Adaptive AutoML for Structured Tabular Prediction: Design, Implementation, and Reproducible Evaluation of a Lightweight No-Code Baseline Platform

Author

Kaushik P, Jai Kaarthik.B, Dr. G. Paavai Anand


Abstract

 Automated machine learning (AutoML) aims to reduce the repetitive effort required to transform a structured dataset into an evaluated predictive model. However, full AutoML systems often involve extensive search, nontrivial compute costs, and methodological complexity that may be unsuitable for introductory or lightweight applications. This paper presents Adaptive AutoML, a Python and Streamlit platform that integrates CSV/Excel ingestion, data profiling, task and target configuration, automated type-dependent preprocessing, comparison of three fixed candidate estimators per task, and downloadable prediction outputs. The implemented classification candidates are logistic regression, random forests, and extremely randomized trees; the regression candidates are ridge regression, random forests, and extremely randomized trees. Training-only fitting of preprocessing steps reduces a common source of leakage. We audit the supplied implementation, execute all three provided unit tests, and conduct 105 estimator fits across seven public or deterministic synthetic datasets using five random train/test splits. Additional two-stage evaluations reserve untouched external test subsets to examine the distinction between model selection and generalization assessment. On the Wine benchmark, Extra Trees attains 0.9889 mean accuracy across five splits; on synthetic Friedman-1 regression, Extra Trees attains a mean root-mean-square error of 1.9711. Results vary substantially by dataset, and no model family dominates all tasks. Importantly, the current interface selects its best model using the same held-out data whose scores it displays; consequently, the displayed winning score is not an independent post-selection performance estimate. We position the contribution as an accessible, auditable baseline workflow rather than a novel optimization algorithm, and identify concrete steps required for stronger validity and deployment.


Keywords

automated machine learning; tabular prediction; Streamlit; scikit-learn; model selection; leakage-aware preprocessing; reproducibility



Full Text:

Download Paper PDF


References


  • Bergstra, J., & Bengio, Y. (2012). Random Search for Hyper-Parameter Optimization. Journal of Machine Learning Research, 13, 281–305. https://www.jmlr.org/papers/v13/bergstra12a.html
  • Breiman, L. (2001). Random Forests. Machine Learning, 45, 5–32. https://doi.org/10.1023/A:1010933404324
  • Feurer, M., Klein, A., Eggensperger, K., Springenberg, J., Blum, M., & Hutter, F. (2015). Efficient and Robust Automated Machine Learning. Advances in Neural Information Processing Systems 28. https://papers.neurips.cc/paper_files/paper/2015/hash/11d0e6287202fced83f79975ec59a3a6-Abstract.html
  • Geurts, P., Ernst, D., & Wehenkel, L. (2006). Extremely Randomized Trees. Machine Learning, 63, 3–42. https://doi.org/10.1007/s10994-006-6226-1
  • Hoerl, A. E., & Kennard, R. W. (1970). Ridge Regression: Biased Estimation for Nonorthogonal Problems. Technometrics, 12(1), 55–67. https://doi.org/10.1080/00401706.1970.10488634
  • Hunter, J. D. (2007). Matplotlib: A 2D Graphics Environment. Computing in Science & Engineering, 9(3), 90–95. https://doi.org/10.1109/MCSE.2007.55
  • Hutter, F., Kotthoff, L., & Vanschoren, J. (Eds.). (2019). Automated Machine Learning: Methods, Systems, Challenges. Springer. https://doi.org/10.1007/978-3-030-05318-5
  • McKinney, W. (2010). Data Structures for Statistical Computing in Python. Proceedings of the 9th Python in Science Conference, 56–61. https://doi.org/10.25080/Majora-92bf1922-00a
  • Olson, R. S., & Moore, J. H. (2016). TPOT: A Tree-based Pipeline Optimization Tool for Automating Machine Learning. Proceedings of Machine Learning Research, 64, 66–74. https://proceedings.mlr.press/v64/olson_tpot_2016.html
  • Pedregosa, F., et al. (2011). Scikit-learn: Machine Learning in Python. Journal of Machine Learning Research, 12, 2825–2830. https://www.jmlr.org/papers/v12/pedregosa11a.html
  • Raschka, S. (2018). Model Evaluation, Model Selection, and Algorithm Selection in Machine Learning. arXiv:1811.12808. https://arxiv.org/abs/1811.12808
  • scikit-learn developers. (2026a). Common Pitfalls and Recommended Practices. https://scikit-learn.org/stable/common_pitfalls.html
  • scikit-learn developers. (2026b). load_breast_cancer API Reference. https://scikit-learn.org/stable/modules/generated/sklearn.datasets.load_breast_cancer.html
  • scikit-learn developers. (2026c). load_diabetes API Reference. https://scikit-learn.org/stable/modules/generated/sklearn.datasets.load_diabetes.html
  • scikit-learn developers. (2026d). load_iris API Reference. https://scikit-learn.org/stable/modules/generated/sklearn.datasets.load_iris.html
  • scikit-learn developers. (2026e). load_wine API Reference. https://scikit-learn.org/stable/modules/generated/sklearn.datasets.load_wine.html
  • scikit-learn developers. (2026f). make_friedman1 API Reference. https://scikit-learn.org/stable/modules/generated/sklearn.datasets.make_friedman1.html
  • (2026). Streamlit Documentation. https://docs.streamlit.io/
  • Varma, S., & Simon, R. (2006). Bias in Error Estimation When Using Cross-Validation for Model Selection. BMC Bioinformatics, 7, Article 91. https://doi.org/10.1186/1471-2105-7-91

Share your valuable work from Social Media Buttons