<p>Aito is a cloud-based predictive database, that provides predictive queries as an addition to traditional database queries. Aito uses lazy learning approach instead of eager learning approach, which allows it to omit model training and model maintenance. Instead you can query arbitrary predictions, recommendations, matches and statistical relationships and get answers in the query responses. The predictive functionality can be combined with database queries and full text searches to provide e.g. personalized searches.</p> It provides full text search services as addition to predictive queries and the traditional database queries. The database guarantees the basic consistency, atomicity and isolation guarantees from ACID, but there are guarantees of durability because internal & file system buffers. The benefits of the approach compared to the traditional machine learning are described in detail in the following article: [Could predictive database queries replace machine learning models?](


The Aito database was initially developed in Futurice (a Finnish consultation company) by Antti Rauhala. was then spinned off and commercialized as startup by Antti, Vesa Grönfors and Kai Inkinen. Aito was inspired by several observations. One observation was that a specialized database structure could be used to accelerate statistical inference and lazy learning based instant predicting, matching, recommendations and data mining functionality. Another observation was, that combining lazy learning with a database could provide an extreme easy way to do ML via database query like predictive queries. Third observation was, that there were a need in the market for a radically easier and faster way to do machine learning. As such: Aito exists to offer an extremely easy way to do machine learning via predictive database queries. While Aito is a unique as a predictive database, there are lot of similarities between Aito and MIT's probabilistic database: BayesDB. Aito also drew its technical inspiration from Lucene and the query syntax was inspired by the MongoDB. While Aito's early users included Ikea and Comcast, its main application area is currently the intelligent process automation done either with RPA, with low-code or with traditional software integrations. Over the long term: the aim is to expand Aito's DB capabilities and create a system, that can provides both the known like the traditional database and the unknown like an ML system. As such, it would serve both as the primary database and as the primary ML/AI system.

Storage Model

N-ary Storage Model (Row/Record)

At low level: aito uses a log-structured merge-tree that spans the database over low-level database segments. At higher level, the basic datastructure is column oriented, and there are several additional datastructures used for accelerating the statistical inference.



Aito uses specialized bitmap indexes that are optimized for statistical inference

Storage Architecture

Disk-oriented In-Memory

Aito uses extensively memory mapping and as such it has many properties of the in-memory databases. Aito spans a Git inspired immutable object store over the underlying file system. This object store is typed, it contains both the original json data as an addition to the specialized structure to simplify database version updates.

Foreign Keys


Aito provides symbolic links between table, and allows references variables behind links in queries. Joins are not supported, because they are problematic for fast cross-table statistical inference.

Aito Logo

Tech Docs


Aito Intelligence

Country of Origin


Start Year


Project Type


Written in


Inspired By

Elasticsearch, MongoDB

Operating Systems