An adaptive ensemble feature selection technique for model-agnostic diabetes prediction

Ensemble learning aggregates several models' outputs to improve the overall model's performance. Ensemble feature selection separating the appropriate features from the extra and non-essential features. In this paper, the main focus will be to expand the scope of Ensemble Learning to include Feature Selection. We will propose an Ensemble Feature Selection Method called AdaptDiabfor Diabetes Prediction that is Model-Agnostic. Our approach combines diverse feature selection techniques, such as filter and wrapper methods, harnessing their complementary strengths. We have used an adaptive combiner function, which dynamically selects the most informative features based on the characteristics of the ensemble members. We demonstrate the effectiveness of our proposed AdaptDiab method through empirical studies using various classification models. Empirical Results of Our Proposed Ensemble Feature Selection Model outperforms traditional methods. This paper contributes to Ensemble Learning Methods and provides a Practical and Better Framework for Feature selection.