Difference between revisions of "User:Zeno Gantner"
Jump to navigation
Jump to search
Zeno Gantner (talk | contribs) |
Zeno Gantner (talk | contribs) |
||
| Line 21: | Line 21: | ||
* [[computational advertising]] | * [[computational advertising]] | ||
* <s>[[content-based filtering]]</s> | * <s>[[content-based filtering]]</s> | ||
| − | * [[context]] | + | * <s>[[context]]</s> |
| − | * [[context-aware recommendation]] | + | * <s>[[context-aware recommendation]]</s> |
| − | * [[decision theory]] | + | * [[data analytics]] |
| + | * [[data mining]] | ||
| + | * [[decision theory]] (ask Martijn or Bart) | ||
* [[distributed computing]] | * [[distributed computing]] | ||
* [[distributed matrix factorization]] | * [[distributed matrix factorization]] | ||
| Line 32: | Line 34: | ||
* [[FAQ for recommender system developers]] | * [[FAQ for recommender system developers]] | ||
* [[FAQ for recommender system users]] | * [[FAQ for recommender system users]] | ||
| − | * [[Filter bubble]] | + | * [[Filter bubble]] (ask Alan and Neal) |
* [[Flixster dataset]] | * [[Flixster dataset]] | ||
| − | * [[GraphLab]] | + | * [[GraphLab]] (ask Danny) |
* <s>[[group recommendation]]</s> | * <s>[[group recommendation]]</s> | ||
* [[Harry Potter effect]] | * [[Harry Potter effect]] | ||
| Line 59: | Line 61: | ||
* [[location-aware recommendation]] | * [[location-aware recommendation]] | ||
* [[long tail]] | * [[long tail]] | ||
| − | * [[MAP]] | + | * [[machine learning]] |
| − | * [[Markov chain]] | + | * [[MAP]] (ask Christoph) |
| + | * [[Markov chain]] (ask Christoph) | ||
* [[Markov decision process]], [[MDP]] | * [[Markov decision process]], [[MDP]] | ||
* <s>[[matrix factorization]]</s> | * <s>[[matrix factorization]]</s> | ||
| Line 68: | Line 71: | ||
* [[model]] | * [[model]] | ||
* [[monetization]] | * [[monetization]] | ||
| − | * [[Movie Hack Day]] | + | * [[Movie Hack Day]] (ask Jannis) |
* [[multi-arm bandit]] | * [[multi-arm bandit]] | ||
* [[Music Hack Day]] | * [[Music Hack Day]] | ||
| + | * [[MyMedia]] | ||
* <s>[[NDCG]]</s> | * <s>[[NDCG]]</s> | ||
* [[news recommendation]] | * [[news recommendation]] | ||
* [[overfitting]] | * [[overfitting]] | ||
| − | * [[pairwise interaction tensor factorization]] | + | * [[pairwise interaction tensor factorization]] (ask Steffen) |
* [[parallel factor analysis]] ([[PARAFAC]]), [[canonical decomposition]] | * [[parallel factor analysis]] ([[PARAFAC]]), [[canonical decomposition]] | ||
* [[parameter]] | * [[parameter]] | ||
| Line 82: | Line 86: | ||
* [[personalized search]] | * [[personalized search]] | ||
* [[product recommendation]] | * [[product recommendation]] | ||
| + | * [[public transport]] (ask Neal) | ||
* [[R]] | * [[R]] | ||
* [[ranking]] | * [[ranking]] | ||
| Line 90: | Line 95: | ||
* <s>[[regularization]]</s> | * <s>[[regularization]]</s> | ||
* [[reputation]] | * [[reputation]] | ||
| − | * [[restricted Boltzmann machine]] | + | * [[restricted Boltzmann machine]] (ask Andriy) |
* [[review]] | * [[review]] | ||
* [[scalability]] | * [[scalability]] | ||
Revision as of 11:37, 23 September 2011
Zeno Gantner from University of Hildesheim, Germany.
- homepage
- Twitter: @zenogantner
I am the main developer of the MyMediaLite recommender system library.
We have currently open PhD/PostDoc positions at our lab: Open positions at ISMLL 2011
Article wishlist
- A/B testing
active learning- attribute-aware recommendation
- attribute-based recommendation
- bandit
- BookCrossing
- Category:File format
- CHI
- choice overload
- CofiRank
cold-start problem- computational advertising
content-based filteringcontextcontext-aware recommendation- data analytics
- data mining
- decision theory (ask Martijn or Bart)
- distributed computing
- distributed matrix factorization
- Eigentaste
- Epinions dataset
- exploration vs. exploitation
- factorization models
- FAQ for recommender system developers
- FAQ for recommender system users
- Filter bubble (ask Alan and Neal)
- Flixster dataset
- GraphLab (ask Danny)
group recommendation- Harry Potter effect
- HCI
- higher-order SVD
hybrid recommendation- hyperparameter
- incentive
- information retrieval
- Introduction to recommender systems
- Introduction to recommender system algorithms
- IPTV
- item
- IUI: IUI 2010, IUI 2011, IUI 2012
- Jester
- Joke recommendation
- KDD Cup
- KDD: KDD 2007, KDD 2008, KDD 2009, KDD 2010
- KDD Cup 2010
- keyword-based recommendation
kNN- learning
- learning to rank
- location-aware recommendation
- long tail
- machine learning
- MAP (ask Christoph)
- Markov chain (ask Christoph)
- Markov decision process, MDP
matrix factorization- mean average precision (MAP) - link to [1]
- mean reciprocal rank
- Million Song Dataset
- model
- monetization
- Movie Hack Day (ask Jannis)
- multi-arm bandit
- Music Hack Day
- MyMedia
NDCG- news recommendation
- overfitting
- pairwise interaction tensor factorization (ask Steffen)
- parallel factor analysis (PARAFAC), canonical decomposition
- parameter
Pearson correlation- personalization
- personalized advertising
- personalized search
- product recommendation
- public transport (ask Neal)
- R
- ranking
- recipe recommendation
- recommendation of financial products
recommender system- reinforcement learning
regularization- reputation
- restricted Boltzmann machine (ask Andriy)
- review
- scalability
- serendipity
- similarity
- software as a service
- software recommendation
- SVD
- SVD++, SVDPlusPlus
- TaFeng
- tag
- tag-aware recommendation
- tensor factorization
- text-based recommendation
- text mining
- time-aware recommendation
- Tucker decomposition
- TV program recommendation
- UMAP: UMAP 2010,
UMAP 2011, UMAP 2012 - user
- user-item matrix
- user model
- user recommendation
- user satisfaction
- video recommendation
- web service
- WSDM: WSDM 2010, WSDM 2011, WSDM 2012
Companies
- Amazon
- Commendo
- EBay
- The Echo Nest
- Filmtipset
- Flixster
- Gravity
- Hulu
- Hunch
- Last.fm
- MoviePilot
- Netflix
- Pandora
- RichRelevance
- Scarab Research
- Strands
- TiVo
- Yahoo
RecSys slides, classes, etc.
Personal TODO list
- rename remaining plural categories
- (after some time) remove the old plural categories
