<?xml version="1.0" encoding="UTF-8"?>
<ArticleSet>
  <Article>
    <Journal>
      <PublisherName>KMAN Publication Inc. (KMANPUB)</PublisherName>
      <JournalTitle>Applied Family Therapy Journal (AFTJ) </JournalTitle>
      <Issn>3041-8798</Issn>
      <Volume>7</Volume>
      <Issue>Serial Number 35</Issue>
      <PubDate PubStatus="epublish">
        <Year>2026</Year>
        <Month>09</Month>
        <Day>01</Day>
      </PubDate>
    </Journal>
    <ArticleTitle>Predicting Infidelity Tendency From Relationship Dissatisfaction, Sexual Satisfaction, Attachment, and Impulsivity Using CatBoost</ArticleTitle>
    <VernacularTitle>Predicting Infidelity Tendency From Relationship Dissatisfaction, Sexual Satisfaction, Attachment, and Impulsivity Using CatBoost</VernacularTitle>
    <FirstPage>1</FirstPage>
    <LastPage>17</LastPage>
    <Language>EN</Language>
    <AuthorList>
      <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>2026</Year>
        <Month>05</Month>
        <Day>09</Day>
      </PubDate>
    </History>
    <Abstract>&lt;p&gt;&lt;strong&gt;Objective:&lt;/strong&gt; This study aimed to predict infidelity tendency among married adults from relationship dissatisfaction, sexual satisfaction, attachment anxiety, attachment avoidance, and impulsivity using the CatBoost machine-learning algorithm and to determine the relative predictive contribution of these factors.&lt;/p&gt;
&lt;p&gt;&lt;strong&gt;Methods and Materials:&lt;/strong&gt; This cross-sectional predictive study was conducted among 512 married adults residing in Qatar. Infidelity tendency was assessed using the Propensity Towards Infidelity Scale, relationship dissatisfaction using the reverse-scored Couples Satisfaction Index-16, sexual satisfaction using the New Sexual Satisfaction Scale, attachment anxiety and attachment avoidance using the Experiences in Close Relationships-Revised questionnaire, and impulsivity using the Barratt Impulsiveness Scale-11. The dataset was randomly divided into an 80% development sample and a 20% holdout test sample. CatBoost regression was trained using five-fold cross-validation and compared with multiple linear regression, random forest, and XGBoost. Predictive performance was evaluated using root mean squared error, mean absolute error, and coefficient of determination. Feature importance, SHAP values, and ablation analyses were used to interpret the final model.&lt;/p&gt;
&lt;p&gt;&lt;strong&gt;Findings:&lt;/strong&gt; CatBoost demonstrated the best predictive performance, achieving a cross-validation RMSE of 5.34, MAE of 4.15, and R² of .66, and a holdout test RMSE of 5.42, MAE of 4.19, and R² of .64. Relationship dissatisfaction was the strongest predictor, accounting for 31.8% of normalized feature importance, followed by impulsivity at 24.6%, sexual satisfaction at 18.9%, attachment avoidance at 14.2%, and attachment anxiety at 10.5%. SHAP analysis indicated that greater relationship dissatisfaction, impulsivity, attachment avoidance, and attachment anxiety increased predicted infidelity tendency, whereas higher sexual satisfaction reduced predicted tendency. Removing relationship dissatisfaction produced the largest decline in model performance, reducing test R² from .64 to .54.&lt;/p&gt;
&lt;p&gt;&lt;strong&gt;Conclusion:&lt;/strong&gt; Infidelity tendency was most accurately predicted through the combined contribution of relational dissatisfaction, sexual functioning, attachment insecurity, and behavioral disinhibition. CatBoost provided superior predictive performance compared with conventional and alternative machine-learning models.&lt;/p&gt;</Abstract>
    <ObjectList>
      <Object Type="keyword">
        <Param Name="value">Infidelity tendency</Param>
      </Object>
      <Object Type="keyword">
        <Param Name="value">CatBoost</Param>
      </Object>
      <Object Type="keyword">
        <Param Name="value">relationship dissatisfaction</Param>
      </Object>
      <Object Type="keyword">
        <Param Name="value">sexual satisfaction</Param>
      </Object>
      <Object Type="keyword">
        <Param Name="value">attachment</Param>
      </Object>
      <Object Type="keyword">
        <Param Name="value">impulsivity</Param>
      </Object>
      <Object Type="keyword">
        <Param Name="value">machine learning</Param>
      </Object>
    </ObjectList>
    <ArchiveCopySource DocType="pdf">https://www.journals.kmanpub.com/index.php/aftj/article/download/6566/12213</ArchiveCopySource>
  </Article>
</ArticleSet>
