12,618 Hits in 7.0 sec

Spatial Object Recommendation with Hints

Hui Luo, Jingbo Zhou, Zhifeng Bao, Shuangli Li, J. Shane Culpepper, Haochao Ying, Hao Liu, Hui Xiong
2020 Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval  
Additionally, MPR can provide insights into why certain recommendations are being made to a user based on three types of hints: user-aspect, POI-aspect, and interaction-aspect.  ...  In this paper, we study how to support top-k spatial object recommendations at varying levels of spatial granularity, enabling spatial objects at varying granularity, such as a city, suburb, or building  ...  Based on the hierarchical categories of each POI, they devised a geographical matrix factorization method (which is a variant of GeoMF [14] ) for recommendation.  ... 
doi:10.1145/3397271.3401090 dblp:conf/sigir/LuoZBLCYLX20 fatcat:7izuyqr7dfal7pcbv3uowfs7di

Collaborative Nowcasting for Contextual Recommendation

Yu Sun, Nicholas Jing Yuan, Xing Xie, Kieran McDonald, Rui Zhang
2016 Proceedings of the 25th International Conference on World Wide Web - WWW '16  
Extensive experiments with real-world data sets from a commercial digital assistant demonstrate the effectiveness of the collaborative nowcasting model.  ...  The dynamics and co-movement among contextual signals are also elusive and complicated.  ...  product of a vector and a matrix is a three-way tensor.  ... 
doi:10.1145/2872427.2874812 dblp:conf/www/SunYXMZ16 fatcat:t7mzjjxhrnbptk57ebfzfvzxr4

Social temporal collaborative ranking for context aware movie recommendation

Nathan N. Liu, Luheng He, Min Zhao
2013 ACM Transactions on Intelligent Systems and Technology  
For the first challenge, we propose a novel ranking based matrix factorization model to aggregate explicit and implicit user feedback.  ...  For the second challenge, we extend this model to a sequential matrix factorization model to enable time-aware parametrization.  ...  The weekly recommendation track of the CAMRa 2010 challenge aims at evaluating a recommendation algorithm's ability to cope with such temporal dynamics.  ... 
doi:10.1145/2414425.2414440 fatcat:v6b25oszajddzbyn5yi3hesq74

Endogenous and Exogenous Multi-Modal Layers in Context Aware Recommendation Systems for Health [article]

Nitish Nag, Vaibhav Pandey, Ramesh C. Jain
2018 arXiv   pre-print
Inherently, this means using data to generate a list of recommendations for a given situation.  ...  Modern user content consumption and decision making in both cyber (e.g. entertainment, news) and physical (eg. food, shopping) spaces rely heavily on targeted personalized recommender systems.  ...  This reduced set can then be incorporated into a multi-dimensional model that takes into account dynamic data streams from multi-modal data to give the final utility matrix of items. primary risk factor  ... 
arXiv:1808.06468v1 fatcat:o5ttjysgwbf73jdvb4ygaptlpe

AToMRS: A Tool to Monitor Recommender Systems

André Costa, Tiago Cunha, Carlos Soares
2016 Proceedings of the 8th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management  
A functional prototype of the application is presented, with the purpose of validating the solution's concept.  ...  To achieve this goal, a multi-granularity approach is developed and implemented in order to organize the different levels of the problem.  ...  Ciência e a Tecnologia as part of project UID/EEA/50014/2013.  ... 
doi:10.5220/0005992801330140 dblp:conf/ic3k/Costa0S16 fatcat:siujrzj5qvfotjcwq2h65yhqvq

Design of near optimal user interface with minimal UI elements using evidence based recommendations and multi criteria decision making: TOPSIS method

S. Margret Anouncia, Subbiah Vairamuthu
2018 International Journal of Humanitarian Technology  
In this work, it has been attempted to recommend designers to build user interface with minimal components without compensating the effectiveness.  ...  Usability factors when not considered properly during interaction design will lead spending more cost and time for any organisation.  ...  an evaluation matrix (often called an options matrix or a decision table ) • standardise the raw scores to generate a priority scores matrix or decision table • determine a weight for each criterion  ... 
doi:10.1504/ijht.2018.10011353 fatcat:vn6ju7wbtjgjzbvji5y3taad2m

Local implicit feedback mining for music recommendation

Diyi Yang, Tianqi Chen, Weinan Zhang, Qiuxia Lu, Yong Yu
2012 Proceedings of the sixth ACM conference on Recommender systems - RecSys '12  
Integration with existing temporal models achieves a great improvement compared to the reported best single model for Yahoo! Music.  ...  Moreover, we design an efficient training algorithm to speed up the updating procedure, and give a method to find the most appropriate time granularity to assist the performance.  ...  Latent factor models, like matrix factorization (MF), and neighborhood models are two canonical approaches in CF to capture users' interests.  ... 
doi:10.1145/2365952.2365973 dblp:conf/recsys/YangCZLY12 fatcat:hq6dwztbvbcizh6f2nmnwqt2wi

Application of New ATAM Tools to Evaluation of the Dynamic Map Architecture [chapter]

