<?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>3</Volume>
      <Issue>Serial Number 13</Issue>
      <PubDate PubStatus="epublish">
        <Year>2025</Year>
        <Month>06</Month>
        <Day>10</Day>
      </PubDate>
    </Journal>
    <ArticleTitle>Simulation of Rational Investment Decision-Making Based on Earnings Quality and Its Impact on Future Stock Returns in the Tehran Stock Exchange</ArticleTitle>
    <VernacularTitle>Simulation of Rational Investment Decision-Making Based on Earnings Quality and Its Impact on Future Stock Returns in the Tehran Stock Exchange</VernacularTitle>
    <FirstPage>1</FirstPage>
    <LastPage>26</LastPage>
    <Language>EN</Language>
    <AuthorList>
      <Author>
        <FirstName></FirstName>
        <LastName></LastName>
        <Affiliation></Affiliation>
      </Author>
      <Author>
        <FirstName></FirstName>
        <LastName></LastName>
        <Affiliation></Affiliation>
      </Author>
      <Author>
        <FirstName></FirstName>
        <LastName></LastName>
        <Affiliation></Affiliation>
      </Author>
    </AuthorList>
    <PublicationType>Journal Article</PublicationType>
    <History>
      <PubDate PubStatus="received">
        <Year>2025</Year>
        <Month>04</Month>
        <Day>04</Day>
      </PubDate>
    </History>
    <Abstract>&lt;p&gt;This study was conducted with the aim of simulating investors’ rational decision-making processes based on earnings quality and examining its impact on future stock returns in the Tehran Stock Exchange. The research also investigated the moderating role of behavioral biases and proposed an integrated framework based on game theory and Bayesian inference for portfolio optimization. Data from 129 listed firms during the period 2001–2023 (2,193 firm-year observations) were selected using a systematic deletion method. The integrated methodology included dynamic generalized method of moments (GMM) regression to control for endogeneity; artificial neural networks, LSTM, and Transformer models for simulating decision-making; SHAP analysis for interpretability; and Monte Carlo simulation with 100,000 iterations for portfolio optimization. The dimensions of earnings quality (accrual quality: 0.315, earnings persistence: 0.271, predictability: 0.203) had a significant and positive effect on future returns. Adding behavioral variables increased R² from 47.36% to 52.47% and reduced RMSE by 13.44%. The Friedman test (χ² = 187.45, p &amp;lt; 0.0001) confirmed the significant moderating role of behavioral factors. The Multi-head Transformer model demonstrated the best predictive performance (R² = 85.12%). The optimized portfolio produced a return of 26.12% with a Sharpe ratio of 1.351, which was 83.6% better than the market index. Therefore, the results indicate that integrating fundamental factors (earnings quality) and behavioral factors within a unified game-theoretic framework significantly enhances the predictive power of future returns. Investors, in addition to traditional financial analysis, should pay particular attention to reporting-quality signals and behavioral indicators of the market.&lt;/p&gt;</Abstract>
    <ObjectList>
      <Object Type="keyword">
        <Param Name="value">earnings quality</Param>
      </Object>
      <Object Type="keyword">
        <Param Name="value">future returns</Param>
      </Object>
      <Object Type="keyword">
        <Param Name="value">rational decision-making simulation</Param>
      </Object>
      <Object Type="keyword">
        <Param Name="value">behavioral biases</Param>
      </Object>
      <Object Type="keyword">
        <Param Name="value">game theory</Param>
      </Object>
      <Object Type="keyword">
        <Param Name="value">deep learning</Param>
      </Object>
    </ObjectList>
    <ArchiveCopySource DocType="pdf">https://journalmbs.com/index.php/jmbs/article/download/85/70</ArchiveCopySource>
  </Article>
</ArticleSet>
