The use of Explainable AI and federated learning

The gap

Evidence profile

Sourced from the limitations and future-work section of the source papers, classified as general, spanning 3 journals.

Supporting evidence — 4 representative gaps

• Leveraging AI-Driven Training Platforms to Mitigate Accounting Workforce Shortages and Enhance Financial Reporting Compliance Standards Globally (2026) · International Journal of Computer Applications Technology and Research · doi

  WORK 11.1 Limitations Despite the promising results, the proposed framework has several limitations that may affect its generalizability and practical implementation. Data bias remains a concern, as training datasets may not fully represent diverse workforce characteristics or organizational contexts. Additionally, the interpretability of complex machine learning models, particularly neural networks, poses challenges in explaining decision-making processes and ensuring transparency. These limitations may impact user trust and regulatory acceptance, highlighting the need for further refinement and validation. Addressing these challenges is essential for broader adoption and long-term effectiveness. 11.2 Future Research Future research should focus on the integration of advanced machine learning techniques, such as reinforcement learning, to enable more dynamic and adaptive training systems. The incorporation of real-time data streams can further enhance system responsiveness and support continuous learning adaptation. Additionally, the development of explainable AI methods can improve transparency and trust in predictive models. These advancements will contribute to more effective and scalable professional development systems in accounting and other domains. framework 12.

  generallimitationsevidence 5/5
  Keywords: learning limitations framework training additionally machine models challenges transparency trust further future systems development despite
• Leveraging AI-Driven Training Platforms to Mitigate Accounting Workforce Shortages and Enhance Financial Reporting Compliance Standards Globally (2026) · International Journal of Computer Applications Technology and Research · doi

  Limitations Despite the promising results, the proposed framework has several limitations that may affect its generalizability and practical implementation. Data bias remains a concern, as training datasets may not fully represent diverse workforce characteristics or organizational contexts. Additionally, the interpretability of complex machine learning models, particularly neural networks, poses challenges in explaining decision-making processes and ensuring transparency. These limitations may impact user trust and regulatory acceptance, highlighting the need for further refinement and validation. Addressing these challenges is essential for broader adoption and long-term effectiveness. 11.2 Future Research Future research should focus on the integration of advanced machine learning techniques, such as reinforcement learning, to enable more dynamic and adaptive training systems. The incorporation of real-time data streams can further enhance system responsiveness and support continuous learning adaptation. Additionally, the development of explainable AI methods can improve transparency and trust in predictive models. These advancements will contribute to more effective and scalable professional development systems in accounting and other domains. framework 12.

  generallimitationsevidence 5/5
  Keywords: learning limitations framework training additionally machine models challenges transparency trust further future systems development despite
• A Comprehensive Review of Machine Learning Techniques for Student Academic Performance Prediction (2026) · International Journal for Research in Applied Science and Engineering Technology · doi

  The use of Explainable AI and federated learning to improve model interpretability and fairness. The development of real-time adaptive feedback systems to improve student outcomes. The conduct of longitudinal studies to assess the prospective performance of machine learning models in real-world institutional settings.

  generalfuture-work sectionevidence 5/5
  Keywords: use explainable federated learning improve model interpretability fairness
• Leveraging machine learning for enhanced employee productivity insights (2026) · Quality & Quantity · doi

  Investigating the use of more advanced machine learning models, - Exploring the application of machine learning to other areas of human resources, - Analyzing the impact of temporal variations in employee behavior on machine learning models, - Addressing feature importance and model interpretability in machine learning analysis

  generalfuture-work sectionevidence 5/5
  Keywords: investigating use advanced machine learning models exploring application

Questions about this gap