What is Aito
  • 16 Jul 2020
  • 2 Minutes To Read
  • Print
  • Share
  • Dark
    Light

What is Aito

  • Print
  • Share
  • Dark
    Light

Aito is a database integrated with machine learning functionality - a predictive database. Databases commonly focus on searching and filtering known information, but Aito adds the ability to predict the yet unknown information.

Aito is a relational database in how it is used: data resides in the tables, that have typed columns and there may be relations (links) between columns of the tables. Where data in a traditional database is queried using a query language (such as SQL), Aito is also used with queries. These queries return the predictions, thus we call them predictive queries.

Aito is a machine learning platform in terms of the functionality it provides. The predictive queries return "unknowns", for example, predictions, recommendations, similarities and matching. Or even explanations to statistical relations within your data.

How is Aito different?

Aito covers the entire machine learning workflow in one hosted solution, significantly saving in development and maintenance time and costs.

Workflow step Traditional ML approach Aito approach
Feature engineering User is expected to perform several steps of feature engineering (imputation, feature scaling, one-hot encoding, grouping, standardization, ...) to produce training data suitable for most machine learning algorithms. Aito uses the data in relational database and does feature selection automatically, without user actions needed.
Model construction User needs to choose a fixed prediction target, and then the most suitable algorithm and it's parameters, typically requiring data science knowledge to get right. Aito works fundamentally differently. The model is generated automatically for each predictive query in real-time. Users do not need to know the details of the science behind.
Deployment and hosting After the model is trained, the user wraps it in an API for production use, and deploys it on a server, needing to take care of the scalability and performance as well as maintenance tasks. There are no static and deployed models in Aito, so this step is made completely irrelevant. It's all behind one elegant API, and we take care of the scaling.
Retraining with new data Every new datapoint means that the model needs to be retrained, and deployed again to production. This pipeline needs to be maintained, managed and monitored in order to keep the accuracy high, and all things running fresh. With Aito's predictive database, every new datapoint automatically contributes to next prediction. This happens without any user action.

Using Aito

Aito can be used either directly with the API, or using the Python SDK that makes it easier to perform several actions provided by the API. Regardless of your chosen approach, you will encounter the predictive queries. That is how you get your desired predictions from Aito.

What machine learning problems can Aito solve?

Aito helps you to solve supervised machine learning problems like getting analytics for decision making, making predictions and suggestions, or automate tasks. See examples at the Tutorials section.

Was This Article Helpful?