Piotr Szwed, Igor Wojnicki, Sebastian Ernst, Andrzej Głowacz
2013 Communications in Computer and Information Science  
To facilitate the task new tools supporting ATAM based assessment are proposed: Scenario Influence Matrix and Architectural Decision Matrix.  ...  The Dynamic Map is a complex information system, composed of spatial databases, storing static and dynamic data relevant for urban traffic, as well as a set of software modules responsible for data collection  ...  -Recommendation: Make a decision on the ontology storage and define a workflow for updating the dictionaries based on ontology.  ... 
doi:10.1007/978-3-642-38559-9_22 fatcat:4mcukd4oardxzbcg5plxsjnxc4

Multi-Rate Deep Learning for Temporal Recommendation

Yang Song, Ali Mamdouh Elkahky, Xiaodong He
2016 Proceedings of the 39th International ACM SIGIR conference on Research and Development in Information Retrieval - SIGIR '16  
In this work, we propose a novel deep neural network based architecture that models the combination of long-term static and short-term temporal user preferences to improve the recommendation performance  ...  The resulted model is applied to a real-world data set from a commercial News recommendation system.  ...  In [14] , the matrix factorization model is extended to allow each user to have a base latent vector and another set of time dependent vectors.  ... 
doi:10.1145/2911451.2914726 dblp:conf/sigir/SongEH16 fatcat:yzexgwnlwve33olztgboq4a5te

Initial Profile Generation in Recommender Systems Using Pairwise Comparison

Lior Rokach, Slava Kisilevich
2012 IEEE Transactions on Systems Man and Cybernetics Part C (Applications and Reviews)  
Our method uses a lazy decision tree, with pairwise comparisons at the decision nodes.  ...  Based on the user's response to a certain comparison, we select on-the-fly what pairwise comparison should next be asked.  ...  Roughly speaking there are two types of item-based methods: static and dynamic methods. With static methods, the system manage a seed set of items to be rated by the newcomer.  ... 
doi:10.1109/tsmcc.2012.2197679 fatcat:opmdsf3wlnco7nsebjs5un2dqu

Modeling the Dynamics of Online News Reading Interests

Elena Viorica Epure, Benjamin Kille, Jon Espen Ingvaldsen, Rebecca Deneckere, Camille Salinesi, Sahin Albayrak
2017 Proceedings of the 25th Conference on User Modeling, Adaptation and Personalization - UMAP '17  
Online news readers exhibit a very dynamic behavior.  ...  News publishers have been investigating ways to predict such changes in order to adjust their recommendation strategies and be er engage the readers.  ...  Let S t refer to the transition matrix based on observations in t ∈ T . Let S T refer to the transition matrix based on all observations.  ... 
doi:10.1145/3079628.3079636 dblp:conf/um/EpureKIDSA17 fatcat:fdd7g3nxkvchlmaeosskj4jeu4

Artificial intelligence in recommender systems

Qian Zhang, Jie Lu, Yaochu Jin
2020 Complex & Intelligent Systems  
recommender systems.  ...  The observations in this paper will directly support researchers and professionals to better understand current developments and new directions in the field of recommender systems using AI.  ...  models such as the aspect model [134] , decision trees [135] , and matrix factorization [136] .  ... 
doi:10.1007/s40747-020-00212-w fatcat:ev3cyoy2mjeuhmq3rymkx2shsy

Adaptive and Architecture-Independent Task Granularity for Recursive Applications [chapter]

Antoni Navarro, Sergi Mateo, Josep Maria Perez, Vicenç Beltran, Eduard Ayguadé
2017 Lecture Notes in Computer Science  
Often, finding the optimal granularity will cause a substantial increase in performance. With that in mind, the quest for optimality is no easy task.  ...  However, with the arrival of tasking models, came granularity management.  ...  This approach might work as expected with some specific architectures, applications and input sizes, however introducing variability in any of these three factors might trigger wrong cutoff decisions,  ... 
doi:10.1007/978-3-319-65578-9_12 fatcat:x6yvnes42fay7esdqhi3536nty

Pedestrian Simulation: A Review [article]

Amir Rasouli
2021 arXiv   pre-print
The review includes: various modeling criteria, such as granularity, techniques, and factors involved in modeling pedestrian behavior, and different pedestrian simulation methods with a more detailed look  ...  At the end, benefits and drawbacks of different simulation techniques are discussed and recommendations are made for future research.  ...  The types of decisions the human makes or actions they perform are motivated by their beliefs, i.e. what they think is the best way of accomplishing a task.  ... 
arXiv:2102.03289v1 fatcat:ytedisucdrfylmx35mfgujmdei

Multi-source Information Fusion for Personalized Restaurant Recommendation

Jing Sun, Yun Xiong, Yangyong Zhu, Junming Liu, Chu Guan, Hui Xiong
2015 Proceedings of the 38th International ACM SIGIR Conference on Research and Development in Information Retrieval - SIGIR '15  
Finally, empirical studies on real-world data demonstrate that the proposed method outperforms benchmark methods with a significant margin.  ...  Specifically, we develop a probabilistic factor analysis framework, named RMSQ-MF, which has the ability in exploiting multi-source information, such as the users' task, their friends' preferences, and  ...  Figure 1 1 shows the decision process of user u to choose restaurant i in a generative way.  ... 
doi:10.1145/2766462.2767818 dblp:conf/sigir/SunXZLGX15 fatcat:3clv5kwhmnbarbjvfgwat6hy4m
« Previous Showing results 1 — 15 out of 12,618 results