scholarly journals Group recommendation method combining short-term interest and long-term preference

2021 ◽  
Vol 2132 (1) ◽  
pp. 012004
Author(s):  
Hangyu Zhu ◽  
Maoting Gao
Keyword(s):  
Collaborative Filtering ◽  
Attention Mechanism ◽  
Group Recommendation ◽  
Short Term ◽  
Traditional Group ◽  
Outer Product ◽  
Data Set ◽  
Fusion Strategy ◽  
Group Fusion

Abstract Based on self-attention and outer product-based neural collaborative filtering,this paper proposed a SLAR model.The model uses the recent interaction information of each user in the group and self-attention mechanism to obtain the short-term interest vector of the group.The attention mechanism and self-attention mechanism are used to calculate the influence of each user and the influence between members during the interaction between the target group and item, so as to aggregate them into the long-term preference vector of the group, and then the sum of short-term interest and long-term preference is input into ONCF model as the embedding vector of the group to mine the interaction between the group and the project from the data, and finally complete the group recommendation. Compared with the traditional group fusion strategy on CAMR2011 data set, the experimental results show that SLGR model achieves better results.

scholarly journals Investigating the Broken-Heart Effect: a Model for Short-Term Dependence between the Remaining Lifetimes of Joint Lives

2012 ◽  
Vol 7 (2) ◽  
pp. 236-257 ◽  
Author(s):  
Jaap Spreeuw ◽  
Iqbal Owadally
Keyword(s):  
Mortality Rates ◽  
Short Term ◽  
Numerical Work ◽  
Data Set ◽  
Multiple State ◽  
Multiple State Model ◽  
Insurance Data ◽  
Over Time ◽  
Assurance Contracts

AbstractWe analyze the mortality of couples by fitting a multiple state model to a large insurance data set. We find evidence that mortality rates increase after the death of a partner and, in addition, that this phenomenon diminishes over time. This is popularly known as a “broken-heart” effect and we find that it affects widowers more than widows. Remaining lifetimes of joint lives therefore exhibit short-term dependence. We carry out numerical work involving the pricing and valuation of typical contingent assurance contracts and of a joint life and survivor annuity. If insurers ignore dependence, or mis-specify it as long-term dependence, then significant mis-pricing and inappropriate provisioning can result. Detailed numerical results are presented.

scholarly journals Effects of agricultural credit on wheat productivity of small farms in Sindh, Pakistan

2018 ◽  
Vol 78 (5) ◽  
pp. 592-610 ◽  
Author(s):  
Abbas Ali Chandio ◽  
Yuansheng Jiang ◽  
Feng Wei ◽  
Xu Guangshun
Keyword(s):  
Wheat Yield ◽  
Considerable Proportion ◽  
Small Scale ◽  
Small Farms ◽  
Short Term ◽  
Agricultural Credit ◽  
Data Set ◽  
Content Type ◽  
The Impact

Purpose The purpose of this paper is to evaluate the impact of short-term loan (STL) vs long-term loan (LTL) on wheat productivity of small farms in Sindh, Pakistan. Design/methodology/approach The econometric estimation is based on cross-sectional data collected in 2016 from 18 villages in three districts, i.e. Shikarpur, Sukkur and Shaheed Benazirabad, Sindh, Pakistan. The sample data set consist of 180 wheat farmers. The collected data were analyzed through different econometric techniques like Cobb–Douglas production function and Instrumental variables (two-stage least squares) approach. Findings This study reconfirmed that agricultural credit has a positive and highly significant effect on wheat productivity, while the short-term loan has a stronger effect on wheat productivity than the long-term loan. The reasons behind the phenomenon may be the significantly higher usage of agricultural inputs like seeds of improved variety and fertilizers which can be transformed into the wheat yield in the same year. However, the LTL users have significantly higher investments in land preparation, irrigation and plant protection, which may lead to higher wheat production in the coming years. Research limitations/implications In the present study, only those wheat farmers were considered who obtained agricultural loans from formal financial institutions like Zarai Taraqiati Bank Limited and Khushhali Bank. However, in the rural areas of Sindh, Pakistan, a considerable proportion of small-scale farmers take credit from informal financial channels. Therefore future researchers should consider the informal credits as well. Originality/value This is the first paper to examine the effects of agricultural credit on wheat productivity of small farms in Sindh, Pakistan. This paper will be an important addition to the emerging literature regarding effects of credit studies.

