Kortical

Score10 out of 10

1 Reviews and Ratings

What is Kortical?

Kortical is an end to end AI as a Service (AIaaS) platform designed to accelerate the creation, iteration, explanation and deployment of world-class machine learning models. The vendor describes the key benefits of Kortical is AutoML that writes custom machine learning solutions from the ground up in code. Getting hands-on with the code is optional but being able to edit code it makes it easy to get the best of data scientists and AutoML, while also getting the benefits of full explainability and mission-critical, enterprise-grade deployment.

Categories & Use Cases

Machine Learning

Media

Screenshot of Lab Screen is the main screen where you upload your data, select the target column and then hit start training for the AutoML to turn your data into machine learning data, automatically build features and then generate the code on the screen (which you can edit if you wish) and leave it to train to find you the best model based on your data.

Screenshot of The graphs show you how many iterations Kortical has gone through to find you the best model.

Screenshot of You can explore any model in more detail.

Screenshot of You get high level explanations for each model

Screenshot of Also row by row explanations - here is a passenger that is highly likely to survive the titanic, due to being female, first class cabinet and high fare but her age at 35 was counting against her surviving a little and you can get these for every row and future prediction.

1 / 5

Screenshot of Lab Screen is the main screen where you upload your data, select the target column and then hit start training for the AutoML to turn your data into machine learning data, automatically build features and then generate the code on the screen (which you can edit if you wish) and leave it to train to find you the best model based on your data.

Verified User

C-Level Executive in Corporate (1-10 employees employees)

Pros

The NLP models results were much better than the ones that we did outside of the platform.
It is really easy and quick to build a good model with a lot of the manual boring tasks all done automatically like one hot encoding, etc.
Kortical shows the features and their importance for any model type as part of the platform which is great for understanding the models.

Cons

It would be ideal to have Jupyter built into the platform, they say it is coming.
Also while it is easy to use, at the start it would have been helpful to have more help guides.

Return on Investment

ROI is great as what we would spend on compute we get the AutoML for essentially the same price so it is cost neutral as Kortical comes with compute built-in.
The results mean that we can automate so much more than our previous model so that is key to the positive ROI.
The platform auto trains new models and lets us know when there is a better model so it has saved a lot of time so we can focus on new business problems to solve with ML.