The predictive database

Traditional databases show what was. The predictive database shows what will be. Sales estimates, demand forecasts, churn predictions, pre-filled forms, and whatever future data points you need.

a company by Futurice

Selected use case

IKEA demand simulator prototype in 5 weeks

Demand simulator prototype allows IKEA’s demand planners to quickly test different hypotheses on how product features (materials, colours etc) will influence the demand of unlaunched articles and why. Using Aito, IKEA had feedback from real users to support their further investment decision.

Aito’s predictive database powered the prototype through SQL-like queries. A fully functional solution was built in only 5 weeks.

ikea demand simulator

Why Aito?

No data science skills needed

We know how hard it is to recruit a good data science team. By using Aito, you only need one developer to get started in the world of AI.

Fast AI iteration

Aito allows you to skip the time-consuming model training phase, unlike traditional AI approaches. You just import your data to Aito and start testing different types of queries to get immediate answers.

Explainable AI

The need for explainable results and decisions made by machines is increasing. Aito not only gives you the answers to your queries, but also shows you the reasoning behind them, making it a valuable business tool.

From idea to solution

Step 1

Upload your data

Upload your data to the Aito predictive database. For this example, we’ve uploaded the public dataset of Kickstarter projects, to predict and understand what contributes to the success of a fundraiser campaign.

Step 2

Query and get immediate results

Whether it's predictions, recommendations, smart search or any other functionality, Aito will return the answers to your queries instantly, allowing fast iteration and experimentation. Here we use the predict query to predict the fundraising success of project in the category of technology.


    "from": "project_status",
    "where": {
      "category": "technology",
      "duration": {"$numeric": 28},
      "goal": {"$numeric": 60000}
    "predict": "reaches_goal"


  "$p": 0.8669790673789294,
  "feature": "success",
  "$why": {
    "factors": [
      {"type": "baseP", "value": 0.5824108373535493},
      {"variable": "goal in [50000.0, 69950.0]", "value": 0.6284269431801215},
      {"variable": "category:technology", "value": 1.5290631512213575},
      {"variable": "duration in [28.0, 28.0]", "value": 1.2528286824463164}

Step 3

Integrate Aito to your product

Changing the parameters instantly influences the prediction result. Queries return in milliseconds, which makes Aito a good fit for real-time interactions. The Aito predictive database can be integrated to make your app, website, or any software smart.


$ curl -X POST \ \
  -H 'content-type: application/json' \
  -d '
    "from": "project_status",
    "where": {
      "category": "technology",
      "duration": {"$numeric": 28},
      "goal": {"$numeric": 60000},


Campaign parameters


Aito prediction

Aito API

We offer an easy API to query your data and get predictions in no time. Once the data is uploaded to Aito, all API endpoints are immediately available. If you have experience with SQL or ElasticSearch you'll feel right at home.


Search and filter objects from tables, similar to select in SQL.
Read more


Predict results based on given scenarios.
Read more


Find recommended objects in a given scenario to maximize KPIs.
Read more


Evaluate statistical inference performance in train/test split.
Read more


Find entries that are similiar to the given sample object.
Read more


Find a suitable pair for a given object. Find objects whose properties are most similar to a given example object.
Read more


Return statistical relationships between different objects or their features.
Read more

Generic query

Expert endpoint that allows inspection of objects' smart properties such as highlight.
Read more

Want to know more techinal details? See our documentation for developers.

Talk to us

Start succeeding in your AI projects. We'll show you how.

Get ready for the predictive database.

Signing up will add your email to the queue to get Aito access, when available. Roll out starts Dec 1st. You can unsubscribe at any time using the link in our emails. Your email is not shared with anyone. For more details, review our privacy policy & terms of service.

Visit us

Kaivokatu 10 A, 8th floor

00100 Helsinki


See map

470 Ramona St.

Palo Alto

CA 94301, USA

See map

Contact info

We'd love to hear from you.

Follow us