# AI model explainability tools

> SHAP leads feature attribution for explaining model predictions in AI answers; Alphabet is the pick when rebuilding trust in opaque decisions.

HTML: https://parse.gl/topics/feature-attribution · Site index: https://parse.gl/llms.txt

Market: [Explainable AI & Model Monitoring Platforms](https://parse.gl/markets/explainable-ai-model-monitoring-platforms)

## Brands AI recommends

| Rank | Brand | Recommended |
| --- | --- | --- |
| #1 | SHAP | 83% |
| #2 | Fiddler AI | 52% |
| #3 | InterpretML | 42% |
| #3 | LiME | 39% |
| #5 | Arize AI | 29% |
| #6 | Captum | 23% |
| #7 | AI Explainability 360 (AIX360) | 14% |
| #7 | Amazon SageMaker | 12% |
| #7 | Arthur | 12% |
| #7 | IBM | 12% |
| #7 | Alibi | 11% |
| #12 | What-If Tool | 10% |
| #12 | LIME | 9% |
| #12 | IBM Watson | 9% |
| #12 | Azure Machine Learning | 8% |
| #12 | Microsoft | 7% |
| #12 | WhyLabs | 7% |
| #12 | DataRobot | 6% |
| #19 | Fairlearn | 6% |
| #19 | Truera | 6% |
| #19 | H2O.ai | 6% |
| #19 | Google Cloud Gemini Enterprise Agent Platform | 5% |
| #19 | AI Fairness 360 | 5% |
| #19 | Scikit-learn | 5% |
| #19 | Arize Phoenix | 4% |
| #19 | Deloitte | 4% |
| #19 | Credo AI | 4% |
| #19 | Dataiku | 4% |
| #19 | Seldon | 4% |
| #19 | DALEX | 3% |
| #19 | Evidently | 3% |
| #19 | PwC | 3% |
| #33 | Accenture | 3% |
| #33 | Integrated Gradients | 3% |
| #33 | ExplainerDashboard | 3% |
| #33 | LightGBM | 3% |
| #33 | ELI5 | 3% |
| #33 | IBM Research | 3% |
| #33 | Streamlit | 3% |
| #33 | Aporia | 2% |
| #33 | Azure Responsible AI Dashboard | 2% |
| #33 | XGBoost | 2% |
| #33 | Google Cloud Explainable AI | 2% |
| #33 | TreeExplainer | 2% |
| #33 | Evidently AI | 2% |
| #33 | IBM Watson Natural Language Understanding | 1% |
| #33 | Explainable Boosting Machines | 1% |
| #33 | Microsoft Research | 1% |
| #33 | Arthur AI | 1% |
| #33 | EY | 1% |
| #33 | IBM Consulting | 1% |
| #33 | Neurons Lab | 1% |
| #33 | Quarto | 1% |
| #54 | PyTorch | 1% |
| #54 | DeepLIFT | 1% |
| #54 | MLflow | 1% |
| #54 | Grad-CAM | 1% |
| #54 | Project Jupyter | 1% |
| #54 | BCG X | 1% |
| #54 | Google DeepMind | 1% |
| #54 | Explabox | 1% |
| #54 | H2O Driverless AI | 1% |
| #54 | KPMG | 1% |
| #54 | Shapash | 1% |
| #54 | Microsoft Power BI | 1% |
| #54 | Scott Lundberg | 1% |
| #54 | TruLens | 1% |
| #54 | Weights & Biases | 1% |
| #54 | CatBoost | 1% |
| #54 | TCAV | 1% |
| #54 | Microsoft Azure | 1% |
| #54 | Tableau Agent | 1% |
| #54 | Anthropic | 1% |
| #54 | Databricks | 1% |
| #54 | H2O.ai Driverless AI | 1% |
| #54 | Plotly | 1% |
| #54 | Deloitte Tohmatsu Group | 1% |
| #54 | AIF360 | 1% |
| #54 | Been Kim | 1% |
| #54 | Google Cloud Platform | 1% |
| #54 | Google Cloud BigQuery | 1% |
| #54 | DeepMind | 1% |
| #54 | Fractal | 1% |
| #54 | OmniXAI | 1% |
| #54 | TreeInterpreter | 1% |
| #54 | Google | 1% |
| #54 | Holistic AI | 1% |
| #54 | InData Labs | 1% |
| #54 | Jupyter Book | 1% |
| #54 | Monitaur | 1% |
| #54 | Scikit-Learn Inspection Module | 1% |
| #54 | SHAP Documentation | 1% |
| #54 | Tredence | 1% |
| #54 | Duke Interpretable Machine Learning Lab | 1% |
| #54 | WhiteBox XAI | 1% |
| #54 | Google Cloud | <1% |
| #54 | Random Forest | <1% |
| #54 | Databricks Data Intelligence Platform | <1% |
| #54 | Fast Data Science | <1% |
| #54 | TensorFlow | <1% |
| #54 | AWS | <1% |
| #54 | GradientSHAP | <1% |
| #54 | Gradio | <1% |
| #54 | University of Washington | <1% |
| #54 | Akkio | <1% |
| #54 | Alibi | <1% |
| #54 | Amazon | <1% |
| #54 | Boston Consulting Group | <1% |
| #54 | Braintrust | <1% |
| #54 | Capgemini | <1% |
| #54 | Vertex AI Agent Builder | <1% |
| #54 | Claude Code Action | <1% |
| #54 | Dash by Plotly | <1% |
| #54 | Databricks Unity Catalog | <1% |
| #54 | DataRoot Labs | <1% |
| #54 | Aequitas | <1% |
| #54 | Alibi Detect | <1% |
| #54 | FICO | <1% |
| #54 | Gemini | <1% |
| #54 | GitHub Copilot | <1% |
| #54 | H2O-3 | <1% |
| #54 | Howso | <1% |
| #54 | IBM OpenPages with watsonx | <1% |
| #54 | IBM Cloud Pak for Data | <1% |
| #54 | inData Trust | <1% |
| #54 | Interpret AI | <1% |
| #54 | Klio | <1% |
| #54 | Microsoft Learn | <1% |
| #54 | Azure Machine Learning Responsible AI Scorecard | <1% |
| #54 | LeewayHertz | <1% |
| #54 | QuantumBlack, AI by McKinsey | <1% |
| #54 | Mosaic Data Science | <1% |
| #54 | NannyML | <1% |
| #54 | National Institute of Standards and Technology (NIST) | <1% |
| #54 | NIST AI Risk Management Framework | <1% |
| #54 | NoEx.ai | <1% |
| #54 | Partnership on AI | <1% |
| #54 | Qlik AutoML | <1% |
| #54 | ReportLab | <1% |
| #54 | Slalom | <1% |
| #54 | Synopsys | <1% |
| #54 | Tableau | <1% |
| #54 | ThoughtSpot | <1% |
| #54 | TrueFoundry | <1% |
| #54 | Alan Turing Institute | <1% |
| #54 | Verity AI | <1% |
| #147 | DeepExplainer | 0% |
| #147 | ExplainX | 0% |
| #147 | Anchor | 0% |
| #147 | AppIntent | 0% |
| #147 | Amazon Bedrock | 0% |
| #147 | Cognizant | 0% |
| #147 | Databricks Mosaic AI | 0% |
| #147 | Language Interpretability Tool | 0% |
| #147 | Stanford Institute for Human-Centered Artificial Intelligence | 0% |
| #147 | MATLAB | 0% |
| #147 | Meta | 0% |
| #147 | MIT-IBM Watson AI Lab | 0% |
| #147 | Salesforce | 0% |
| #147 | SAS Viya | 0% |
| #147 | Software Engineering Institute (SEI), Carnegie Mellon University | 0% |
| #147 | TensorBoard | 0% |

