• Prajwal Narayan Yalligutti
• Shashank H
• H Sangamesh

The research introduces and evaluates a novel automated system to eliminate the frustrating "trial-and-error" phase of machine learning (ML) model selection. The system is based on data profiling (or "datasetification"), which is a methodical approach to studying the nature of a dataset in order to quickly determine the correct task type (classification or regression) and cascade many algorithms all in one [automated] pipeline from data preprocessing to model ranking. Evaluation will be made following task metrics; for example, using the F1 score for classification tasks and the R2 coefficient for regression tasks. In both endeavours using the power of data profiling and the flexibility of scikit-learn, we clearly demonstrate higher performance for treeensemble models over classical linear modeling approaches both in terms of OH's work and through ensemble models offered in today's frameworks (XGBoost, LightGBM, CatBoost).In the end, the system allows for a clear feedback mechanism by displaying output on a universally understood ranked leaderboard, giving all data scientists (novice to expert) a fast and objective way to identify what algorithms to use and how to set them up, just after they have prepared their data.

Automated Machine Learning (AutoML), Model Selection, Data Profiling, Ensemble Methods, Classification, Regression, Predictive Modeling Efficiency.1. Introduction: The Model Selection Bottleneck.

"IDENTIFICATION OF ALGORITHM USING AI/ ML DATASET: A SYSTEMATIC FRAMEWORK FOR AUTOMATED MODEL SELECTION", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.12, Issue 11, page no.c429-c433, November-2025, Available :http://www.jetir.org/papers/JETIR2511252.pdf

"IDENTIFICATION OF ALGORITHM USING AI/ ML DATASET: A SYSTEMATIC FRAMEWORK FOR AUTOMATED MODEL SELECTION", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.12, Issue 11, page no. ppc429-c433, November-2025, Available at : http://www.jetir.org/papers/JETIR2511252.pdf