Abstract
The quality of the natural environment has become one of the primary concerns in present society.
In Canada, we have been asked to take on the ``One Tonne
Challenge'' to reduce personal household emissions by
1 tonne. However, very little has been done to illuminate
the various connections between our household
purchases and the effect they can have on the quality of
our health and environment. Several decision support
systems are available to assist consumers compare alternatives.
However, these systems do little to enhance
the consumer's experience. Correct clustering of consumers
in terms of their product attribute preferences
would enable the construction of personalized user interfaces
thus increase consumer satisfaction when interacting
with the system and increase the chance of
inspiring greener purchasing habits. This paper analyzes
a clustering technique that uses methods from
multivariate statistics, rough set theory, and machine
learning to cluster users in a web-based environmental
decision support system and test the success of the
clustering. Results from our analysis are discussed.
Users
Please
log in to take part in the discussion (add own reviews or comments).