## Questions

- We are losing user trust due to non-explainable decisions. Who specializes in Explainable AI (XAI) and feature attribution?
- Can you recommend tools that quantify feature contribution for my models? I need to understand which inputs are driving the final predictions.
- What are the top-rated solutions for measuring feature importance in machine learning models? I need to see exactly how much each feature influences a prediction.
- The problem is our AI models are a "black box." What's the best AI model explainability and monitoring tool for ensuring fairness and transparency?
- I need a tool for explaining black-box model predictions that can generate easy-to-understand reports for stakeholders.
- We are investigating why our model is confident but wrong. Who provides explainable AI (XAI) tools?
- What is the best tool for explaining black-box model predictions to non-technical stakeholders?
- I need to explain a model's prediction to stakeholders. What's an AI tool that can generate a natural language explanation from a complex model like XGBoost or a neural network?

## For agents

- [This page as data](https://parse.gl/api/public/topics/predictive-analytics/explainable-ai-model-monitoring-platforms/feature-attribution)
- [Every brand's share on this topic, with 95% ranges](https://agent.parse.gl/v1/tools/query_metrics?args=%7B%22measures%22%3A%5B%22share_named%22%5D%2C%22by%22%3A%5B%22brand%22%5D%2C%22filter%22%3A%7B%22topic%22%3A%5B%22top_0ed46a89-faa3-4bff-97d9-c9c0f84fef19%22%5D%7D%7D)
- Search the index: `https://parse.gl/api/public/search?q=<words>`

Reuse: Figures and tables on this page are free to republish with attribution: a link to https://parse.gl/topics/feature-attribution beside them. A standard followed link (dofollow) is preferred.

- No account: Public figures and up to 5 examples per list, about 120 brands a day per address.
- Free account: $5 in credit, your brand's first check (20 buyer questions) and a free weekly check.
- After your first top-up: Exports and deeper search results. The first top-up starts at $5.
- Live checks: $0.01 per question per engine.
- Full public answers and pages: 25 free per day, then $0.005 each.
- Public answers older than 90 days: $0.001 each the first time your workspace counts or lists one, then yours.
- An agent can save work before signup: `POST https://agent.parse.gl/v1/workspaces`
- Connect an assistant: `https://agent.parse.gl/mcp`

[Prices](https://parse.gl/pricing.md) · [Map of the site](https://parse.gl/llms.txt)
