Performance Evaluation and Comparison of a New Regression Algorithm
This is an incremental study that provides a detailed performance comparison for regression tasks, aimed at researchers and practitioners in machine learning.
The paper compares a newly proposed regression algorithm against four conventional methods using Mean Absolute Error on diverse datasets, showing its potential and robustness, though no specific performance numbers are provided.
In recent years, Machine Learning algorithms, in particular supervised learning techniques, have been shown to be very effective in solving regression problems. We compare the performance of a newly proposed regression algorithm against four conventional machine learning algorithms namely, Decision Trees, Random Forest, k-Nearest Neighbours and XG Boost. The proposed algorithm was presented in detail in a previous paper but detailed comparisons were not included. We do an in-depth comparison, using the Mean Absolute Error (MAE) as the performance metric, on a diverse set of datasets to illustrate the great potential and robustness of the proposed approach. The reader is free to replicate our results since we have provided the source code in a GitHub repository while the datasets are publicly available.