Reverse Recommendation: without user details
Main Article Content
Abstract
The recommendation is the new and probably the only method to ensure any online
application effectively caters to a global audience. An application that caters to a very wide
group of people from different backgrounds so people can find the data they could be looking
for. We see the use of recommendations almost everywhere in our digital lives. We can look
at recommended apps, posts, dishes, songs, and this list extends till infinity. Personalizing an
application for any specific user helps in achieving better conversion rates. This is achieved
through recommending the user based on the data collected about the user. The more data is
collected, the more precise the recommendation gets, thus resulting in greater conversion
rates. Various machine learning algorithms could be used for creating a recommendation
system based on the type of recommendation required. The recommendation could get better
with the collection of more data and then training the algorithm on the particular dataset.
More precise recommendations could lead to the reverse effect of the recommendation. It
could be used to model the user behavior according to what the developer wants. This could
lead to negative consumer patterns as user now does what the developer wants them to do.
But this does not mean we forbid the idea of recommendation asa whole. A recommendation
is a great tool for achieving more conversion rates. In this paper, the authors propose
recommending using groups. This not only ensures that reverse consumer behavior is
prevented from being achieved, but is also computationally cheaper.
Downloads
Metrics
Article Details
Licensing
TURCOMAT publishes articles under the Creative Commons Attribution 4.0 International License (CC BY 4.0). This licensing allows for any use of the work, provided the original author(s) and source are credited, thereby facilitating the free exchange and use of research for the advancement of knowledge.
Detailed Licensing Terms
Attribution (BY): Users must give appropriate credit, provide a link to the license, and indicate if changes were made. Users may do so in any reasonable manner, but not in any way that suggests the licensor endorses them or their use.
No Additional Restrictions: Users may not apply legal terms or technological measures that legally restrict others from doing anything the license permits.
