| Title | A Supervised Feature Selection Approach Based on Global Sensitivity |
| Authors | Sulieman, Hana; Alzaatreh, Ayman |
| Year | 2018 |
| Volume | Archives of Data Science, Series A 5(1) / 2018 |
| Abstract | In this paper we propose a wrapper method for feature selection in supervised learning. It is based on the global sensitivity analysis; a variance-based technique that determines the contribution of each feature and their interactions to the overall variance of the target variable. First-order and total Sobol sensitivity indices are used for feature ranking. Feature selection based on global sensitivity is a wrapper method that utilizes the trained model to evaluate feature importance. It is characterized by its computational efficiency because both sensitivity indices are calculated using the same Monte Carlo integral. A publicly available data set in machine learning is used to demonstrate the application of the algorithm. |