EURO 2024 Copenhagen
Abstract Submission

EURO-Online login

2551. SynthEco: A digital system for analyzing multi-dimensional mechanisms of human behaviour in a multi-layered and dynamic geospatial environment

Invited abstract in session MD-28: Advancements of OR-analytics in statistics, machine learning and data science 4, stream Advancements of OR-analytics in statistics, machine learning and data science.

Monday, 14:30-16:00
Room: 065 (building: 208)

Authors (first author is the speaker)

1. Antonia Gieschen
University of Edinburgh
2. Raja Sengupta
McGill University
3. Duo Zhang
McGill University
4. catherine paquet
Marketing, Universite Laval
5. Fares Belkhiria
McGill University
6. Laurette Dubé
McGill University

Abstract

Synthetic populations are datasets which are created to be statistically representative of a chosen population using census data. They have been used in multiple contexts where researchers are interested in modelling effects on a population or individual level, including health related agent-based models and epidemiology. The SynthEco project aims to provide a platform for researchers to create synthetic populations in the form of an open source Python package available on GitHub through an iterative proportional fitting approach. The package allows for synthetic population creation from any census data and on different geographic levels through a simple plug-in system. Plugins exists for census data from the USA and from Canada, and researchers are invited to contribute their own plugins to create other populations. The use of SynthEco will be demonstrated through several application cases in Montreal, Canada, such as modelling access to healthy food and spatial inequality in financial wellbeing. These are made possible through dataset linkage of the synthetic population with geo-referenced discovery and population cohorts.

Keywords

Status: accepted


Back to the list of papers