scholarly journals A Survey on Session-based Recommender Systems

2021 ◽  
Vol 54 (7) ◽  
pp. 1-38
Author(s):  
Shoujin Wang ◽  
Longbing Cao ◽  
Yan Wang ◽  
Quan Z. Sheng ◽  
Mehmet A. Orgun ◽  
...  
Keyword(s):  
Recommender Systems ◽  
User Preferences ◽  
Session Length ◽  
New Paradigm ◽  
Problem Statement ◽  
Short Term ◽  
Comprehensive Review ◽  
New Research ◽  
Dynamic User Preferences

Recommender systems (RSs) have been playing an increasingly important role for informed consumption, services, and decision-making in the overloaded information era and digitized economy. In recent years, session-based recommender systems (SBRSs) have emerged as a new paradigm of RSs. Different from other RSs such as content-based RSs and collaborative filtering-based RSs that usually model long-term yet static user preferences, SBRSs aim to capture short-term but dynamic user preferences to provide more timely and accurate recommendations sensitive to the evolution of their session contexts. Although SBRSs have been intensively studied, neither unified problem statements for SBRSs nor in-depth elaboration of SBRS characteristics and challenges are available. It is also unclear to what extent SBRS challenges have been addressed and what the overall research landscape of SBRSs is. This comprehensive review of SBRSs addresses the above aspects by exploring in depth the SBRS entities (e.g., sessions), behaviours (e.g., users’ clicks on items), and their properties (e.g., session length). We propose a general problem statement of SBRSs, summarize the diversified data characteristics and challenges of SBRSs, and define a taxonomy to categorize the representative SBRS research. Finally, we discuss new research opportunities in this exciting and vibrant area.

Are Biopharmaceutical Budget Caps Good Public Policy?

2016 ◽  
Vol 13 (1) ◽  
Author(s):  
Dana P. Goldman ◽  
Darius N. Lakdawalla ◽  
James R. Baumgardner ◽  
Mark T. Linthicum
Keyword(s):  
Cost Savings ◽  
Healthcare Spending ◽  
Short Term ◽  
The Past ◽  
Long Run ◽  
The Status ◽  
Pharmaceutical Spending ◽  
Health Returns ◽  
New Research

AbstractMedical innovation has generated significant gains in health over the past decades, but these advances have been accompanied by rapid growth in healthcare spending. Faced with a growing number of high-cost but high-impact innovations, some have argued to constrain prices for new therapies – especially through global caps on pharmaceutical spending and limits on prices for individual drugs. We show that applying this threshold to past innovations would have limited access to many highly valuable drugs such as statins and anti-retrovirals. We also argue that budget caps violate several important principles of health policy. First, budget caps treat healthcare spending as a consumption good, like going to a movie or buying a meal. However, healthcare spending should be viewed as an investment, whose benefits accrue over many years – much like spending on education. Second, budgetary cost is a poor indicator of value, thereby distorting coverage decisions. Third, affordability arguments often use a short-term horizon, thereby missing that long-term health is society’s ultimate goal. Fourth, assessments of benefit should incorporate not just the immediate clinical benefit to patients, but also long-term health improvements, cost savings, and increased productivity. Fifth, global budget caps arbitrarily anchor spending on the status quo, thereby setting too stringent a threshold for socially-desirable innovation. In sum, a solitary focus on short-term costs can be detrimental to population health in the long-run. When medical treatment decisions are properly viewed as investments, budget caps are not the answer; rather, we need to find mechanisms to encourage spending decisions based on long-term value. Only then can we generate health returns to societal investments, while also encouraging the new research and development necessary to extend the gains of recent decades.

Research on Modeling User’s Preference in the Steel E-Trading Platform

2015 ◽  
Vol 743 ◽  
pp. 687-691
Author(s):  
Ping Wu ◽  
Tao Yu ◽  
J.B. Du ◽  
G.Q. Qu ◽  
Feng Xiong
Keyword(s):  
Recommendation System ◽  
User Preferences ◽  
Cluster Method ◽  
Basic Information ◽  
Short Term

In order to meet the increasing personalized needs of users in the steel trading platform, the intelligent recommendation system has been introduced into the platform. And the users’ interests and preferences-based modeling is the key and foundation of recommendation system, and changes with the change of time. So, in this paper, the user preferences are divided into long-term and short-term firstly, then the users’ basic information vectors and cluster method are used to model users’ long-term interests and preferences, while mining and analyzing users’ operating records in the platform to model users’ the short-term. Finally, the whole interest and preference’s model of user will be built by integrating the two models.

scholarly journals A Unified Approach for Predicting Long- and Short-Term Capability Indices with Dependence on Manufacturing Target Bias

