Filters








1,006 Hits in 7.2 sec

I Know You'll Be Back: Interpretable New User Clustering and Churn Prediction on a Mobile Social Application [article]

Carl Yang, Xiaolin Shi, Jie Luo, Jiawei Han
2019 arXiv   pre-print
Then we design a novel deep learning pipeline based on LSTM and attention to accurately predict user churn with very limited initial behavior data, by leveraging the correlations among users' multi-dimensional  ...  , based on the intuition that proper user clustering can help understand and predict user churn.  ...  Future works include but are not limited to the study on user ego-network heterogeneity, where we hope to understand how different types of users connect with each other, as well as the modeling of user  ... 
arXiv:1910.01447v1 fatcat:mfea4xsmgffhxnc6diyjizxe2u

Generative Models for Spear Phishing Posts on Social Media [article]

John Seymour, Philip Tully
2018 arXiv   pre-print
We present a long short-term memory (LSTM) neural network that learns to socially engineer specific users into clicking on deceptive URLs.  ...  We augment the model with clustering to triage high value targets based on their level of social engagement, and measure success of the LSTM's phishing expedition using click-rates of IP-tracked links.  ...  We ensure our dummy account doesn't follow any other users, and so our posts are only visible to us and to our targets. The content of the post is generated by a long short-term memory (LSTM) model.  ... 
arXiv:1802.05196v1 fatcat:vwjix4cuyfdxhlxuegxzhdrs2i

Expert recommendation in community question answering: a review and future direction

Zhengfa Yang, Qian Liu, Baowen Sun, Xin Zhao
2019 International Journal of Crowd Science  
Design/methodology/approach In this paper, keywords such as "CQA", "Social Question Answering", "expert recommendation", "question routing" and "expert finding" are used to search major digital libraries  ...  The final sample includes a list of 83 relevant articles authored in academia as well as industry that have been published from January 1, 2008 to March 1, 2019.  ...  Dehghan et al. (2019) propose a new method long short-term memory (LSTM) deep neural network for T-shaped expert finding that is based on temporal expert profiling to resolve the challenge of the dynamicity  ... 
doi:10.1108/ijcs-03-2019-0011 fatcat:5waemn4e3zfu5b4n55f6qxafbu

Security Enhancement of an Automated Teller Machine Using Fingerprint and Password

C. Nwankwo, Augustine University, Epe, Lagos State, Nigeria, G. Oletu, O.B. Longe
2020 Advances in Multidisciplinary & Scientific Research Journal Publication  
In order to achieve security and to overcome illegal activities, shortcoming of piracy in money transactions, we propose the idea of using fingerprints of customers and password instead of traditional  ...  This paper focuses on how to enhanced security of Transactions in Automatic Teller Machine system using a multi-factor authentication system (Password and Fingerprint).  ...  [11] in his paper entitled "A Five Way Fuzzy Authentication for secured banking" proposed to combine the use of Pin Number along Keypad ID, RFID Tag, Fingerprint.  ... 
doi:10.22624/isteams/v26p5-ieee-ng-ts fatcat:5mrlw7sebncwhn4qhjpqc5eir4

Matching Recommendation Technologies and Domains [chapter]

Robin Burke, Maryam Ramezani
2010 Recommender Systems Handbook  
Unlike other taxonomies of recommender systems, our approach is centered on the question of knowledge: what knowledge does a recommender system need in order to function, and where does that knowledge  ...  Acknowledgements This article is based on research performed by Ms. Ramezani at IBM Watson Research Center during the summer of 2007.  ...  additional authors Lawrence Bergman, Rich Thompson and Bamshad Mobasher appeared as "Selecting and Applying Recommendation Technologies" at the Workshop on Recommendation and Collaboration at the Intelligent User  ... 
doi:10.1007/978-0-387-85820-3_11 fatcat:eygp3krdtvh3da4xkz33meibce

Big Data: Challenges, Opportunities and Realities [article]

Abhay Bhadani, Dhanya Jothimani
2017 arXiv   pre-print
Few research issues and future directions are presented in this chapter.  ...  With the advent of Internet of Things (IoT) and Web 2.0 technologies, there has been a tremendous growth in the amount of data generated.  ...  short-term public health images monitoring and long-term epidemiological research programs Internet of Things (IoT) Sensor data To monitor various activities in smart cities Life Sciences Gene sequences  ... 
arXiv:1705.04928v1 fatcat:5q4tsrfjbvcadmpq2knisjbp2a

Program

2021 2021 International Conference on Data Science and Its Applications (ICoDSA)  
Two main methods will be implementing as Crime Classification using Ontology and Rule-Based Crime Argument Extraction.  ...  Crime Information Extraction is a task to extract some entities in the crime domain. Previous researchers have studied this task using rules to extract some crime entities in the English dataset.  ...  We use time series forecasting by using a deep learning approach so-called Long Short Term Memory (LSTM) and Bidirectional LSTM (BiLSTM) to forecast temperature data in Semarang City, Indonesia.  ... 
doi:10.1109/icodsa53588.2021.9617531 fatcat:5ozme7noqbckbfeiccdu2er764

User Response Prediction in Online Advertising [article]

