A Framework to Predict Consumption Sustainability Levels of Individuals

Innovative Information Systems services have the potential to promote more sustainable behavior. For these so-called Green Information Systems (Green IS) to work well, they should be tailored to individual behavior and attitudes. Although various theoretical models already exist, there is currently...

Full description

Saved in:
Bibliographic Details
Published in:Sustainability 2020-02, Vol.12 (4), p.1423
Main Authors: Moro, Arielle, Holzer, Adrian
Format: Article
Language:English
Subjects:
Behavior
Carbon footprint
Climate change
Emissions
Energy demand
Greenhouse gases
Influence
Information systems
Mobility
Polls & surveys
Prediction models
Residential energy
Sustainability
Sustainable consumption
Thunberg, Greta
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Innovative Information Systems services have the potential to promote more sustainable behavior. For these so-called Green Information Systems (Green IS) to work well, they should be tailored to individual behavior and attitudes. Although various theoretical models already exist, there is currently no technological solution that automatically estimates individual’s current sustainability levels related to their consumption behaviors in various consumption domains (e.g., mobility and housing). The paper aims at addressing this gap and presents the design of GREENPREDICT, a framework that enables to predict these levels based on multiple features, such as demographic, socio-economic, psychological, and factual knowledge about energy information. To do so, the paper presents and evaluates six different classifiers to predict acts of consumption on the Swiss Household Energy Demand Survey (SHEDS) dataset containing survey answers of 2000 representative individuals living in Switzerland. The results highlight that the ensemble prediction models (i.e., random forests and gradient boosting trees) and the multinomial logistic regression model are the most accurate for the mobility and housing prediction tasks.
ISSN:2071-1050
2071-1050
DOI:10.3390/su12041423