2008 ◽  
Vol 2008 ◽  
pp. 1-10 ◽  
Author(s):  
Nikhil T. Satyala ◽  
R. J. Pieper
Keyword(s):  
Sufficient Conditions ◽  
Unified Approach ◽  
New Paradigm ◽  
Process Mean ◽  
Short Term ◽  
Capability Index ◽  
Capability Indices ◽  
Distributed Process ◽  
Specific Formulation

It is shown that the exact solution for the capability index (CPI) for Gaussian-distributed process with target bias can be expressed in terms of an unbiased CPI and a normalized target bias. The principal advantage of this specific formulation is that it facilitates evaluation of the degradation of the capability of the process due to bias between process mean and the process target. It is shown how this formalism, initially developed for the short-term process, is readily extended to long-term process for which the distribution is Gaussian. Readily isolated in the latter case are the two long-term CPI degrading effects, namely, process instability and target bias. Sufficient conditions to guarantee that long-term processes are distributed as Gaussian are discussed. Within the context of these assumed conditions, a new paradigm for a long-term locator ‘‘k’’ is proposed. For a three sigma process the results indicate that the exact CPI model is a less pessimistic predictor than both of the industry CPI models tested.

scholarly journals Anxiety and Depression in Patients Hospitalized With Chronic Kidney Disease in Barranquilla Clinics, Colombia

2018 ◽  
Vol 10 (11) ◽  
pp. 144
Author(s):  
Carmen A. Sierra Llamas ◽  
Rafael E. Donado Castillo ◽  
Gustavo Aroca ◽  
Santos Ángel Depine ◽  
Gladys Gaviria ◽  
...  
Keyword(s):  
Chronic Kidney Disease ◽  
Kidney Disease ◽  
Population Group ◽  
Anxiety And Depression ◽  
Depression And Anxiety ◽  
Short Term ◽  
The Individual ◽  
New Research ◽  
The City

The purpose of this study is to determine the levels of anxiety and depression in patients aged between 18 and 70 years, hospitalized with chronic kidney disease in a clinic entity of the city of Barranquilla. The type of research is descriptive, presenting the information through the indicators and statistical tables, the Hospital Scale of Anxiety and Depression of, Zigmond & Smith (1983), which evaluates the detection of depressive and anxious disorders in the non-psychiatric hospital context. The application of the Scale was performed in the hospital entity of the city of Barranquilla to 50 patients with Chronic Kidney Disease. The results they are beneficial in the short term, because they create new research proposals applied to another population group diagnosed with chronic diseases, especially for the evaluation and intervention in the area of health psychology. In the long term, new theories, methods of intervention and evaluation applied to the population of patients with chronic kidney disease will be studied. In the same way, the results show marked trends related to depression, an aspect that is consistent with the deterioration that affects the individual in the course of the disease and also show a positive correlation of the study variables, depression and anxiety disorders in patients with CKD can be due to a symptomatology or consequence of psychological burnout.

scholarly journals Where to Go Next: Modeling Long- and Short-Term User Preferences for Point-of-Interest Recommendation

2020 ◽  
Vol 34 (01) ◽  
pp. 214-221 ◽  
Author(s):  
Ke Sun ◽  
Tieyun Qian ◽  
Tong Chen ◽  
Yile Liang ◽  
Quoc Viet Hung Nguyen ◽  
...  
Keyword(s):  
State Of The Art ◽  
User Preferences ◽  
Short Term ◽  
Preference Modeling ◽  
Point Of Interest ◽  
Proposed Model ◽  
Poi Recommendation ◽  
Novel Method ◽  
Real World Datasets

Point-of-Interest (POI) recommendation has been a trending research topic as it generates personalized suggestions on facilities for users from a large number of candidate venues. Since users' check-in records can be viewed as a long sequence, methods based on recurrent neural networks (RNNs) have recently shown promising applicability for this task. However, existing RNN-based methods either neglect users' long-term preferences or overlook the geographical relations among recently visited POIs when modeling users' short-term preferences, thus making the recommendation results unreliable. To address the above limitations, we propose a novel method named Long- and Short-Term Preference Modeling (LSTPM) for next-POI recommendation. In particular, the proposed model consists of a nonlocal network for long-term preference modeling and a geo-dilated RNN for short-term preference learning. Extensive experiments on two real-world datasets demonstrate that our model yields significant improvements over the state-of-the-art methods.

