A Framework to Predict Consumption Sustainability Levels of Individuals
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.
Moro, A.; Holzer, A. A Framework to Predict Consumption Sustainability Levels of Individuals. Sustainability 2020, 12, 1423.
Moro A, Holzer A. A Framework to Predict Consumption Sustainability Levels of Individuals. Sustainability. 2020; 12(4):1423.Chicago/Turabian Style
Moro, Arielle; Holzer, Adrian. 2020. "A Framework to Predict Consumption Sustainability Levels of Individuals." Sustainability 12, no. 4: 1423.