Predictability Analysis of Regression Problems via Conditional Entropy Estimations
This work addresses the need for better predictability analysis in regression problems for machine learning practitioners, offering incremental improvements in interpretability and framework development.
This study tackled the problem of assessing predictability in regression problems by introducing conditional entropy estimators, specifically KNIFE-P and LMC-P, which provide under- and over-estimation to analyze the achievable performance and limitations of feature sets, with results demonstrating their robustness and utility on synthesized and real-world datasets.
In the field of machine learning, regression problems are pivotal due to their ability to predict continuous outcomes. Traditional error metrics like mean squared error, mean absolute error, and coefficient of determination measure model accuracy. The model accuracy is the consequence of the selected model and the features, which blurs the analysis of contribution. Predictability, in the other hand, focus on the predictable level of a target variable given a set of features. This study introduces conditional entropy estimators to assess predictability in regression problems, bridging this gap. We enhance and develop reliable conditional entropy estimators, particularly the KNIFE-P estimator and LMC-P estimator, which offer under- and over-estimation, providing a practical framework for predictability analysis. Extensive experiments on synthesized and real-world datasets demonstrate the robustness and utility of these estimators. Additionally, we extend the analysis to the coefficient of determination \(R^2 \), enhancing the interpretability of predictability. The results highlight the effectiveness of KNIFE-P and LMC-P in capturing the achievable performance and limitations of feature sets, providing valuable tools in the development of regression models. These indicators offer a robust framework for assessing the predictability for regression problems.