How loan interest rate liberalization affects firms’ loan maturity structure

2014 ◽  
Vol 4 (2) ◽  
pp. 153-167 ◽  
Author(s):  
Jianfang Zhou ◽  
Jingjing Wang ◽  
Jianping Ding
Keyword(s):  
Interest Rate ◽  
Interest Rates ◽  
Manufacturing Companies ◽  
Short Term ◽  
Data Set ◽  
Content Type ◽  
Interest Rate Liberalization ◽  
Upper Limit ◽  
Maturity Structure

Purpose – After loan interest rate upper limit deregulation in October 2004, the financing environment in China changed dramatically, and the banks were eligible for risk compensation. The purpose of this paper is to focus on the influence of the loan interest rate liberalization on firms’ loan maturity structure. Design/methodology/approach – Based on Rajan's (1992) model, the authors constructed a trade-off model of how the banks choose long-term and short-term loans scales, and further analyzed banks’ loan term decisions under the loan interest rate upper limit deregulation or collateral cases. Then the authors used an unbalanced panel data set of 586 Chinese listed manufacturing companies and 9,376 observations during the period 1996-2011 to testify the theoretical conclusion. Furthermore, the authors studied the effect on firms with different characteristics of ownership or scale. Findings – The results show that the loan interest rate liberalization significantly decreases the private companies’ reliance on short-term loans and increases sensitivity to interest rates of state-owned companies’ long-term loans. But the results also show that the companies’ ownership still plays a key role on the long-term loans availability. When monetary policy tightened, small companies still have to borrow short-term loans for long-term purposes. As the bank industry is still dominated by state-owned banks and the deposit interest rate has upper limits, the effect of the loan interest rate liberalization on easing long-term credit constraints is limited. Originality/value – From a new perspective, the content and findings of this paper contribute to the study of the effect of the interest rate liberalization on China economy.

scholarly journals An LSTM-Based Method with Attention Mechanism for Travel Time Prediction

Sensors ◽  
2019 ◽  
Vol 19 (4) ◽  
pp. 861 ◽  
Author(s):  
Xiangdong Ran ◽  
Zhiguang Shan ◽  
Yufei Fang ◽  
Chuang Lin
Keyword(s):  
Short Term Memory ◽  
Attention Mechanism ◽  
Traffic Prediction ◽  
Travel Time Prediction ◽  
Short Term ◽  
Term Memory ◽  
Proposed Model ◽  
Departure Time ◽  
Long Short Term Memory

Traffic prediction is based on modeling the complex non-linear spatiotemporal traffic dynamics in road network. In recent years, Long Short-Term Memory has been applied to traffic prediction, achieving better performance. The existing Long Short-Term Memory methods for traffic prediction have two drawbacks: they do not use the departure time through the links for traffic prediction, and the way of modeling long-term dependence in time series is not direct in terms of traffic prediction. Attention mechanism is implemented by constructing a neural network according to its task and has recently demonstrated success in a wide range of tasks. In this paper, we propose an Long Short-Term Memory-based method with attention mechanism for travel time prediction. We present the proposed model in a tree structure. The proposed model substitutes a tree structure with attention mechanism for the unfold way of standard Long Short-Term Memory to construct the depth of Long Short-Term Memory and modeling long-term dependence. The attention mechanism is over the output layer of each Long Short-Term Memory unit. The departure time is used as the aspect of the attention mechanism and the attention mechanism integrates departure time into the proposed model. We use AdaGrad method for training the proposed model. Based on the datasets provided by Highways England, the experimental results show that the proposed model can achieve better accuracy than the Long Short-Term Memory and other baseline methods. The case study suggests that the departure time is effectively employed by using attention mechanism.

