2020-10-09

AIRE – AI for Real Estate

Abiro was involved in a Vinnova-funded project called AIRE – AI for Real Estate during September 2019 to September 2020.

The main goal was to get educated in machine learning and a suitable development environment.

Prediction of energy consumption in real estate was chosen as the use case, as such data is readily available via APIs.

Anaconda, that is a development platform for Python, was chosen as the most practical development environment. Eventually Visual Studio Code was used instead of the editor in Anaconda.

During the project several APIs for energy data and weather data were investigated practically, including Metry, E.ON, OpenWeather, SMHI and Trafikverket.

Several spin-off projects are considered for the future based on the outcomes.

Abiro Energy Prophet

The main outcome of the project was a tool for predicting energy consumption in real estate.

It’s developed in Python and using Facebook Prophet for training and prediction, as well as Flask and Wtforms to create a web application.

Experiments

A separate site developed in PHP was set up to experiment with energy data, weather data and machine learning.

More information