student at the Institute of Information Technology and Management
Roman Vladimirovich BAUER
Peter the Great Saint-Petersburg Polytechnic University
Russian Federation
Graduate student
Russian Federation
Graduate student
References
1. Konstantinov G.N. Strategic management: concepts. Moscow, Business-alignment, 2009, 239 p. (in Russian) / Константинов Г.Н. Стратегический менеджмент: концепции. — М.: Бизнес-элайнмент, 2009, 239 стр.
2. Principles of Machine Learning. Microsoft, 2018. Available at: https://www.edx.org/course/principles-machine-learning-microsoft-dat203-2x-6.
3. Training on tagged data. Moscow Institute of Physics and Technology, Yandex School of Data Analysis. Coursera, 2018. Available at: https://www.coursera.org/learn/supervised-learning (in Russian) / Курс “Обучение на размеченных данных”. МФТИ, Яндекс.
4. Machine Learning. Yandex School of Data Analysis, Moscow Institute of Physics and Technology, 2018. Available at: http://lectoriy.mipt.ru/course/MachineLearning-L (in Russian) / Курс “Машинное обучение”. Яндекс, МФТИ, 2018.
5. Mathematics and Python for data analysis. Moscow Institute of Physics and Technology, Yandex School of Data Analysis. Coursera. 2018. Available at: https://www.coursera.org/learn/mathematics-and-python (in Russian) / Курс “Математика и Python для анализа данных”. Яндекс, МФТИ, 2018.
6. Vorontsov K.V. Mathematical teaching methods on precedents (machine learning theory), 2018. (in Russian) Available at: http://www.machinelearning.rU/wiki/images/6/6d/Voron-ML-1.pdf / Воронцов К. Математические методы обучения по прецедентам (теория обучения машин), 2018.
7. Min-Yuan Cheng, Nhat-Duc Hoang. Interval estimation of construction cost at completion using least squares support vector machine, Journal of Civil Engineering and Management, vol. 20, no. 2, 2014, pp. 223-236.
8. Min-Yuan Cheng, Nhat-Duc Hoang. Dynamic prediction of project success using evolutionary support vector machine inference model. In Proc. from the 25th International Symposium on Automation and Robotics in Construction, 2008, pp 452-458.
9. ScikitLearn, Scikit-learn developers (BSD License), 2007 - 2017. Available at: http://scikit-learn.org/stable/modules/linear_model.html#logistic-regression.
10. Kaftannikov I.L., Parasich A.V. Problems of Training Set’s Formation in Machine Learning Tasks. Bulletin of the South Ural State University. Series Computer Technologies, Automatic Control, Radio Electronics, vol. 16, no. 3, 2016, pp. 15–24. (in Russian) / Кафтанников И.Л., А.В. Парасич. Проблемы формирования обучающей выборки в задачах машинного обучения. Вестник ЮУрГУ. Серия «Компьютерные технологии, управление, радиоэлектроника, том 16, no. 3, 2016 г., стр. 15-24.
Review
For citations:
KULTIN N.B., KULTIN D.N., BAUER R.V. Application of machine learning technology to analyze the probability of winning a tender for a project. Proceedings of the Institute for System Programming of the RAS (Proceedings of ISP RAS). 2020;32(2):29-36. https://doi.org/10.15514/ISPRAS-2020-32(2)-3
Email this article 