<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE article PUBLIC "-//NLM//DTD JATS (Z39.96) Journal Publishing DTD v1.3 20210610//EN" "JATS-journalpublishing1-3.dtd">
<article article-type="research-article" dtd-version="1.3" xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xml:lang="ru"><front><journal-meta><journal-id journal-id-type="publisher-id">inform</journal-id><journal-title-group><journal-title xml:lang="ru">Информатика</journal-title><trans-title-group xml:lang="en"><trans-title>Informatics</trans-title></trans-title-group></journal-title-group><issn pub-type="ppub">1816-0301</issn><issn pub-type="epub">2617-6963</issn><publisher><publisher-name>UIIP NASB</publisher-name></publisher></journal-meta><article-meta><article-id pub-id-type="doi">10.37661/1816-0301-2024-21-1-83-104</article-id><article-id custom-type="elpub" pub-id-type="custom">inform-1271</article-id><article-categories><subj-group subj-group-type="heading"><subject>Research Article</subject></subj-group><subj-group subj-group-type="section-heading" xml:lang="ru"><subject>ИНФОРМАЦИОННЫЕ ТЕХНОЛОГИИ</subject></subj-group><subj-group subj-group-type="section-heading" xml:lang="en"><subject>INFORMATION TECHNOLOGY</subject></subj-group></article-categories><title-group><article-title>Классификация займа с использованием нейронной сети прямого распространения</article-title><trans-title-group xml:lang="en"><trans-title>Loan classification using a feed-forward neural network</trans-title></trans-title-group></title-group><contrib-group><contrib contrib-type="author" corresp="yes"><contrib-id contrib-id-type="orcid">https://orcid.org/0000-0003-1142-3992</contrib-id><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Бегунков</surname><given-names>В. И.</given-names></name><name name-style="western" xml:lang="en"><surname>Behunkou</surname><given-names>U. I.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Бегунков Владимир Иванович, магистр технических наук</p><p> </p></bio><bio xml:lang="en"><p>Uladzimir I. Behunkou, M. Sc. (Eng.)</p></bio><email xlink:type="simple">vbegunkov@gmail.com</email></contrib></contrib-group><pub-date pub-type="collection"><year>2024</year></pub-date><pub-date pub-type="epub"><day>29</day><month>03</month><year>2024</year></pub-date><volume>21</volume><issue>1</issue><fpage>83</fpage><lpage>104</lpage><permissions><copyright-statement>Copyright &amp;#x00A9; Бегунков В.И., 2024</copyright-statement><copyright-year>2024</copyright-year><copyright-holder xml:lang="ru">Бегунков В.И.</copyright-holder><copyright-holder xml:lang="en">Behunkou U.I.</copyright-holder><license xml:lang="ru" license-type="creative-commons-attribution" xlink:href="https://creativecommons.org/licenses/by/4.0/" xlink:type="simple"><license-p>Данная работа распространяется под лицензией Creative Commons Attribution 4.0.</license-p></license><license xml:lang="en" license-type="creative-commons-attribution" xlink:href="https://creativecommons.org/licenses/by/4.0/" xlink:type="simple"><license-p>This work is licensed under a Creative Commons Attribution 4.0 License.</license-p></license></permissions><self-uri xlink:href="https://inf.grid.by/jour/article/view/1271">https://inf.grid.by/jour/article/view/1271</self-uri><abstract><sec><title>Цели</title><p>Цели. Целью исследования являются построение и изучение использования нейронной сети прямого распространения для решения задачи классификации займа, а также проведение сравнительного анализа подхода на основе нейронной сети с существующим подходом, основанным на логистической регрессии.</p></sec><sec><title>Метод</title><p>Метод. На базе нейронной сети прямого распространения с использованием исторических данных по выданным займам вычисляются следующие метрики: стоимостная функция, Accuracy, Precision, Recall и мера, рассчитанная на основе значений Precision и Recall. Полиномиальные параметры и метод главных компонент применяются для определения оптимального модифицированного набора входных данных для исследуемой нейронной сети.