<?xml version="1.0" encoding="UTF-8"?>
<article article-type="research-article" dtd-version="1.3" xml:lang="ru" xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:noNamespaceSchemaLocation="https://metafora.rcsi.science/xsd_files/journal3.xsd">
  <front>
    <journal-meta>
      <journal-id journal-id-type="publisher-id">moitvivt</journal-id>
      <journal-title-group>
        <journal-title xml:lang="ru">Моделирование, оптимизация и информационные технологии</journal-title>
        <trans-title-group xml:lang="en">
          <trans-title>Modeling, Optimization and Information Technology</trans-title>
        </trans-title-group>
      </journal-title-group>
      <issn pub-type="epub">2310-6018</issn>
      <publisher>
        <publisher-name>Издательство</publisher-name>
      </publisher>
    </journal-meta>
    <article-meta>
      <article-id pub-id-type="doi">10.26102/2310-6018/2025.49.2.021</article-id>
      <article-id pub-id-type="custom" custom-type="elpub">1819</article-id>
      <title-group>
        <article-title xml:lang="ru">Оценка потенциала нейросетевой модели дискретного выбора с сиамским обучением для задачи прогнозирования покупки недвижимости</article-title>
        <trans-title-group xml:lang="en">
          <trans-title>Evaluating the potential of neural discrete choice model with siamese networks for a real estate sales forecasting problem</trans-title>
        </trans-title-group>
      </title-group>
      <contrib-group>
        <contrib contrib-type="author">
          <contrib-id contrib-id-type="orcid">0009-0009-7857-3101</contrib-id>
          <name-alternatives>
            <name name-style="eastern" xml:lang="ru">
              <surname>Разумовский</surname>
              <given-names>Лев Григорьевич</given-names>
            </name>
            <name name-style="western" xml:lang="en">
              <surname>Razumovskiy</surname>
              <given-names>Lev Grigorievich</given-names>
            </name>
          </name-alternatives>
          <email>lev.razumovskiy@ramax.com</email>
          <xref ref-type="aff">aff-1</xref>
        </contrib>
        <contrib contrib-type="author">
          <contrib-id contrib-id-type="orcid">0009-0000-1317-2512</contrib-id>
          <name-alternatives>
            <name name-style="eastern" xml:lang="ru">
              <surname>Каренин</surname>
              <given-names>Николай Евгеньевич</given-names>
            </name>
            <name name-style="western" xml:lang="en">
              <surname>Karenin</surname>
              <given-names>Nikolay Evgen'evich</given-names>
            </name>
          </name-alternatives>
          <email>nikolay.karenin@ramax.com</email>
          <xref ref-type="aff">aff-2</xref>
        </contrib>
        <contrib contrib-type="author">
          <contrib-id contrib-id-type="orcid">0009-0007-8758-1555</contrib-id>
          <name-alternatives>
            <name name-style="eastern" xml:lang="ru">
              <surname>Герасимова</surname>
              <given-names>Мария Алексеевна</given-names>
            </name>
            <name name-style="western" xml:lang="en">
              <surname>Gerasimova</surname>
              <given-names>Mariya Alekseevna</given-names>
            </name>
          </name-alternatives>
          <email>mariya.gerasimova@ramax.com</email>
          <xref ref-type="aff">aff-3</xref>
        </contrib>
      </contrib-group>
      <aff-alternatives id="aff-1">
        <aff xml:lang="ru">Группа компаний "Ramax"</aff>
        <aff xml:lang="en">Ramax Group</aff>
      </aff-alternatives>
      <aff-alternatives id="aff-2">
        <aff xml:lang="ru">Группа компаний "Ramax"</aff>
        <aff xml:lang="en">Ramax Group</aff>
      </aff-alternatives>
      <aff-alternatives id="aff-3">
        <aff xml:lang="ru">Группа компаний "Ramax"</aff>
        <aff xml:lang="en">Ramax Group</aff>
      </aff-alternatives>
      <pub-date pub-type="epub">
        <day>01</day>
        <month>01</month>
        <year>2026</year>
      </pub-date>
      <volume>1</volume>
      <issue>1</issue>
      <elocation-id>10.26102/2310-6018/2025.49.2.021</elocation-id>
      <permissions>
        <copyright-statement>Copyright © Авторы, 2026</copyright-statement>
