Beyond explaining: XAI-based Adaptive Learning with SHAP Clustering for Energy Consumption Prediction

• DOI: 10.48550/arxiv.2402.04982
• Publication Date: 2024-02-07
• Authors: Tobias Clement; Hung T. Nguyen; Nils Kemmerzell; Mohamed Abdelaal; Davor Stjelja
• Keywords: Consumption

This paper presents an approach integrating explainable artificial intelligence (XAI) techniques with adaptive learning to enhance energy consumption prediction models, a focus on handling data distribution shifts. Leveraging SHAP clustering, our method provides interpretable explanations for model predictions and uses these insights adaptively refine the model, balancing complexity predictive performance. We introduce three-stage process: (1) obtaining values explain predictions, (2) clustering identify distinct patterns outliers, (3) refining based derived characteristics. Our mitigates overfitting ensures robustness in evaluate comprehensive dataset comprising records of buildings, as well two additional datasets assess transferability other domains, regression, classification problems. experiments demonstrate effectiveness both task types, resulting improved performance explanations.