Abstract
Typical supervised classification techniques require training instances similar to the values that need to be classified. This research proposes a methodology that can utilize training instances found in a different format. The benefit of this approach is that it allows the use of traditional classification techniques, without the need to hand-tag training instances if the information exists in other data sources. The proposed approach is presented through a practical classification application. The evaluation results show that the approach is viable, and that the segmentation of classifiers can greatly improve accuracy.
Highlights
This research proposes a novel ensemble classification methodology
The novelty of the method lies in the ability to train the classifiers with data that are in a different format from the values that they later classify
All available products were retrieved from each web site4
Summary
This research proposes a novel ensemble classification methodology. The proposed methodology is presented through a practical application, which serves as a consistent example and an evaluation framework. This work is part of a research project that proposes a market-independent recommender system, focusing on identifying only a handful of products to serve as final recommendations. The aforementioned recommender system needs to gather information about user needs and connect them to product attributes. For example relate “every day use of a camera”, to a sufficient amount of “Megapixels”. As this analysis is not done for every attribute, the need arises to realize which attributes have an important role in the decision making.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
More From: Journal of Intelligent Learning Systems and Applications
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.