Give your ML Pipelines a Boost with Custom Feature Engineering in Cortex
Vidora Cortex is the first and only Machine Learning platform which automates the entire Machine Learning (ML) Pipeline from start to finish, including feature cleaning and feature engineering. Cortex does the heavy lifting, but now anyone can augment Cortex with their intuitions around specific Machine Learning problems.
Custom Feature Engineering, Vidora’s latest release, allows you to transfer your business knowledge directly into Cortex using a simple UI. In just a few clicks, you can define a custom feature, add it to any ML pipeline, and quickly gauge its predictive value. We’re giving you more control over ML pipelines so that you can tailor them to solve your organization’s most pressing problems.
Augment the Machine Learning Pipeline
Feature engineering is arguably the most critical component of the ML Pipeline (here is a past blog post we wrote on feature engineering). It’s also the most domain-specific – building predictive features can require knowledge of your underlying business problem.
At Vidora, we’ve taken huge strides to automatically identify and build predictive features for each ML Pipeline. Typically Vidora automatically generates upwards of 200 unique features for each pipeline. Now our partners can augment those automated features with custom features based on intuitions of their business and ML problem. All of this can be done in a simple, intuitive UI accessible to anyone in your organization.
How does it work?
Creating a custom feature in Cortex is optional – Cortex will always automatically search for predictive features for your pipeline. But if you’d like to inject your intuition into this process, Custom Feature Engineering gives anyone the ability to:
- Create a custom feature by writing simple SQL statements on data ingested across multiple sources.
- Manage all custom features in a simple list.
- Easily add custom features to new pipeline with one click.
- Quickly gauge the effectiveness of custom features through Understandable ML. Also, edit your features to iterate and find the best ones for each problem.
What sort of features can I build?
You know your business best. With Custom Feature Engineering, you have the tools to create any feature that your intuition says may be predictive of the problem you’re looking to solve.
For example, say you’re know from experience that users who are highly active on your site in the mornings are more likely to come back day after day. When you create a retention pipeline, you might apply a custom feature which measures the percent of each user’s total activity that occurs in the morning.
You can build any feature in this way – if you can describe in your raw data using SQL, you can create it in Cortex!
Want to learn more about how custom features can give your business a boost? Give us a shout at firstname.lastname@example.org to set up a demo!