New answers tagged recommender-system
0
votes
In-batch Random Negative Sampling
In the paper you mentioned, the authors are using In-batch Random Negative Sampling (IRNS) for training a recommendation model. IRNS is a technique for training recommender models using negative ...
- 2,981
0
votes
In-batch Random Negative Sampling
The authors mean that in each batch, there are 600 pairs, where each pair consists of one positive example (selected randomly from the set of positive examples) and 3000 negative examples (selected ...
1
vote
In-batch Random Negative Sampling
From your words, I guess the authors mean that each sample is formed by 3000 negatives and 1 positive, and so each batch is formed by 600(3000+1) examples.
Indeed, the authors write that positive ...
- 122
0
votes
Accepted
Evaluate a Recommender System based on the data between two months
Because tool A and B might result in recommendations with different numbers of items, using ratio is more suitable than the actual score.
calculate hit ratio for each one
eg. hit ratio = 1 * ( ...
- 26
Top 50 recent answers are included
Related Tags
recommender-system × 478machine-learning × 192
python × 62
data-mining × 32
deep-learning × 31
similarity × 29
predictive-modeling × 28
matrix-factorisation × 25
neural-network × 23
dataset × 21
clustering × 20
evaluation × 20
classification × 18
nlp × 17
information-retrieval × 17
cosine-distance × 17
apache-spark × 15
scikit-learn × 14
algorithms × 13
ranking × 13
statistics × 12
data-science-model × 12
k-nn × 10
machine-learning-model × 9
text-mining × 9