A new imputation method based on genetic programming and weighted KNN for symbolic regression with incomplete data

Incompleteness is one of the problematic data quality challenges in real-world machine learning tasks. A large number studies have been conducted for addressing this challenge. However, most existing focus on classification task and only a limited symbolic regression with missing values exist. In work, new imputation method incomplete proposed. The aims to improve both effectiveness efficiency imputing regression. This based genetic programming (GP) weighted K-nearest neighbors (KNN). It constructs GP-based models using other available features predict features. instances used constructing such are selected KNN. experimental results sets show that proposed outperforms state-of-the-art methods respect accuracy, performance, time.