Session Recommendation via Recurrent Neural Networks over Fisher Embedding Vectors

Abstract

Recommendation services bear great importance in e-commerce, shopping, tourism, and social media, as they aid the user in navigating through the items that are most relevant to their needs. In order to build recommender systems, organizations log the item consumption in their user sessions by using different sensors. For instance, Web sites use Web data loggers, museums and shopping centers rely on user in-door positioning systems to register user movement, and Location-Based Social Networks use Global Positioning System for out-door user tracking. Most organizations do not have a detailed history of previous activities or purchases by the user. Hence, in most cases recommenders propose items that are similar to the most recent ones viewed in the current user session. The corresponding task is called session based, and when only the last item is considered, it is referred to as item-to-item recommendation. A natural way of building next-item recommendations relies on item-to-item similarities and item-to-item transitions in the form of "people who viewed this, also viewed" lists. Such methods, however, depend on local information for the given item pairs, which can result in unstable results for items with short transaction history, especially in connection with the cold-start items that recently appeared and had no time yet to accumulate a sufficient number of transactions. In this paper, we give new algorithms by defining a global probabilistic similarity model of all the items based on Random Fields. We give a generative model for the item interactions based on arbitrary distance measures over the items, including explicit, implicit ratings and external metadata to estimate and predict item-to-item transition probabilities. We exploit our new model in two different item similarity algorithms, as well as a feature representation in a recurrent neural network based recommender. Our experiments on various publicly available data sets show that our new model outperforms simple similarity baseline methods and combines well with recent item-to-item and deep learning recommenders under several different performance metrics.

Keywords: fisher information; markov random fields; recommender systems; recurrent neural networks.

Figure 1

Similarity graph of item i with sample items $S=\{i_1,i_2,...,i_N\}$ of distances $\mathrm{dist}(i,i_n)$ from i.

Figure 2

Pairwise similarity graph with sample set $S=\{i_1,i_2,...,i_N\}$ for a pair of items i and j.

Figure 3

Single and multimodal similarity graph with sample set $S=\{i_1,i_2,...,i_N\}$ and $\left|R\right|$ modalities.

Figure 4

Expanded Gru4Rec model for Fisher embedding.

Figure 5

The Kernel Density Estimation function of the item co-occurrence concentrates at infrequent values.

Figure 6

An example of movies from the MovieLens dataset that shows the relations of the movies using the DBpedia knowledge graphs. The black squares show the movie title, the edges are the properties and the white nodes are the property values.

Figure 7

The quality of algorithms FD and FC with Jaccard similarity, as the function of the number of most popular items used as reference in the similarity graphs of Figure 1, Figure 2 and Figure 3 (horizontal axis). The Recall (top) and DCG (bottom) increases as we add more items in the sample set (i.e., list of recommended items).

Figure 8

Linear combination weights for Feedback Jaccard and content based Fisher embedding models.

Figure 9

Performance of the different Gru4Rec based models in case of different item supports.

Figure 10

Recall@20 as the function of item support for the Netflix data set.