Paper proposes Explainable AI for trustworthy heat demand forecasting

A new paper introduces an ante-hoc Explainable AI methodology to evaluate the global feature importance of machine learning models used in heat demand forecasting. The research aims to enhance the interpretability and trustworthiness of these models, addressing concerns related to standards, customer satisfaction, and liability. The methodology employs four approaches: the intrinsic interpretability of Gradient Boosting and post-hoc methods like Partial Dependence, Accumulated Local Effects, and SHAP, without relying on feature permutation or perturbations. AI

IMPACT Enhances trust and interpretability in machine learning models for critical infrastructure forecasting.

RANK_REASON The cluster contains an academic paper detailing a new methodology for machine learning interpretability. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.LG →

• Accumulated local effects
• arXiv
• gradient boosting
• Milan Zdravković
• Shap

• paper
• other

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →