Nowadays the amount of data that is collected in various settings is growing rapidly. These elaborate data records enable the training of machine learning models that can be used to extract insights and for making better informed decisions. When doing the data mining task, on one hand, feature selection is often used to reduce the dimensionality of the data. On the other hand, we need to decide the structure (parameters) of the model when building the model. However, feature selection and the parameters of the model may interact and affect the performance of the model. Therefore, it is difficult to decide the optimal parameter and the optimal feature subset without an exhaustive search of all the combination of the parameters and the feature subsets which is time-consuming. In this paper, we study how the interaction between feature selection and the parameters of a model affect the performance of the model through experiments on four data sets.
|Publication status||Published - 2018|
|Event||International Conference on Information Processing and Management of Uncertainty in Knowledge-Based Systems - Cadiz, Spain|
Duration: 11 Jun 2018 → 15 Jun 2018
|Conference||International Conference on Information Processing and Management of Uncertainty in Knowledge-Based Systems|
|Abbreviated title||IPMU 2018|
|Period||11/06/18 → 15/06/18|