</p></sec><sec><title>Результаты</title><p>Результаты. Проанализировано воздействие нормализации исходных данных на конечный результат, оценено влияние количества элементов скрытого уровня на конечный результат при помощи двухэтапного метода и метода Монте-Карло, определено воздействие использования сбалансированных данных, рассчитано оптимальное граничное значение для выходного уровня рассматриваемой нейронной сети, найдена оптимальная функция активации для элементов скрытого уровня, изучено влияние увеличения количества входных показателей путем заполнения отсутствующих значений и использования полиномов разной степени, а также проанализирован на избыточность имеющийся набор входных показателей.</p></sec><sec><title>Заключение</title><p>Заключение. По итогам исследования можно сделать вывод, что применение сети прямого распространения для решения задач классификации займа является целесообразным. В сравнении с логистической регрессией реализация решения с использованием нейронной сети прямого распространения требует больше времени и вычислительных ресурсов. Однако полученные наиболее важные значения Accuracy и меры выше, чем те, которые были рассчитаны с применением логистической регрессии [<xref ref-type="bibr" rid="cit1">1</xref>].</p></sec></abstract><trans-abstract xml:lang="en"><sec><title>Objectives</title><p>Objectives. The purpose of the study is to construct and study the use of a feed-forward neural network to solve the problem of loan classification, as well as to conduct a comparative analysis of the neural networkbased approach with the existing approach based on logistic regression.</p></sec><sec><title>Methods</title><p>Methods. Based on a feed-forward neural network using historical data on loans issued, the following metrics are calculated: cost function, Accuracy, Precision, Recall, and measure, calculated on Precision and Recall values. Polynomial parameters and the principal component method are used to determine the optimal set of input data for the studied neural network.</p></sec><sec><title>Results</title><p>Results. The impact of data normalization on the final result was analyzed, the influence of the number of units in the hidden layer on the outcome was evaluated using a two-stage method and the Monte Carlo method, the effect of balanced data use was determined, the optimal threshold value for output layer of the neural network under investigation was calculated, the optimal activation function for the hidden layer units was found, the effect of increasing input indicators through missing values imputation and the use of polynomials of varying degrees was studied and the redundancy in the existing set of input indicators was analyzed.</p></sec><sec><title>Conclusion</title><p>Conclusion. Based on the results of the research, we can conclude that the use of a direct distribution network to solve problems of loan classification is appropriate. Compared to logistic regression, implementing a solution using a feed-forward neural network requires more time and computing resources. However, the obtained most important values of Accuracy and measure are higher than those calculated using logistic regression [<xref ref-type="bibr" rid="cit1">1</xref>].</p></sec></trans-abstract><kwd-group xml:lang="ru"><kwd>классификация займа</kwd><kwd>скоринг</kwd><kwd>нейронная сеть прямого распространения</kwd><kwd>машинное обучение</kwd><kwd>нормализация данных</kwd></kwd-group><kwd-group xml:lang="en"><kwd>loan classification</kwd><kwd>scoring</kwd><kwd>feed-forward neural network</kwd><kwd>machine learning</kwd><kwd>data normalization</kwd></kwd-group></article-meta></front><back><ref-list><title>References</title><ref id="cit1"><label>1</label><citation-alternatives><mixed-citation xml:lang="ru">Бегунков, В. И. Классификация займов c использованием логистической регрессии / В. И. Бегунков, М. Я. Ковалев // Информатика. – 2023. − Т. 20, № 1. – С. 55–74. https://doi.org/10.37661/1816-0301-2023-20-1-55-74</mixed-citation><mixed-citation xml:lang="en">Behunkou U. I., Kovalyov M. Y. Loan classification using logistic regression. Informatika [Informatics], 2023, vol. 20, no. 1, pp. 55−74 (In Russ.). https://doi.org/10.37661/1816-0301-2023-20-1-55-74</mixed-citation></citation-alternatives></ref><ref id="cit2"><label>2</label><citation-alternatives><mixed-citation xml:lang="ru">Murati, A. Disruption in European consumer finance: Lessons from Sweden [Electronic resource] / A. Murati, O. Skau, Z. Taraporevala // McKinsey Quarterly. – 2018. – Mode of access: https://www.mckinsey.com/industries/financial-services/our-insights/disruption-in-european-consumer-finance-lessons-from-sweden. – Date of access: 01.06.2021.