        <copyright-year>2026</copyright-year>
        <license license-type="creative-commons-attribution" xlink:href="https://creativecommons.org/licenses/by/4.0/">
          <license-p>This work is licensed under a Creative Commons Attribution 4.0 International License</license-p>
        </license>
      </permissions>
      <self-uri xlink:href="https://moitvivt.ru/ru/journal/article?id=1819"/>
      <abstract xml:lang="ru">
        <p>В работе рассматривается задача воспроизведения процесса покупок объектов недвижимости, решение которой позволит проверять как существующие, так и будущие алгоритмы динамического ценообразования, строить предсказания предпочтений покупателей и формировать кривую спроса. В качестве решения предлагается использовать подход, основанный на использовании моделей дискретного выбора, которые широко представлены в экономической литературе и имеют обширный круг приложений в области изучения потребительского поведения и предпочтений на конкурентных рынках. В данной работе излагается новая модель дискретного выбора, использующая нейронную сеть для формирования полезности объекта недвижимости. Предлагается подход к обучению модели через сиамские нейронные сети. Также в статье предложена нестандартная архитектура основной нейросети, позволяющая избежать потери сходимости при ее обучении. В работе проводится симуляция процесса покупки объектов недвижимости с помощью классических моделей, основанных на логистической регрессии со случайными коэффициентами, и с помощью нейросетевой модели, а также проведено их сравнение. В результате численных экспериментов показано заметное преимущество предложенного нейросетевого подхода. С помощью пермутационного теста доказана статистическая значимость полученных результатов.</p>
      </abstract>
      <trans-abstract xml:lang="en">
        <p>The paper considers the problem of reproducing the process of purchasing real estate, the solution of which will allow testing both existing and future dynamic pricing algorithms, building predictions of buyers' preferences and forming a demand curve. As a solution, it is proposed to use an approach based on the use of discrete choice models, which are widely represented in the economic literature and have a wide range of applications in the field of studying consumer behavior and preferences in competitive markets. This paper presents a new discrete choice model that uses a neural network to form the utility of a real estate object. An approach to training the model through Siamese neural networks is proposed. The article also proposes a non-standard architecture of the main neural network, which allows avoiding the loss of convergence during its training. The paper simulates the process of purchasing real estate using classical models based on logistic regression with random coefficients and using a neural network model, and compares them. As a result of numerical experiments, a noticeable advantage of the proposed neural network approach is shown. Using a permutation test, the statistical significance of the obtained results is proved.</p>
      </trans-abstract>
      <kwd-group xml:lang="ru">
        <kwd>модель дискретного выбора</kwd>
        <kwd>сиамские нейросети</kwd>
        <kwd>процесс продаж</kwd>
        <kwd>недвижимость</kwd>
        <kwd>предпочтения покупателей</kwd>
        <kwd>эконометрическое моделирование</kwd>
      </kwd-group>
      <kwd-group xml:lang="en">
        <kwd>discrete choice model</kwd>
        <kwd>siamese neural networks</kwd>
        <kwd>sales process</kwd>
        <kwd>real estate</kwd>
        <kwd>customer preference</kwd>
        <kwd>econometric modeling</kwd>
      </kwd-group>
      <funding-group>
        <funding-statement xml:lang="ru">Исследование выполнено без спонсорской поддержки.</funding-statement>
        <funding-statement xml:lang="en">The study was performed without external funding.</funding-statement>
      </funding-group>
    </article-meta>
  </front>
  <back>
    <ref-list>
      <title>References</title>
      <ref id="cit1">
        <label>1</label>
        <mixed-citation xml:lang="ru">McFadden D. Economic Choices. American Economic Review. 2001;91(3):351–378. https://doi.org/10.1257/aer.91.3.351</mixed-citation>
