Basket-Sensitive Personalized Item Recommendation

Authors: Duc-Trong Le, Hady W. Lauw, Yuan Fang

IJCAI 2017 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Experiments on three real-life datasets from different domains empirically validate these models against baselines based on matrix factorization and association rules. Through experiments on three real-life datasets from different domains, we conduct an empirical analysis of BFM and CBFM in Section 5, which also includes a comparison to an association rule-based baseline.
Researcher Affiliation Collaboration School of Information Systems, Singapore Management University, Singapore Institute for Infocomm Research, A*STAR, Singapore
Pseudocode No The paper describes models and equations but does not provide a separate pseudocode block or algorithm.
Open Source Code No The paper mentions implementing BFM in Java based on lib FM (footnote 5 links to http://www.libfm.org), but this refers to a third-party tool they used, not their own source code release.
Open Datasets Yes Ta Feng2: This is a retail market dataset...2http://recsyswiki.com/wiki/Grocery_shopping_datasets; Bei Ren3: This comes from a large retailer in China...3http://www.brjt.cn; Foursquare4: This consists of users check-ins at various points of interest in Singapore [Yuan et al., 2013].4http://www.ntu.edu.sg/home/gaocong/datacode.htm
Dataset Splits Yes For each user, we sort her transactions chronologically. The last transaction will be part of the testing set. The second-last transaction will be part of the validation set. The rest will be part of the training set.
Hardware Specification Yes Timing is based on a PC with Intel Core i5 3.2GHz with 8GB RAM.
Software Dependencies No The paper mentions 'Java' and 'lib FM' but does not provide specific version numbers for either, nor for any other software libraries or dependencies used.
Experiment Setup Yes For these experiments, we use latent factor dimension K = 8 and regularization parameter λθ = 0.01, which are also the defaults of lib FM. The initial learning rate η is 0.0001 for Ta Feng, Bei Ren and 0.001 Foursquare respectively to reflect their relative sparsity. We further apply the Bold-Driver adaptive learning rate [Battiti, 1989].