Sold by: Mphasis
Deployed on AWS
Explainable AI solution to identify the important words in text-classification models and their impact on predicted output
Overview
Explainable AI - NLP Models solution can identify the important words (tokens) from a text classification model and provide the effect they have on each predicted class. The solution can work with many sklearn based models without specifying the type of algorithm used to create these models. This helps users to interpret the predictions in much more detail rather than just getting the predicted class.
Highlights
- The solution takes in the data and model for which the AI explanations must be computed. The result generated contains the features (words/tokens) that are significant in making the prediction for an instance.
- The AI explanations act as a performance measure to help us determine whether the model is robust. It also helps us determine if there are any biases and prejudices which have got incorporated in the machine learning models
- PACE - ML is Mphasis Framework and Methodology for end-to-end machine learning development and deployment. PACE-ML enables organizations to improve the quality & reliability of the machine learning solutions in production and helps automate, scale, and monitor them. Need customized Machine Learning and Deep Learning solutions? Get in touch!
Details
Sold by
Delivery method
Latest version
Deployed on AWS
Unlock automation with AI agent solutions
Fast-track AI initiatives with agents, tools, and solutions from AWS Partners.
Features and programs
Financing for AWS Marketplace purchases
AWS Marketplace now accepts line of credit payments through the PNC Vendor Finance program. This program is available to select AWS customers in the US, excluding NV, NC, ND, TN, & VT.
Pricing
Pricing is based on actual usage, with charges varying according to how much you consume. Subscriptions have no end date and may be canceled any time.
Additional AWS infrastructure costs may apply. Use the AWS Pricing Calculator to estimate your infrastructure costs.
Dimension | Description | Cost/host/hour |
|---|---|---|
ml.m5.xlarge Inference (Batch) Recommended | Model inference on the ml.m5.xlarge instance type, batch mode | $16.00 |
ml.m5.xlarge Inference (Real-Time) Recommended | Model inference on the ml.m5.xlarge instance type, real-time mode | $8.00 |
ml.m4.4xlarge Inference (Batch) | Model inference on the ml.m4.4xlarge instance type, batch mode | $16.00 |
ml.m5.4xlarge Inference (Batch) | Model inference on the ml.m5.4xlarge instance type, batch mode | $16.00 |
ml.m4.16xlarge Inference (Batch) | Model inference on the ml.m4.16xlarge instance type, batch mode | $16.00 |
ml.m5.2xlarge Inference (Batch) | Model inference on the ml.m5.2xlarge instance type, batch mode | $16.00 |
ml.p3.16xlarge Inference (Batch) | Model inference on the ml.p3.16xlarge instance type, batch mode | $16.00 |
ml.m4.2xlarge Inference (Batch) | Model inference on the ml.m4.2xlarge instance type, batch mode | $16.00 |
ml.c5.2xlarge Inference (Batch) | Model inference on the ml.c5.2xlarge instance type, batch mode | $16.00 |
ml.p3.2xlarge Inference (Batch) | Model inference on the ml.p3.2xlarge instance type, batch mode | $16.00 |
Vendor refund policy
Currently we do not support refunds, but you can cancel your subscription to the service at any time.
Legal
Vendor terms and conditions
Upon subscribing to this product, you must acknowledge and agree to the terms and conditions outlined in the vendor's End User License Agreement (EULA) .
Content disclaimer
Vendors are responsible for their product descriptions and other product content. AWS does not warrant that vendors' product descriptions or other product content are accurate, complete, reliable, current, or error-free.
Delivery details
Amazon SageMaker model
An Amazon SageMaker model package is a pre-trained machine learning model ready to use without additional training. Use the model package to create a model on Amazon SageMaker for real-time inference or batch processing. Amazon SageMaker is a fully managed platform for building, training, and deploying machine learning models at scale.
Deploy the model on Amazon SageMaker AI using the following options:
Version release notes
Bug Fixes and Performance Improvement
Additional details
Inputs
- Summary
Input
Supported content types: application/zip Input format: ‘Input.zip’. Input zip file must contain: • training_data.csv (containing ‘text’ and ‘target’ columns). • model.sav (containing pipeline of pre-processing and classification steps). • testing_data.csv (containing ‘test_instance’ column).
Usage Guidelines: • ‘Input.zip’ must be less than 6 MB. • Explainer has been tested with the following machine learning models: o Logistic regression (scikit-learn version 0.21.x and below) o Naïve Bayes (scikit-learn version 0.21.x and below) o Support Vector Classification (scikit-learn version 0.21.x and below) – Kindly put “probability” parameter = True while calling your constructor during training o Random Forest Classifier (scikit-learn version 0.21.x and below) o Decision Tree Classifier (scikit-learn version 0.21.x and below) o Adaboost (scikit-learn version 0.21.x and below) o Gradient Boosting (scikit-learn version 0.21.x and below) o XgBoost (xgboost version 1.1.1) • Explainer will explain the first instance of your ‘test_instance’ column in testing_data.csv.
Output
Content type: application/zip Output is explainer_results.zip file containing explanations in: • explanation.json file containing predicted class and explanations. • out.png containing explanations.
Invoking endpoint
AWS CLI Command
You can invoke endpoint using AWS CLI:
aws sagemaker-runtime invoke-endpoint --endpoint-name $model_name --body fileb://$file_name --content-type 'application/zip' --region us-east-2 output.zipResources
Sample Notebook : https://tinyurl.com/y3ymryh9 Sample Input :https://tinyurl.com/yxaaf292 Sample Output: https://tinyurl.com/y4z44pj6
- Input MIME type
- application/zip, text/plain, text/csv
See Input Summary
See Input Summary
Resources
Vendor resources
Support
Vendor support
For any assistance reach out to us at:
AWS infrastructure support
AWS Support is a one-on-one, fast-response support channel that is staffed 24x7x365 with experienced and technical support engineers. The service helps customers of all sizes and technical abilities to successfully utilize the products and features provided by Amazon Web Services.
Similar products
Explainable AI solution to extract features which explain deep learning model predictions.
Co-innovated with the AWS Generative AI Innovation Center (GenAIIC) Partner Agent Factory (PAF), Crayon refiNER is a multilingual, agentic entity recognition framework that enhances existing NER systems with large language models and adaptive refinement. It acts as an intelligent reflection layer that automatically identifies, validates, and improves entity extraction across different domains and languages. Using contextual reasoning and web-based validation, Crayon refiNER delivers accurate, explainable, and scalable results. Designed for enterprise NLP workflows, it improves precision, reduces manual effort, and continuously adapts to new data and domains without the need for retraining.
IT Convergence offers professional services designed to meet the exact needs of our customers. We deliver packaged and custom-based solutions to facilitate the creation and deployment of business use cases with documented justifications using Generative AI and related technologies.
FinCense is an end-to-end AML and fraud (FRAML) prevention system powered by explainable AI and federated learning. It brings together onboarding risk assessments, transaction monitoring, screening, alert prioritisation, and investigations, all in one intelligent platform.
Customer reviews
No customer reviews yet
Be the first to review this product . We've partnered with PeerSpot to gather customer feedback. You can share your experience by writing or recording a review, or scheduling a call with a PeerSpot analyst.