<?xml version="1.0" encoding="UTF-8"?>
<ArticleSet>
  <Article>
    <Journal>
      <PublisherName></PublisherName>
      <JournalTitle>Journal of Management and Business Solutions</JournalTitle>
      <Issn>3092-7226</Issn>
      <Volume></Volume>
      <Issue>In Press</Issue>
      <PubDate PubStatus="epublish">
        <Year>2027</Year>
        <Month>05</Month>
        <Day>01</Day>
      </PubDate>
    </Journal>
    <ArticleTitle>A Causal Inference Framework Using Machine Learning to Assess the Effect of Capital Market Expansion on SME Growth</ArticleTitle>
    <VernacularTitle>A Causal Inference Framework Using Machine Learning to Assess the Effect of Capital Market Expansion on SME Growth</VernacularTitle>
    <FirstPage>1</FirstPage>
    <LastPage>12</LastPage>
    <Language>EN</Language>
    <AuthorList>
      <Author>
        <FirstName></FirstName>
        <LastName></LastName>
        <Affiliation></Affiliation>
      </Author>
    </AuthorList>
    <PublicationType>Journal Article</PublicationType>
    <History>
      <PubDate PubStatus="received">
        <Year>2026</Year>
        <Month>02</Month>
        <Day>12</Day>
      </PubDate>
    </History>
    <Abstract>&lt;p&gt;The objective of this study was to develop and empirically test a causal inference framework integrating machine learning techniques to estimate the effect of capital market expansion on the growth of small and medium-sized enterprises. This study employed a quantitative, explanatory, and quasi-experimental design using observational panel data from 412 SMEs operating in Tehran over the period 2019 to 2024. Data were collected from a combination of audited financial records, official economic databases, and structured questionnaires measuring firm-level characteristics such as financial literacy and innovation capacity. To address selection bias, propensity score matching was applied to construct comparable treatment and control groups based on baseline firm attributes. The causal impact of capital market expansion was then estimated using a difference-in-differences model. In addition, advanced machine learning methods, including gradient boosting and causal forests, were utilized to model non-linear relationships and estimate heterogeneous treatment effects. Model robustness was evaluated through cross-validation and sensitivity analyses, and all analyses were conducted using Python and R environments. The results revealed a statistically significant positive causal effect of capital market expansion on SME growth, with treated firms exhibiting higher growth rates compared to non-treated firms (p &amp;lt; 0.001). The interaction effect in the difference-in-differences model confirmed that exposure to capital markets substantially enhances firm performance over time. Machine learning results demonstrated strong predictive accuracy and identified non-linear relationships, indicating diminishing marginal returns at higher levels of exposure. Heterogeneous treatment effect analysis showed that medium-sized firms and those with higher financial literacy and innovation capacity experienced significantly stronger growth effects (p &amp;lt; 0.001), highlighting the moderating role of internal capabilities. The findings provide robust evidence that capital market expansion plays a critical causal role in enhancing SME growth, particularly when complemented by firm-level capabilities such as financial literacy and innovation. The integration of causal inference and machine learning offers a comprehensive analytical framework for understanding complex economic relationships and provides valuable insights for policymakers and practitioners aiming to promote sustainable SME development.&lt;/p&gt;</Abstract>
    <ObjectList>
      <Object Type="keyword">
        <Param Name="value">SME growth</Param>
      </Object>
      <Object Type="keyword">
        <Param Name="value">capital market expansion</Param>
      </Object>
      <Object Type="keyword">
        <Param Name="value">causal inference</Param>
      </Object>
      <Object Type="keyword">
        <Param Name="value">machine learning</Param>
      </Object>
      <Object Type="keyword">
        <Param Name="value">financial access</Param>
      </Object>
      <Object Type="keyword">
        <Param Name="value">heterogeneous treatment effects</Param>
      </Object>
    </ObjectList>
    <ArchiveCopySource DocType="pdf">https://www.journalmbs.com/index.php/jmbs/article/download/300/222</ArchiveCopySource>
  </Article>
</ArticleSet>
