Machine Learning Solution

Machine Learning Solution

Model Interpretability

Treasure Mapping

ML Operations

System Control

Model Development

Forecasting & Prediction

MLops as a Service

  1. Enable automated model training/serving
  2. Instantiate model deployment pipelines
  3. Plumb data pipelines to models and serving
  4. Serialization of data pipelines and models for hot swapping and reproducibility
  5. Install and plumb front end analytics platforms

Solution Focus Areas

Model Interpretability

  1. Build a model.
  2. Is my model biased or unfair?
  3. What’s the potential ROI impact? What’s the potential PR impact?
  4. How can we fix the model?
  5. Fix the model.

How Does It Work?

Phase 1: detection

Phase 2: reconciliation

Executive Summary

Solution Modules

Engagements

Solution Engagements

2-5 Day Assessments

3-5 Week PoC

3-6 Month Project

Data assessment focused on business goals and user enablement.
Working data pipeline prototype for data/user subset, from experimentation to deployment.
Working data pipeline, scalable to your organization from experimentation to deployment.

Deliverables may include

  • Report on future state of data tooling and strategy for enabling future vision
  • Report on suggested data and model analysis
  • Exploratory data analysis notebooks and findings

Prerequisites requested

  • Description of data, platform users, stakeholders and timeline
  • Sample data

Customer team members requested

  • Project Manager - business vision
  • Technical Lead - technology goals

Deliverables may include

  • Code, including exploratory data analysis notebooks and findings
  • Employee training on system
  • Future vision to enable all user and data types

Prerequisites requested

  • Access to full data
  • Current architecture access
  • Licenses to new tools

Customer team members requested

  • Technical Lead - technology goals
  • Technical Implementers - build process

Deliverables may include

  • Operational system including models and data pipeline
  • Employee training on system
  • Full secure access to all user types and data

Prerequisites requested

  • Access to full data
  • Current architecture access
  • Licenses to new tools

Customer team members requested

  • Technical Lead - technology goals
  • Technical Implementers - build process

MLops as a Service

  1. Enable automated model training/serving
  2. Instantiate model deployment pipelines
  3. Plumb data pipelines to models and serving
  4. Serialization of data pipelines and models for hot swapping and reproducibility
  5. Install and plumb front end analytics platforms

Solution Focus Areas

  • Data lake
  • DS sandboxes
  • Data pipeline versioning + persistence
  • Model training
  • Model versioning + persistence
  • Model inference + serving
  • Model staleness testing
  • Pipeline and model updating
  • User-in-the-loop model updating
  • Front end analytics and BI

Model Interpretability

  1. Build a model.
  2. Is my model biased or unfair?
  3. What’s the potential ROI impact? What’s the potential PR impact?
  4. How can we fix the model?
  5. Fix the model.

How Does It Work?

Phase 1: detection

  • Is my model biased?
  • Common methods: feature factor analysis, feature correlation, model I/O perturbation, and more
  • We require: input data, output predictions, output groundtruth, and a trained model
  • We can deliver: report on a model’s bias and sensitivity, evaluation of potential magnitude of impact on business, possible strategies for fixing the model bias, a corrected model.

Phase 2: reconciliation

  • How can I fix my model?
  • Common methods: latent space analysis, concept activation vectors, neuron factor analysis, and more
  • We require: input data, output predictions, output groundtruth, and a trained model
  • We can deliver: model’s current interpretability score, a system to perturb model latent space and observe outputs, a strategy for fixing model, a corrected model.
View our Gallery

Included Technologies

Preferred Technologies

Why Our Solution is Different