1,721,292 research outputs found
Recommender method and system, in particular for IPTV
No full textRecommender method and system, in particular for IPT
NFC: a Deep and Hybrid Item-based Model for Item Cold-start Recommendation
Full text linkNew items, also called cold-start items, are introduced every day in the catalogs of numerous online systems. Due to the absence of previous preferences, recommending these items is difficult but important task for a recommender system. For this reason, the item cold-start recommendation problem still represents an interesting research topic for the community. In this work, we propose Neural Feature Combiner (NFC), a novel deep learning, item-based approach for cold-start item recommendation. The model learns to map the content features of the items into a low-dimensional hybrid embedding space. The features that compose the embeddings are then combined in order to reproduce collaborative item similarity values. We compare NFC with three variants of the same model that learn from user feedback, showing the advantages of learning from similarities in terms of accuracy and convergence time. With an extensive set of experiments on four datasets, we show that NFC outperforms several cutting edge approaches in the top-n recommendation task of cold-start items. Results in extremely cold (i.e., with a very low amount of interactions for training) and cold-warm hybrid scenarios prove that NFC effectively exploits collaborative information, leading to state-of-the-art accuracy. We finally conduct a qualitative analysis of the embeddings generated by different models, and we provide an analysis of the importance that different models assign to the input features, empirically demonstrating the robustness of the hybrid representations produced by our new model
Automated service time estimation method for IT system resources
No full textA automated method for upgrading and/or allocating resources in an IT system for a non-capacity planner (a person unskilled in capacity planning) along with a visual mining technique to aid a capacity planner track down performance degradations is disclosed. The method comprises the steps of collecting a dataset by sampling utilization versus workload of a resource in the IT system and then analyzing said dataset to obtain service time through a new clusterwise regression procedure with a refinement procedure which identifies the (i) cluster memberships, (2) the number of clusters (3) outliers where, said service time being used to trigger the upgrade or allocation of said resources, followed by a visual mining technique to bring out the relationship between the cluster membership and the time stamp Ieading to the identification of sporadic configuration changes which extend over a well defined time frame and the ones composed of isolated recurring observations caused due to scheduled activites.characterized in that the method comprises the following steps divided in two main phases: Phase I : (i) normalize collected dataset, (it) scatter data when utilization has been rounded, (iii) provide for partition of data to find density based dusters through DBSCAIM procedure, (Iv) discard clusters with less than the z% of the total number of observations, (v) in each cluster, perform clusterwise regression and obtain linear sub-dusters in a pre-defined number, (vi) reduce sub-clusters applying refinement procedure, removing sub- dusters that fit to outliers and merging pairs of clusters that fit the same model, (vi) update clusters with the reduced sub-clusters, (vii) remove globular clusters, (viii) reduce number of clusters with refinement procedure, and (ix) de-normalize results. Phase II : Visual minining (i) calculate the silhouette value for each point to measure the strength of point to cluster membership (Si) choose value of threshold (Hi) output the charts - Silhouette-Time Chart, Cardinality-Time Chart, Parameter-Time Chart, Hour of day Chart, Day of week Chart and Timetable Chart for indentifying the bottlenecks
- …