Methodology of Creep Data Analysis for Advanced High Cr Ferritic Steel

2007 ◽  
Author(s):  
Kouichi Maruyama ◽  
Kyosuke Yoshimi
Keyword(s):  
Data Analysis ◽  
Rupture Life ◽  
Creep Rupture ◽  
Creep Data ◽  
Short Term ◽  
Data Set ◽  
Region Analysis ◽  
Rupture Data ◽  
Term Creep

Long term creep rupture life is usually evaluated from short term data by a time-temperature parameter (TTP) method. The apparent activation energy Q for rupture life of steels sometimes changes from a high value of short term creep to a low value of long term creep. However, the conventional TTP analyses ignore the decrease in Q, resulting in the overestimation of rupture life recognized recently in advanced high Cr ferritic steels. A multi region analysis of creep rupture data is applied to a creep data set of Gr.122 steel; in the analysis a creep rupture data is divided into several data sets so that Q value is unique in each divided data set. The multi region analysis provides the best fit to the data and the lowest value of 105 h creep rupture strength among the three ways of data analysis examined. The conventional single region analysis cannot correctly represent the data points and predicts the highest strength. A half of 0.2% proof stress could not be an appropriate boundary for dividing data to be used in the multi region analysis. In the 2001 Edition of ASME Code an F average concept has been proposed as a substitution for the safety factor of 2/3 for average rupture stress. The allowable stress of Gr.122 steel may decrease significantly when the F average concept and the multi region analysis are adopted.

scholarly journals Re-analysis of ground-based microwave ClO measurements from Mauna Kea, 1992 to early 2012

2013 ◽  
Vol 13 (17) ◽  
pp. 8643-8650 ◽  
Author(s):  
B. J. Connor ◽  
T. Mooney ◽  
G. E. Nedoluha ◽  
J. W. Barrett ◽  
A. Parrish ◽  
...  
Keyword(s):  
Atmospheric Composition ◽  
Composition Change ◽  
Major Focus ◽  
Short Term ◽  
Data Set ◽  
Long Term Changes ◽  
The Difference ◽  
Long Term Trend ◽  
Linear Decline

Abstract. We present a re-analysis of upper stratospheric ClO measurements from the ground-based millimeter-wave instrument from January 1992 to February 2012. These measurements are made as part of the Network for the Detection of Atmospheric Composition Change (NDACC) from Mauna Kea, Hawaii, (19.8° N, 204.5° E). Here, we use daytime and nighttime measurements together to form a day–night spectrum, from which the difference in the day and night profiles is retrieved. These results are then compared to the day–night difference profiles from the Upper Atmosphere Research Satellite (UARS) and Aura Microwave Limb Sounder (MLS) instruments. We also compare them to our previous analyses of the same data, in which we retrieved the daytime ClO profile. The major focus will be on comparing the year-to-year and long-term changes in ClO derived by the two analysis methods, and comparing these results to the long-term changes reported by others. We conclude that the re-analyzed data set has less short-term variability and exhibits a more constant long-term trend that is more consistent with other observations. Data from 1995 to 2012 indicate a linear decline of mid-stratospheric ClO of 0.64 ± 0.15% yr−1 (2σ).

scholarly journals Aspect Category Detection Based on Attention Mechanism and Bi-Directional LSTM

2019 ◽  
Vol 37 (3) ◽  
pp. 558-564
Author(s):  
Chenchao Zhou ◽  
Qun Chen ◽  
Zhanhuai Li ◽  
Bo Zhao ◽  
Yongjun Xu ◽  
...  
Keyword(s):  
Short Term Memory ◽  
Online Reviews ◽  
Attention Mechanism ◽  
Purchase Decisions ◽  
Short Term ◽  
Data Set ◽  
Part Of Speech ◽  
Urgent Task ◽  
Long Short Term Memory

