GitHub - jaderberg/NewsRank: Optimising links displayed based on metrics learnt over time.

jaderberg / NewsRank Public

Notifications You must be signed in to change notification settings
Fork 0
Star 1

Optimising links displayed based on metrics learnt over time.

Notifications

Name		Name	Last commit message	Last commit date
Latest commit History 2 Commits
README		README
addNewArticleToSet.m		addNewArticleToSet.m
articleClicked.m		articleClicked.m
getNewsRank.m		getNewsRank.m
newsRank.m		newsRank.m
normalize.m		normalize.m
normalizeArticle.m		normalizeArticle.m
normalizeSet.m		normalizeSet.m
updateArticleMetric.m		updateArticleMetric.m
updateArticleRank.m		updateArticleRank.m
updateSetRanks.m		updateSetRanks.m

Repository files navigation

NewsRank ranks articles (or any object) based on a set of metrics.

Each metric has an associated weight which are initialised in newsRank.m. 
The metric weights are learnt over time - articles clicked are assumed to have desired  metrics.

newsRank() will return you an article set. Use the update... functions to add articles, change metrics and simulate selecting an article.

TODO: Implement in Python.

Copyright 2011 Max Jaderberg