ExplainabilityTransparencyTrustworthinesscs.LG
A comparative analysis of machine learning models in SHAP analysis
Justin Lin, Julia Fukuyama
April 8, 2026
arXiv.org
1 citations
Key Takeaways
-
SHAP analysis helps make "black-box" AI models more trustworthy by quantifying how much each piece of data (feature) contributes to a model's prediction, addressing a critical gap in high-stakes applications where understanding why a decision was made is essential.
-
There is no one-size-fits-all approach to interpreting SHAP values — the meaning and analysis of these explanations depends on which machine learning model is being used, so practitioners need model-specific guidance rather than universal procedures.
-
SHAP analysis empowers data-driven problem-solving by providing detailed insight into how models make decisions, enabling organizations to identify potential biases, validate that models are using appropriate reasoning, and build more accountable AI systems.
-
The paper extends SHAP visualization tools to multi-classification problems, making the explanation method more practical for real-world scenarios where AI systems must choose between many categories rather than just two outcomes.
Abstract
In this growing age of data and technology, large black-box models are becoming the norm due to their ability to handle vast amounts of data and learn incredibly complex data patterns. The deficiency of these methods, however, is their inability to explain the prediction process, making them untrustworthy and their use precarious in high-stakes situations. SHapley Additive exPlanations (SHAP) analysis is an explainable AI method growing in popularity for its ability to explain model predictions in terms of the original features. For each sample and feature in the data set, an associated SHAP value quantifies the contribution of that feature to the prediction of that sample. Analysis of these SHAP values provides valuable insight into the model's decision-making process, which can be leveraged to create data-driven solutions. The interpretation of these SHAP values, however, is model-dependent, so there does not exist a universal analysis procedure. To aid in these efforts, we present a detailed investigation of SHAP analysis across various machine learning models and data sets. In uncovering the details and nuance behind SHAP analysis, we hope to empower analysts in this less-explored territory. We also present a novel generalization of the waterfall plot to the multi-classification problem.