Online reviews play an increasingly important role in users' purchase decisions. E-commerce websites provide massive user reviews, but it is hard for individuals to make full use of the information. Therefore, it is an urgent task to classify, analyze and summarize the massive comments. In this paper, a model based on attention mechanism and bi-directional long short-term memory (BLSTM) is used to identify the categories of these review objects for the classification of the reviews. The model first uses BLSTM to train the review in the form of word vectors; then according to the part-of-speech, the output vectors of the BLSTM are given corresponding weights. The weights as prior knowledge can guide the learning of attention mechanism to enhance the classification accuracy; finally, the attention mechanism is used to capture category-related important features which are used for category determination. Experiments on the SemEval data set show that our model outperforms the state-of-the-art methods on aspect category detection.

Prediction of long-term cancer survival from a short-term data set?

2003 ◽  
Vol 48 (12) ◽  
pp. L35-L35
Author(s):  
G Bruggmoser, F Heinemann, N Hodapp R hner
Keyword(s):  
Cancer Survival ◽  
Short Term ◽  
Data Set ◽  
Term Data

Mesospheric water vapor and D/H ratio at the Venus terminator from SOIR/VEx

2020 ◽  
Author(s):  
Arnaud Mahieux ◽  
Ann Carine Vandaele ◽  
Sarah Chamberlain ◽  
Valérie Wilquet ◽  
Séverine Robert ◽  
...  
Keyword(s):  
Water Vapor ◽  
Full Range ◽  
Lower Thermosphere ◽  
Temporal Variations ◽  
Mixing Ratio ◽  
Short Term ◽  
Data Set ◽  
Solar Occultation ◽  
Venus Express

<p>The Solar Occultation in the InfraRed (SOIR) instrument onboard Venus Express sounded the Venus mesosphere and lower thermosphere at the terminator using solar occultation technique between April 2006 and December 2014.</p><p>We report on the water vapor vertical distribution above the clouds and geo-temporal variations, observed during the full Venus Express mission. Water vapor profiles are sampled between 80 and 120 km, and calculations of the water vapor volume mixing ratio agrees with those from previous studies. Short term variations over several Earth days dominate the data set, with densities varying by up to a factor 19 over a 24 hr period. Similarly to what was found for other trace gases detected with the SOIR instrument, such as HCl, HF and SO<sub>2</sub>, no significant spatial or long term trends are observed.</p><p>287 water vapor vertical profiles obtained at the Venus terminator between 80 km and 120 km from August 2006 and September 2014 were analyzed for temporal and spatial abundance variations. Standard deviations are significantly smaller than the full range of volume mixing ratio values at all altitudes indicating that the variations are real.</p><p>The decrease in volume mixing ratio abundance below 100 km appears to be a common feature of most water vapor volume mixing ratio profiles and agrees with the decrease in water vapor reported in previous studies. Based on a very limited number of spectra, the variability of the water vapor VMR was found to be higher in the lower than in the upper mesosphere of Venus; this is in agreement with our observations as the standard deviation of the SOIR mean profile is the smallest at 100 km and increases with decreasing altitude.</p><p>No significant spatial variations or long term temporal variations are observed in the present data set in which short term variability masks all other possible trends. Our observations agree that short term (between 1 and 10 Earth days) variability is dominant.</p><p>We also report on simultaneous observations of the water first isotopologue HDO made by SOIR, which occurred 194 times during the whole VEx mission. Similarly to water vapor, we observe a large variation of HDO with time and space, without any clear time of spatial dependency.</p><p>We report on the ratio of the simultaneously measured HDO and H<sub>2</sub>O profiles, that show a constant ratio of 0.1 ± 0.1 below 100 km, and increase exponentially at higher altitude to reach a value of 1 ± 0.4 at 120 km of altitude. The results are in agreement with previous works below 100 km.</p>

Sign in / Sign up

Export Citation Format

Share Document