Kelvin ML

Kelvin Machine Learning Library

Many law firms and legal departments have realized the potential for applied machine learning (ML) to create substantial value for their clients and impact on their financial performance. However, the labor and infrastructure required to build and deploy ML models is a significant barrier to entry. The Kelvin Legal Data OS is designed to help lower this cost, and the Kelvin ML library is designed seamlessly integrate into Kelvin workflows to make common use cases easier to implement.

Use Cases

Kelvin ML is designed to simplify the following common use cases:

  • Feature Engineering
  • Feature Storage
  • Model Training
  • Model Testing
  • Model Deployment

Library and Framework Integrations

Kelvin ML is designed to integrate not just with the Kelvin Legal Data OS, but also with other common data science and machine learning libraries or frameworks, including the following:

  • pandas
  • scikit-learn
  • PyTorch
  • TensorFlow
  • transformers (Hugging Face)
  • Apache Arrow
  • Apache Spark (Databricks)
  • Dask