Modified SHAP approach for interpretable prediction of cardiovascular complications

Sharipov, D.K., Saidov, A.D., Шарипов, Д.К., Саидов, А.Д.

Ҳисоблаш ва амалий математика муаммолари · 2025-yil

Annotatsiya

This article explores the significance of modifying SHAP (SHapley Additive exPlana tions) values to enhance model interpretability in machine learning. SHAP values provide a fair attribution of feature contributions, making AI-driven decision-making more trans parent and reliable. However, raw SHAP values can sometimes be difficult to interpret due to feature interactions, noise, and inconsistencies in scale. The article discusses key techniques for modifying SHAP values, including feature aggregation, normalization, cus tom weighting, and noise reduction, to improve clarity and relevance in explanations. It also examines how these modifications align interpretations with real-world needs, ensur ing that SHAP-based insights remain practical and actionable. By strategically refining SHAP values, data scientists can derive more meaningful explanations, improving trust in AI models and enhancing decision-making processes. The article provides a structured approach to modifying SHAP values, offering practical applications and benefits across various domains. 

Maqola ma’lumotlari
MualliflarSharipov, D.K., Saidov, A.D., Шарипов, Д.К., Саидов, А.Д.
JurnalҲисоблаш ва амалий математика муаммолари
Nashr sanasi2025-05-15
Son2
Betlar114-122
TilIngliz
DOI10.71310/pcam.2_64.2025.10

Kalit so‘zlar

model interpretability, feature importance, normalization, AI transparency, интерпретабельность модели, важность признаков, нормализация, прозрачность ИИ

Ilmiy soha

Ҳисоблаш ва амалий математика муаммолари jurnalidan boshqa maqolalar

Ҳисоблаш ва амалий математика муаммолари — barcha maqolalar