NP-miner: A real-time recommendation algorithm by using web usage mining

Huang, Yueh‐Min; Kuo, Yu‐Hsuan; Chen, Juei-Nan; Jeng, Yu-Lin

doi:10.1016/j.knosys.2006.04.001

Cited by 25 publications

(12 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The first category explores common problems in frequent patterns mining and strives to efficiently retrieve solutions from technical perspectives. It includes mining closed sequence patterns to reduce the solution space [34], handling noisy sequences [10], enhancing execution performance, and incrementally mining [21], real-time recommendation [17], etc.…”

Section: Temporal Sequences Discoverymentioning

confidence: 99%

Discovering forward sequences from temporal data

Liu

2013

Knowledge-Based Systems

View full text Add to dashboard Cite

Section: Temporal Sequences Discoverymentioning

confidence: 99%

Discovering forward sequences from temporal data

Liu

2013

Knowledge-Based Systems

View full text Add to dashboard Cite

“…Consequently, if a small time is available to compute predictions, in some cases, no recommendation can be proposed to the user. In the frame of the storage of navigation patterns in a tree, [22] proposes a real-time recommender algorithm: all navigation patterns are stored in the tree (the tree evolves as new user navigations arrive), confidence and support are computed when traversing the tree to find candidate patterns to compute predictions, that takes time. Moreover, the "final" score of a resource is computed before computing the one of the following resource, the recommendation is thus not anytime.…”

Section: All Kth Order Markov Modelsmentioning

confidence: 99%

Towards Privacy Compliant and Anytime Recommender Systems

Brun

Boyer

2009

E-Commerce and Web Technologies

View full text Add to dashboard Cite

Abstract. Recommendation technologies have traditionally been used in domains such as E-commerce and Web navigation to recommend resources to customers so as to help them to get the pertinent resources. Among the possible approaches is collaborative filtering that does not take into account the content of the resources: only the traces of usage of the resources are considered. State of the art models, such as sequential association-rules and Markov models, that can be used in the frame of privacy concerns, are usually studied in terms of performance, state space complexity and time complexity. Many of them have a large time complexity and require a long time to compute recommendations. However, there are domains of application of the models where recommendations may be required quickly. This paper focuses on the study of how these state of the art models can be adapted so as to be anytime. In that case recommendations can be proposed to the user whatever is the computation time available, the quality of the recommendations increases according to the computation time. We show that such models can be adapted so as to be anytime and we propose several strategies to compute recommendations iteratively. We also show that the computation time needed by these new models is not increased compared to classical ones; even so, it sometimes decreases.

show abstract

“…Web usage mining involves using data mining techniques in the discovery of web navigation patterns from web log data, also referred to as click stream data (Hand et al, 2001;Spiliopoulou and Pohle, 2001;Huang et al, 2006). The idea is that the analysis of the sequence of web pages requested by users within a particular web site may provide a better understanding and prediction of users' behavior, and may thus be used to improve the design of the web site concerned.…”

Section: Introductionmentioning

confidence: 99%

Latent class modeling of website users’ search patterns: Implications for online market segmentation

Dias

Vermunt

2007

Journal of Retailing and Consumer Services

View full text Add to dashboard Cite

Appropriate modeling of web use patterns may yield very relevant marketing and retailing information. We propose using a modelbased clustering approach for market segmentation based on website users' search patterns. We not only provide a detailed discussion of technical issues such as the problem of the selection of the number of segments, but also a very interesting empirical illustration of the potentials of the proposed approach. r

show abstract

NP-miner: A real-time recommendation algorithm by using web usage mining

Cited by 25 publications

References 23 publications

Discovering forward sequences from temporal data

Discovering forward sequences from temporal data

Towards Privacy Compliant and Anytime Recommender Systems

Latent class modeling of website users’ search patterns: Implications for online market segmentation

Contact Info

Product

Resources

About