</mixed-citation><mixed-citation xml:lang="en">Murati A., Skau O., Taraporevala Z. Disruption in European consumer finance: Lessons from Sweden. McKinsey Quarterly, 2018. Available at: https://www.mckinsey.com/industries/financial-services/our-insights/disruption-in-european-consumer-finance-lessons-from-sweden (accessed 01.06.2021).</mixed-citation></citation-alternatives></ref><ref id="cit3"><label>3</label><citation-alternatives><mixed-citation xml:lang="ru">Hand, D. J. Statistical classification methods in consumer credit scoring: a review / D. J. Hand, W. E. Henley // J. of the Royal Statistical Society: Series A (Statistics in Society). – 1997. – Vol. 160, no. 3. – P. 523–541.</mixed-citation><mixed-citation xml:lang="en">Hand D. J., Henley W. E. Statistical classification methods in consumer credit scoring: a review. Journal of the Royal Statistical Society: Series A (Statistics in Society), 1997, vol. 160, no. 3, pp. 523–541.</mixed-citation></citation-alternatives></ref><ref id="cit4"><label>4</label><citation-alternatives><mixed-citation xml:lang="ru">Kombe, S. K. Effects of internet banking on the financial performance of commercial banks in Kenya a case of Kenya Commercial Bank / S. K. Kombe, M. K. Wafula // Intern. J. of Scientific and Research Publications. – 2015. – Vol. 5, no. 5. – P. 1–10.</mixed-citation><mixed-citation xml:lang="en">Kombe S. K., Wafula M. K. Effects of internet banking on the financial performance of commercial banks in Kenya a case of Kenya Commercial Bank. International Journal of Scientific and Research Publications, 2015, vol. 5, no. 5, pр. 1–10.</mixed-citation></citation-alternatives></ref><ref id="cit5"><label>5</label><citation-alternatives><mixed-citation xml:lang="ru">Benchmarking state-of-the-art classification algorithms for credit scoring: An update of research / S. Lessmann [et al.] // European J. of Operational Research. – 2015. – Vol. 247, iss. 1. – Р. 124–136.</mixed-citation><mixed-citation xml:lang="en">Lessmann S., Baesens B., Seow H.-V., Thomas L. C. Benchmarking state-of-the-art classification algorithms for credit scoring: An update of research. European Journal of Operational Research, 2015, vol. 247, iss. 1, рр. 124–136.</mixed-citation></citation-alternatives></ref><ref id="cit6"><label>6</label><citation-alternatives><mixed-citation xml:lang="ru">Geron, A. Hands-on Machine Learning with Scikit-Learn, Keras, and TensorFlow / A. Geron. – 2nd ed. – O’Reilly Media, 2019. – P. 205–207, 370–371.</mixed-citation><mixed-citation xml:lang="en">Geron A. Hands-on Machine Learning with Scikit-Learn, Keras, and TensorFlow, 2nd edition. O’Reilly Media, 2019, pp. 205–207, 370–371.</mixed-citation></citation-alternatives></ref><ref id="cit7"><label>7</label><citation-alternatives><mixed-citation xml:lang="ru">Oldham, K. An Atlas of Functions: with Equator, the Atlas Function Calculator / K. Oldham, J. Myland, J. Spanier. – 2nd ed. – Springer Science + Business Media, 2009. – P. 289–290.</mixed-citation><mixed-citation xml:lang="en">Oldham K., Myland J., Spanier J. An Atlas of Functions: with Equator, the Atlas Function Calculator, 2nd edition. Springer Science + Business Media, 2009, pp. 289–290.</mixed-citation></citation-alternatives></ref><ref id="cit8"><label>8</label><citation-alternatives><mixed-citation xml:lang="ru">Shalev-Shwartz, S. Understanding Machine Learning: From Theory to Algorithms / S. Shalev-Shwartz, S. Ben-David. – Cambridge University Press, 2014. – P. 125–127.