Kanva Support Center

Contact Us

We're here to help! Choose your preferred method of contact:

Frequently Asked Questions

Kanva is deployed directly in the customer's infrastructure. This approach ensures data privacy, ownership, and security. Kanva runs entirely locally in your infrastructure, without using any external services or pre-trained models. No data leaves the platform, giving you complete control over your information.
Kanva supports various types of predictive models, including:
  • Forecasting
  • Binary Classification
  • Multiple Classification
  • Regression
These models can be used for a wide range of applications such as predicting customer churn, forecasting sales, predicting risk of incidents, implementing predictive maintenance schemes, and much more.
No, Kanva is designed for domain and subject matter experts who don't necessarily possess coding or data science skills. It combines powerful machine learning models with a user-friendly interface, allowing your domain experts to create and use predictive models without extensive technical knowledge.
Kanva supports various data sources, including:
  • ODBC Databases
  • Web APIs
  • Files (Excel spreadsheets, CSV files, TSV files, parquet files)
  • Cognite Data Fusion
You can start with a free trial of Kanva. This includes:
  • Kanva installed on your infrastructure
  • The ability to create as many predictive models as you want
  • No subscription fee
The trial has a maximum duration of 3 months. After the trial, you can switch to a permanent subscription if Kanva proves valuable for your organization.
Kanva offers robust model interpretability features:
  • For each individual prediction, you get an overview of how much each driver influenced it and in which way.
  • You can identify the most important/predictive drivers at a global level.
These features help you understand the reasoning behind the model's predictions and make informed decisions based on the results.