Difference between revisions of "Cold-Start Problem"
Jump to navigation
Jump to search
Zeno Gantner (talk | contribs) |
Zeno Gantner (talk | contribs) |
||
| Line 1: | Line 1: | ||
| − | '''Cold-start problems''' occur when past data is scarce, e.g. after the initial start of a system, or if a new [[user]] or [[item]] is added to the system. | + | '''Cold-start problems''' occur when past data is scarce, e.g. after the initial start of a [[recommender system]], or if a new [[user]] or [[item]] is added to the system. |
Pure [[collaborative filtering]] methods are not able to come up with good predictions in such scenarios. | Pure [[collaborative filtering]] methods are not able to come up with good predictions in such scenarios. | ||
| − | [[Wikipedia: Cold start]] | + | == External links == |
| + | * [[Wikipedia: Cold start]] | ||
| + | |||
| + | |||
| + | [[Category: Task]] | ||
Revision as of 09:55, 26 September 2011
Cold-start problems occur when past data is scarce, e.g. after the initial start of a recommender system, or if a new user or item is added to the system. Pure collaborative filtering methods are not able to come up with good predictions in such scenarios.
