Explainable AI in Predictive Analytics Pipelines Using Snowflake Native Apps and AWS Glue Catalog Integration

  • Authors

    • Dr. Shalini Gupta Associate Professor, Panjab University, India. Author

    DOI:

    https://doi.org/10.67228/30715717/IJDEIC-2022PI6B4Y

    Published 04-14-2022

  • Explainable Ai (Xai), Predictive Analytics, Snowflake Native Apps, Aws Glue Catalog, Data Governance, Shap, Lime, Model Interpretability, Cloud-Native Pipelines, Real-Time Inference, Metadata Management, Responsible Ai, Data Engineering, Ai Transparency, Ai Compliance

    Issue

    Vol. 5 No. 1 (2022)

    Section

    Articles

    How to Cite

    [1]
    S. Gupta, “Explainable AI in Predictive Analytics Pipelines Using Snowflake Native Apps and AWS Glue Catalog Integration”, IJDEIC, vol. 5, no. 1, pp. 01–09, Apr. 2022, doi: 10.67228/30715717/IJDEIC-2022PI6B4Y.

  • Abstract

    In the era of data-driven decision-making, predictive analytics models are increasingly deployed in cloud-native environments. However, their adoption in critical applications is often hindered by a lack of transparency and interpretability. This paper explores the integration of Explainable Artificial Intelligence (XAI) techniques into predictive analytics pipelines using Snowflake Native Apps and AWS Glue Catalog. We present a modular architecture that leverages the metadata-driven capabilities of AWS Glue for robust data governance and schema discovery, while utilizing Snowflake’s native application framework for scalable model deployment and real-time inference. By embedding explainability modules such as SHAP and LIME directly within the pipeline, stakeholders gain clearer insights into model behavior and decision logic. A case study on customer churn prediction demonstrates the practical benefits of this approach, highlighting improved trust, compliance, and actionable intelligence. We further discuss the architectural advantages, implementation challenges, and future opportunities for combining XAI with cloud-native analytics platforms.

  • References

    [1] Ribeiro, M. T., Singh, S., & Guestrin, C. (2016). "Why Should I Trust You?": Explaining the Predictions of Any Classifier. Proceedings of the 22nd ACM SIGKDD, 1135–1144.

    [2] Lundberg, S. M., & Lee, S. I. (2017). A Unified Approach to Interpreting Model Predictions. Advances in Neural Information Processing Systems (NeurIPS), 4765–4774.

    [3] Arya, V., et al. (2019). One Explanation Does Not Fit All: A Toolkit and Taxonomy of AI Explainability Techniques. ArXiv preprint arXiv: 1909.03012.

    [4] Doshi-Velez, F., & Kim, B. (2017). Towards a Rigorous Science of Interpretable Machine Learning. ArXiv preprint arXiv: 1702.08608.

    [5] Lipton, Z. C. (2016). The Mythos of Model Interpretability. ArXiv preprint arXiv: 1606.03490.

    [6] Hall, P., Gill, N., & Schmidt, J. (2019). Machine Learning in Practice: Interpretability and Explainability. O’Reilly Media.

    [7] Shankaranarayana, S. M., & Runje, A. (2021). Alibi Explain: Machine Learning Model Explanation Library. ArXiv preprint arXiv: 2107.10482.

    [8] Suresh, H., & Guttag, J. V. (2021). A Framework for Understanding Unintended Consequences of Machine Learning. Communications of the ACM, 64(11), 62–71.

    [9] Bhatt, U., et al. (2020). Explainable Machine Learning in Deployment. Proceedings of the 2020 ACM Conference on Fairness, Accountability, and Transparency, 648–657.

  • Downloads