Personalized, Sequential, Attentive, Metric-Aware Product Search

The task of personalized product search aims at retrieving a ranked list of products given a user’s input query and his/her purchase history. To address this task, we propose the PSAM model, a Personalized, Sequential, Attentive and Metric-aware (PSAM) model, that learns the semantic representations of three different categories of entities, i.e., users, queries, and products, based on user sequential purchase historical data and the corresponding sequential queries. Specifically, a query-based attentive LSTM (QA-LSTM) model and an attention mechanism are designed to infer users dynamic embeddings, which is able to capture their short-term and long-term preferences. To obtain more fine-grained embeddings of the three categories of entities, a metric-aware objective is deployed in our model to force the inferred embeddings subject to the triangle inequality, which is a more realistic distance measurement for product search. Experiments conducted on four benchmark datasets show that our PSAM model significantly outperforms the state-of-the-art product search baselines in terms of effectiveness by up to 50.9% improvement under NDCG@20. Our visualization experiments further illustrate that the learned product embeddings are able to distinguish different types of products.

Concept of searching for anchor goods based on the study of commodity indices

The article is devoted to the search for anchor goods — goods whose prices are forming for the prices of groups of goods. The role of the desired anchor product is similar to the role of the anchor currency. The identification of such anchors will allow us to understand the pricing structure, which is presumably of a self-affinity nature. The authors believe that there are several options for why a particular product becomes an anchor: historical, cultural or economic. To identify the main requirements for the anchor product, the behavior and dynamics of price changes of goods included in the CRB index were analyzed. Attention to this index is due, firstly, to its complex but significant role in setting exchange rates, and secondly, its role in analyzing world markets. The CRB index is an indicator of trends in the global commodity market. It displays all the movements and changes in the structure of the world commodity market. The characteristic patterns in the behavior of the goods in question are revealed. Typical phase portraits of their relational series for CRB index products have been revealed. The goods included in the CRB index were regrouped according to the similarity of their behavior relative to each other. Four groups were obtained, within each of which phase portraits of relational time series based on a pair of goods have a similar appearance. Reference phase portraits are described. The basic rules of the anchor product search are formulated based on the study of goods included in the selected commodity index. The conceptual proposals for the search for anchor goods using commodity indexes are formulated Based on the proposed approach, some products were investigated and their ability to play the role of an anchor was evaluated.

Gale Literature Criticism

Gale Literature Criticism provides a (potentially) wide selection of literature criticism articles and original interpretive materials appropriate for undergraduates. Its interface is generally friendly and easy to use, but libraries heavily invested in existing Gale content may find the lack of cross-product search integration to be a problem.