• explainable artificial intelligence
• incomplete data
• missing values
• interpretable machine learning

Handling missing data is a significant challenge in the field of Machine Learning.
While multiple Machine Learning algorithms can tackle this problem, there is a need for more transparent and interpretable approaches that can effectively handle missing data. As the development of understandable algorithms becomes increasingly essential, it is also crucial to have methods that can adequately manage them.
This master's thesis project proposes an extended version of a widely used local and model-agnostic explainer that 
enables explainability in the presence of missing values. Extensive experiments show the effectiveness of the proposed method.