Zhabiz Gharibshah, Xingquan Zhu
2021 arXiv   pre-print
Online advertising, as the vast market, has gained significant attention in various platforms ranging from search engines, third-party websites, social media, and mobile apps.  ...  Recent years have witnessed a significant increase in the number of studies using computational approaches, including machine learning methods, for user response prediction.  ...  To address short-term and long-term sequential data, there are two form of event-based and session based datasets.  ... 
arXiv:2101.02342v2 fatcat:clgefamcd5fmbeg5ephizy3zqu

The Impact of Churn Labelling Rules on Churn Prediction in Telecommunications

Andrej Bugajev, Rima Kriauzienė, Olegas Vasilecas, Viktoras Chadyšas
2022 Informatica  
, i.e. labelling rules derived from definition lead to very good classification accuracy, however, it does not imply the usefulness for such churn detection in the context of further customer retention  ...  The data in this study consist of call detail records (CDRs) and other user aggregated daily data, 11000 user entries over 275 days of data was analysed. 6 different classification methods were applied  ...  Thus, in a long-term perspective customer churn problem must be addressed more actively than proper advertisements of company services.  ... 
doi:10.15388/22-infor484 fatcat:xhxn7kk36navpeuvxgelziygla

Artificial Intelligence Marketing (AIM) for Enhancing Customer Relationships

Kok-Lim Alvin Yau, Norizan Mat Saad, Yung-Wey Chong
2021 Applied Sciences  
knowledge, and then disseminate and apply the knowledge to enhance customer relationships in a knowledge-based environment.  ...  The main processor, which is the key component, uses AI to process structured data processed by pre-processor in order to make real-time decisions and reasonings.  ...  or unsupervised learning Recurrent neural network [47] , including long short-term memory (LSTM) A neural network that uses a feedback loop to feed outputs back to the input.  ... 
doi:10.3390/app11188562 fatcat:xoaoy4jzijhrpcml6bna5tmmrm

Quality of Experience: From Assessment to Application (Dagstuhl Seminar 15022)

Katrien De Moor, Markus Fiedler, Peter Reichl, Martín Varela, Marc Herbstritt
2015 Dagstuhl Reports  
The seminar and the challenges that were addressed have their roots in the earlier Dagstuhl Seminars 09192 "From Quality of Service to Quality of Experience" and 12181 "Quality of Experience: From User  ...  ", "Monetization of QoE" and "QoE in new domains".  ...  Physiological factors such as long-term personality traits or short-term moods.  ... 
doi:10.4230/dagrep.5.1.57 dblp:journals/dagstuhl-reports/MoorFRV15 fatcat:mqpoyvr2zna45k27ftmtufmv5e

Blackmarket-Driven Collusion on Online Media: A Survey

Hridoy Sankar Dutta, Tanmoy Chakraborty
2021 ACM/IMS Transactions on Data Science  
We refer to such unfair ways of bolstering social reputation in online media as collusion .  ...  These services are operated in such a way that most of their inorganic activities are going unnoticed by the media authorities, and the customers of the blackmarket services are less likely to be spotted  ...  classification using Individual Twitter freemium/premium supervised models blackmarket services Fame4Sale [34] Users involved in Feature-based classification using Individual Twitter blackmarket-based  ... 
doi:10.1145/3517931 fatcat:7fvgujegh5hohdiemsok6kzviq

AI in Finance: Challenges, Techniques and Opportunities [article]

Longbing Cao
2021 arXiv   pre-print
AI in finance broadly refers to the applications of AI techniques in financial businesses.  ...  In contrast to either discussing the problems, aspects and opportunities of finance that have benefited from specific AI techniques and in particular some new-generation AI and data science (AIDS) areas  ...  by neural models such as long short-term memory, attentive RNN, neural models with multi-head attention, encoderdecoder, and variational autoencoder, Transformer and its variants, etc  ... 
arXiv:2107.09051v1 fatcat:g62cz4dqt5dcrbckn4lbveat3u

Deep Learning at the Mobile Edge: Opportunities for 5G Networks

Miranda McClellan, Cristina Cervelló-Pastor, Sebastià Sallent
2020 Applied Sciences  
Machine Learning (ML) is leveraged within mobile edge computing to predict changes in demand based on cultural events, natural disasters, or daily commute patterns, and it prepares the network by automatically  ...  Mobile edge computing (MEC) within 5G networks brings the power of cloud computing, storage, and analysis closer to the end user.  ...  Performing the gradient descent-based training on RNNs caused issues with "exploding gradients", which was corrected by new ML models called long-short term memory (LSTM) models with additional information  ... 
doi:10.3390/app10144735 fatcat:ytrnh35x6zbxbki3zg435xqacu

Risk Assessment of Public Safety and Security Mobile Service

Matti J. Peltola, Pekka Kekolahti
2015 2015 10th International Conference on Availability, Reliability and Security  
Therefore, it is difficult to assess from all the found patterns which of them represent some more underlying and long-term aspects and which are more short-term.  ...  These datasets have been utilized in the classification of mobile services and their users based on the service usage behaviour.  ... 
doi:10.1109/ares.2015.65 dblp:conf/IEEEares/PeltolaK15 fatcat:iqzzjbyqrzbmfanhry2rj742pi
« Previous Showing results 1 — 15 out of 1,006 results