</mixed-citation><mixed-citation xml:lang="en">Shalev-Shwartz S., Ben-David S. Understanding Machine Learning: From Theory to Algorithms. Cambridge University Press, 2014, pp. 125–127.</mixed-citation></citation-alternatives></ref><ref id="cit9"><label>9</label><citation-alternatives><mixed-citation xml:lang="ru">Raschka, S. Python Machine Learning / S. Raschka, V. Mirjalili. – 3d ed. – Packt Publishing Ltd., 2019. – P. 65, 415–421.</mixed-citation><mixed-citation xml:lang="en">Raschka S., Mirjalili V. Python Machine Learning, 3d edition. Packt Publishing Ltd., 2019, pp. 65, 415–421.</mixed-citation></citation-alternatives></ref><ref id="cit10"><label>10</label><citation-alternatives><mixed-citation xml:lang="ru">Rumelhart, D. Learning representations by back-propagating errors / D. Rumelhart, G. Hinton, R. Williams // Nature. – 1986. – Vol. 323. – P. 533–536.</mixed-citation><mixed-citation xml:lang="en">Rumelhart D., Hinton G., Williams R. Learning representations by back-propagating errors. Nature, 1986, vol. 323, pp. 533–536.</mixed-citation></citation-alternatives></ref><ref id="cit11"><label>11</label><citation-alternatives><mixed-citation xml:lang="ru">Goodfellow, I. Deep Learning / I. Goodfellow, Y. Bengio, A. Courville. – MIT Press, 2016. – P. 82–86, 205.</mixed-citation><mixed-citation xml:lang="en">Goodfellow I., Bengio Y., Courville A. Deep Learning, MIT Press, 2016, pp. 82–86, 205.</mixed-citation></citation-alternatives></ref><ref id="cit12"><label>12</label><citation-alternatives><mixed-citation xml:lang="ru">Bishop, C. Neural Networks for Pattern Recognition / C. Bishop. – Clarendon Press Oxford, 1995. – P. 231.</mixed-citation><mixed-citation xml:lang="en">Bishop C. Neural Networks for Pattern Recognition. Clarendon Press Oxford, 1995, p. 231.</mixed-citation></citation-alternatives></ref><ref id="cit13"><label>13</label><citation-alternatives><mixed-citation xml:lang="ru">Metropolis, N. The Monte Carlo method / N. Metropolis, S. Ulam // J. of the American Statistical Association. – 1949. – Vol. 44, no. 247. – P. 335–341.</mixed-citation><mixed-citation xml:lang="en">Metropolis N., Ulam S. The Monte Carlo method. Journal of the American Statistical Association, 1949, vol. 44, no. 247, pp. 335–341.</mixed-citation></citation-alternatives></ref><ref id="cit14"><label>14</label><citation-alternatives><mixed-citation xml:lang="ru">Harrington, P. Machine Learning in Action / P. Harrington. – 1st ed. – Manning Publication Co., 2012. – Р. 148, 269–279.</mixed-citation><mixed-citation xml:lang="en">Harrington P. Machine Learning in Action, 1st edition. Manning Publication Co., 2012, pр. 148, 269–279.</mixed-citation></citation-alternatives></ref><ref id="cit15"><label>15</label><citation-alternatives><mixed-citation xml:lang="ru">Glorot, X. Deep sparse rectifier neural networks / X. Glorot, A. Bordes, Y. Bengio // Proc. of the 14th Intern. Conf. on Artificial Intelligence and Statistics, Fort Lauderdale, FL, USA, 11–13 Apr. 2011. – Fort Lauderdale, 2011. – Vol. 15. – P. 315–323.</mixed-citation><mixed-citation xml:lang="en">Glorot X., Bordes A., Bengio Y. Deep sparse rectifier neural networks. Proceedings of the 14th International Conference on Artificial Intelligence and Statistics, Fort Lauderdale, FL, USA, 11–13 April 2011. Fort Lauderdale, 2011, vol. 15, pp. 315–323.</mixed-citation></citation-alternatives></ref><ref id="cit16"><label>16</label><citation-alternatives><mixed-citation xml:lang="ru">Murphy, K. P. Machine Learning: A Probabilistic Perspective (Adaptive Computation and Machine Learning series) / K. P. Murphy. – The MIT Press, 2012. – P. 387–407.</mixed-citation><mixed-citation xml:lang="en">Murphy K. P. Machine Learning: A Probabilistic Perspective (Adaptive Computation and Machine Learning series). The MIT Press, 2012, pp. 387–407.</mixed-citation></citation-alternatives></ref></ref-list><fn-group><fn fn-type="conflict"><p>The authors declare that there are no conflicts of interest present.</p></fn></fn-group></back></article>
