2
votes
Accepted
How does amazon's reviews that mention extracts topics from reviews?
One possible approach I can see is as follows:
Amazon considers (until now and based on its historic data, and checked every X time) a possible number of frequent categories (i.e. labels in a ...
1
vote
Accepted
What approach should I take for my product classification ML model with user feedback for improving result accuracy?
This could be framed, as a first approximation, as a supervised learning classifier, where, based on the input texts (both name and description), you can build a series of features to build your ...
Only top scored, non community-wiki answers of a minimum length are eligible
Related Tags
real-ml-usecase × 5machine-learning × 2
nlp × 2
regression × 1
linear-regression × 1
reinforcement-learning × 1
preprocessing × 1
prediction × 1
image-preprocessing × 1
text × 1
topic-model × 1
pvalue × 1