      </ref>
      <ref id="cit2">
        <label>2</label>
        <mixed-citation xml:lang="ru">Sifringer B., Lurkin V., Alahi A. Enhancing Discrete Choice Models with Neural Networks. In: 18th Swiss Transport Research Conference (STRC 2018), 16–18 May 2018, Monte Verità, Switzerland. 2018. pp. 1–13.</mixed-citation>
      </ref>
      <ref id="cit3">
        <label>3</label>
        <mixed-citation xml:lang="ru">Jeng J.-M., Fesenmaier D.R. A Neural Network Approach to Discrete Choice Modeling. Journal of Travel &amp; Tourism Marketing. 1996;5(1-2):119–144. https://doi.org/10.1300/J073v05n01_08</mixed-citation>
      </ref>
      <ref id="cit4">
        <label>4</label>
        <mixed-citation xml:lang="ru">Haj-Yahia Sh., Mansour O., Toledo T. Incorporating Domain Knowledge in Deep Neural Networks for Discrete Choice Models. arXiv. URL: https://arxiv.org/abs/2306.00016 [Accessed 20th December 2024].</mixed-citation>
      </ref>
      <ref id="cit5">
        <label>5</label>
        <mixed-citation xml:lang="ru">Aouad A., Désir A. Representing Random Utility Choice Models with Neural Networks.  arXiv. URL: https://arxiv.org/abs/2207.12877 [Accessed 20th December 2024].</mixed-citation>
      </ref>
      <ref id="cit6">
        <label>6</label>
        <mixed-citation xml:lang="ru">Yang Ya., Zhai P. Click-Through Rate Prediction in Online Advertising: A Literature Review. Information Processing &amp; Management. 2022;59(2). https://doi.org/10.2139/ssrn.4036054</mixed-citation>
      </ref>
      <ref id="cit7">
        <label>7</label>
        <mixed-citation xml:lang="ru">Guo Ya., Wang M., Li X. An Interactive Personalized Recommendation System Using the Hybrid Algorithm Model. Symmetry. 2017;9(10). https://doi.org/10.3390/sym9100216</mixed-citation>
      </ref>
      <ref id="cit8">
        <label>8</label>
        <mixed-citation xml:lang="ru">Craparotta G., Thomassey S., Biolatti A. A Siamese Neural Network Application for Sales Forecasting of New Fashion Products Using Heterogeneous Data. International Journal of Computational Intelligence Systems. 2019;12:1537–1546. https://doi.org/10.2991/ijcis.d.191122.002</mixed-citation>
      </ref>
      <ref id="cit9">
        <label>9</label>
        <mixed-citation xml:lang="ru">Van Cranenburgh S., Garrido-Valenzuela F. Computer vision-enriched discrete choice models, with an application to residential location choice. arXiv. URL: https://arxiv.org/abs/2308.08276 [Accessed 20th December 2024].</mixed-citation>
      </ref>
      <ref id="cit10">
        <label>10</label>
        <mixed-citation xml:lang="ru">Ruan G., Kirschen D.S., Zhong H., Xia Q., Kang C. Estimating Demand Flexibility Using Siamese LSTM Neural Networks. IEEE Transactions on Power Systems. 2021;37(3):2360–2370. https://doi.org/10.48550/arXiv.2109.01258</mixed-citation>
      </ref>
      <ref id="cit11">
        <label>11</label>
        <mixed-citation xml:lang="ru">Train K.E. Discrete Choice Methods with Simulation. Cambridge; New York: Cambridge University Press; 2009. 388 p. https://doi.org/10.1017/CBO9780511805271</mixed-citation>
      </ref>
      <ref id="cit12">
        <label>12</label>
        <mixed-citation xml:lang="ru">Hornik K. Approximation capabilities of multilayer feedforward networks. Neural Networks.1991;4(2):251–257. https://doi.org/10.1016/0893-6080(91)90009-T</mixed-citation>
      </ref>
      <ref id="cit13">
        <label>13</label>
        <mixed-citation xml:lang="ru">Dong G., Kweon Y., Park B.B., Boukhechba M. Utility-Based Route Choice Behavior Modeling Using Deep Sequential Models. Journal of Big Data Analytics in Transportation. 2022;4(2-3):119–133. https://doi.org/10.1007/s42421-022-00058-3</mixed-citation>
      </ref>
      <ref id="cit14">
        <label>14</label>
        <mixed-citation xml:lang="ru">Wang F., Ross C.L. Machine Learning Travel Mode Choices: Comparing the Performance of an Extreme Gradient Boosting Model with a Multinomial Logit Model. Transportation Research Record: Journal of the Transportation Research Board. 2018;2672(47). https://doi.org/10.1177/0361198118773556</mixed-citation>
      </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>