On the Importance of Subtext in Recommender Systems

i-com ◽  
2015 ◽  
Vol 14 (1) ◽  
pp. 41-52 ◽  
Author(s):  
Peter Grasch ◽  
Alexander Felfernig
Keyword(s):  
Empirical Study ◽  
Recommender Systems ◽  
Recommender System ◽  
Unsolved Problem ◽  
Preference Elicitation ◽  
User Preferences ◽  
Session Length ◽  
Knowledge Based ◽  
Paralinguistic Information ◽  
Recommendation Strategy

AbstractConversational recommender systems have been shown capable of allowing users to navigate even complex and unknown application domains effectively. However, optimizing preference elicitation remains a largely unsolved problem. In this paper we introduce SPEECHREC, a speech-enabled, knowledge-based recommender system, that engages the user in a natural-language dialog, identifying not only purely factual constraints from the users’ input, but also integrating nuanced lexical qualifiers and paralinguistic information into the recommendation strategy. In order to assess the viability of this concept, we present the results of an empirical study where we compare SPEECHREC to a traditional knowledge-based recommender system and show how incorporating more granular user preferences in the recommendation strategy can increase recommendation quality, while reducing median session length by 46 %.

scholarly journals An Attention-Based Recommender System to Predict Contextual Intent Based on Choice Histories across and within Sessions

2018 ◽  
Vol 8 (12) ◽  
pp. 2426 ◽  
Author(s):  
Ruo Huang ◽  
Shelby McIntyre ◽  
Meina Song ◽  
Haihong E ◽  
Zhonghong Ou
Keyword(s):  
Recommender Systems ◽  
State Of The Art ◽  
User Profile ◽  
Vital Role ◽  
Short Term ◽  
Novel Approach ◽  
Learning Techniques ◽  
Real World Datasets ◽  
Near Future

Recent years have witnessed the growth of recommender systems, with the help of deep learning techniques. Recurrent Neural Networks (RNNs) play an increasingly vital role in various session-based recommender systems, since they use the user’s sequential history to build a comprehensive user profile, which helps improve the recommendation. However, a problem arises regarding how to be aware of the variation in the user’s contextual preference, especially the short-term intent in the near future, and make the best use of it to produce a precise recommendation at the start of a session. We propose a novel approach named Attention-based Short-term and Long-term Model (ASLM), to improve the next-item recommendation, by using an attention-based RNNs integrating both the user’s short-term intent and the long-term preference at the same time with a two-layer network. The experimental study on three real-world datasets and two sub-datasets demonstrates that, compared with other state-of-the-art methods, the proposed approach can significantly improve the next-item recommendation, especially at the start of sessions. As a result, our proposed approach is capable of coping with the cold-start problem at the beginning of each session.

scholarly journals 2P-AGRCFN: Two Phase Attention Gated Recurrent Context Filtering Network for Sequential Recommender Systems

2019 ◽  
Vol 9 (1) ◽  
pp. 3693-3700
Keyword(s):  
Recommender Systems ◽  
Second Phase ◽  
Short Term ◽  
Time Step ◽  
Two Phase ◽  
Current Time ◽  
Sequence Modeling ◽  
Term Dependency ◽  
Hidden States

The recent trends in recommender systems have focused on modeling long-term tastes as well as short-term preferences. The various recurrent architectures have used for sequence modeling in recommender systems, since each state is a combination of current and previous layer output recurrently. Although the Recurrent Neural Networks (RNNs) have the ability for modeling both long-term and short-term dependency to some extent, the monotonic nature of temporal dependency of RNN reduces the effect of short-term interests of the user. Thus final interests of the users can’t be predicted from the hidden states. We propose a Two Phase- Attention Gated Recurrent Context Filtering Network (2P-AGRCF) for dealing with user’s long-term dependency as well as short-term preferences. The first phase of 2P-AGRCFN is performed in the input level by constructing a contextual input using certain number of recent input contexts for handling user’s short-term interests. This can handle the correlation among recent inputs and leads to strong hidden states. In the second phase, the contextual-hidden state is computed by fusing the attention mechanism and the hidden state at current time step, which leads to the effective modeling of overall interest of the user on recommendation. We experiment our model with YooChoose DataSet and it shows efficacy in generating personalized as well as ranked recommendations.

scholarly journals Generating Personalized Web Search Using Semantic Context

2015 ◽  
Vol 2015 ◽  
pp. 1-10 ◽  
Author(s):  
Zheng Xu ◽  
Hai-Yan Chen ◽  
Jie Yu
Keyword(s):  
Information Needs ◽  
Web Search ◽  
User Profile ◽  
User Preferences ◽  
Short Term ◽  
Personalized Search ◽  
User Session ◽  
User Context ◽  
The One

The “one size fits the all” criticism of search engines is that when queries are submitted, the same results are returned to different users. In order to solve this problem, personalized search is proposed, since it can provide different search results based upon the preferences of users. However, existing methods concentrate more on the long-term and independent user profile, and thus reduce the effectiveness of personalized search. In this paper, the method captures the user context to provide accurate preferences of users for effectively personalized search. First, the short-term query context is generated to identify related concepts of the query. Second, the user context is generated based on the click through data of users. Finally, a forgetting factor is introduced to merge the independent user context in a user session, which maintains the evolution of user preferences. Experimental results fully confirm that our approach can successfully represent user context according to individual user information needs.

Sign in / Sign up

Export Citation Format

Share Document