Cascaded Deep Neural Ranking Models in LinkedIn People Search

2021 ◽  
Author(s):  
Zimeng Yang ◽  
Song Yan ◽  
Abhimanyu Lad ◽  
Xiaowei Liu ◽  
Weiwei Guo
Keyword(s):  
1999 ◽  
Author(s):  
Carla C. Chandler ◽  
Patricia Cheng ◽  
Keith Holyoak
Keyword(s):  

2008 ◽  
Vol 42 (2) ◽  
pp. 103-103 ◽  
Author(s):  
Krisztian Balog
Keyword(s):  

2021 ◽  
Vol 187 ◽  
pp. 586-591
Author(s):  
Yang Guangcheng ◽  
Su Xiao ◽  
Boran Wang ◽  
Wang Ying ◽  
Chang Fei ◽  
...  

Author(s):  
Luca Miceli ◽  
Rym Bednarova ◽  
Iliana Bednarova ◽  
Alessandro Rizzardo ◽  
Lorenzo Cobianchi ◽  
...  
Keyword(s):  
The Law ◽  

Author(s):  
Chen Lin ◽  
Xiaolin Shen ◽  
Si Chen ◽  
Muhua Zhu ◽  
Yanghua Xiao

The study of consumer psychology reveals two categories of consumption decision procedures: compensatory rules and non-compensatory rules. Existing recommendation models which are based on latent factor models assume the consumers follow the compensatory rules, i.e. they evaluate an item over multiple aspects and compute a weighted or/and summated score which is used to derive the rating or ranking of the item. However, it has been shown in the literature of consumer behavior that, consumers adopt non-compensatory rules more often than compensatory rules. Our main contribution in this paper is to study the unexplored area of utilizing non-compensatory rules in recommendation models.Our general assumptions are (1) there are K universal hidden aspects. In each evaluation session, only one aspect is chosen as the prominent aspect according to user preference. (2) Evaluations over prominent and non-prominent aspects are non-compensatory. Evaluation is mainly based on item performance on the prominent aspect. For non-prominent aspects the user sets a minimal acceptable threshold. We give a conceptual model for these general assumptions. We show how this conceptual model can be realized in both pointwise rating prediction models and pair-wise ranking prediction models. Experiments on real-world data sets validate that adopting non-compensatory rules improves recommendation performance for both rating and ranking models.


Author(s):  
Sendy Farag ◽  
Tim Schwanen ◽  
Martin Dijst

Searching product information or buying goods online is becoming increasingly popular and could affect shopping trips. However, the relationship between e-shopping and in-store shopping is currently unclear. The aim of this study is to investigate empirically how the frequencies of online searching, online buying, and nondaily shopping trips relate to each other, after controlling for sociodemographic, land use, behavioral, and attitudinal characteristics. Data were collected from 826 respondents residing in four municipalities (one urban, three suburban) in the center of the Netherlands, with the use of a shopping survey. Path analysis was used to model direct and indirect effects. The findings suggest that complementarity or generation between e-shopping and in-store shopping appears to be more likely than substitution. The more often people search online, the more shopping trips they tend to make. Individuals who frequently search or buy online tend to be male, young, single, adventurous, and frequent Internet users; have a high income; and have a positive attitude toward e-shopping. The residential environment affects e-shopping indirectly via Internet use; urban residents shop online more often than suburban residents do because urban residents use the Internet more often. Frequent in-store shoppers tend to be female and highly educated, have a high income, have no car, and have a positive attitude toward in-store shopping. It appears that for most individuals e-shopping is just another way of shopping, complementary to their in-store shopping.


2007 ◽  
Vol 38 ◽  
pp. 1-12 ◽  
Author(s):  
Herwig Wolfram

Throughout the world, historians expand the history of their nations and states into periods when these polities did not yet exist. The French speak of their first dynasty and mean the Frankish Merovingians. Until recently French history textbooks even for students in the French overseas territories started with “Nos ancêtres, les Gaulois.” In the German Kaiserreich between 1871 and 1918, let us say, little Jan Kowalski in Poznan had to accept the Germanic peoples as his forefathers, as every textbook on German history dealt with them at length. Needless to say, not only German medievalists speak of Germans long before theodiscus or teutonicus came to mean deutsch. All over the world people search for the roots of their identity. Take, for instance, the present preoccupation with Celtic ancestors. Not only the Irish, Welsh, Scots, and Bretons, but a great many other Europeans also want to be Celts by origin. “Their successors in Brittany, Wales, or Ireland do not threaten anybody with Anschluss or war. The Celtic origins, therefore, fit the Austrian neutrality perfectly well,” as Erich Zöllner ironically put it in 1976 after Chancellor Bruno Kreisky had openly declared that the Celts and not the Germans were our forefathers.


Sign in / Sign up

Export Citation Format

Share Document