Domain Knowledge-Based Link Prediction in Customer-Product Bipartite Graph for Product Recommendation

2019 ◽  
Vol 18 (01) ◽  
pp. 311-338 ◽  
Author(s):  
Lingling Zhang ◽  
Jing Li ◽  
Qiuliu Zhang ◽  
Fan Meng ◽  
Weili Teng
Keyword(s):  
Bipartite Graph ◽  
Link Prediction ◽  
Domain Knowledge ◽  
Attenuation Factor ◽  
Prediction Algorithm ◽  
Bipartite Network ◽  
Topological Similarity ◽  
Product Recommendation ◽  
Knowledge Based ◽  
Context Knowledge

In this paper, we propose domain knowledge-based link prediction algorithm in customer-product bipartite network to improve effectiveness of product recommendation in retail. The domain knowledge is classified into product domain knowledge and time context knowledge, which play an important part in link prediction. We take both of them into consideration in recommendation and form a unified domain knowledge-based link prediction framework. We capture product semantic similarity by ontology-based analysis and time attenuation factor from time context knowledge, then incorporate them into network topological similarity to form a new linkage measure. To evaluate the algorithm, we use a real retail transaction dataset from Food Mart. Experimental results demonstrate that the usage of domain knowledge in link prediction achieved significantly better performance.

scholarly journals Higher-order temporal network effects through triplet evolution

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Qing Yao ◽  
Bingsheng Chen ◽  
Tim S. Evans ◽  
Kim Christensen
Keyword(s):  
Real World ◽  
Link Prediction ◽  
Higher Order ◽  
Prediction Algorithm ◽  
Interaction Patterns ◽  
Temporal Networks ◽  
World Systems ◽  
Order Interaction ◽  
Space And Time ◽  
Pairwise Interactions

AbstractWe study the evolution of networks through ‘triplets’—three-node graphlets. We develop a method to compute a transition matrix to describe the evolution of triplets in temporal networks. To identify the importance of higher-order interactions in the evolution of networks, we compare both artificial and real-world data to a model based on pairwise interactions only. The significant differences between the computed matrix and the calculated matrix from the fitted parameters demonstrate that non-pairwise interactions exist for various real-world systems in space and time, such as our data sets. Furthermore, this also reveals that different patterns of higher-order interaction are involved in different real-world situations. To test our approach, we then use these transition matrices as the basis of a link prediction algorithm. We investigate our algorithm’s performance on four temporal networks, comparing our approach against ten other link prediction methods. Our results show that higher-order interactions in both space and time play a crucial role in the evolution of networks as we find our method, along with two other methods based on non-local interactions, give the best overall performance. The results also confirm the concept that the higher-order interaction patterns, i.e., triplet dynamics, can help us understand and predict the evolution of different real-world systems.

Configuration Tree Solver: A Technology for Automated Design and Configuration

1990 ◽  
Author(s):  
Alexander Kott ◽  
Gerald Agin ◽  
Dave Fawcett
Keyword(s):  
Problem Solving ◽  
General Model ◽  
General Class ◽  
Domain Knowledge ◽  
Automated Design ◽  
Automotive Component ◽  
Business Operation ◽  
Knowledge Based ◽  
Specific Configuration

Abstract Configuration is a process of generating a definitive description of a product or an order that satisfies a set of specified requirements and known constraints. Knowledge-based technology is an enabling factor in automation of configuration tasks found in the business operation. In this paper, we describe a configuration technique that is well suited for configuring “decomposable” artifacts with reasonably well defined structure and constraints. This technique may be classified as a member of a general class of decompositional approaches to configuration. The domain knowledge is structured as a general model of the artifact, an and-or hierarchy of the artifact’s elements, features, and characteristics. The model includes constraints and local specialists which are attached to the elements of the and-or-tree. Given the specific configuration requirements, the problem solving engine searches for a solution, a subtree, that satisfies the requirements and the applicable constraints. We describe an application of this approach that performs configuration and design of an automotive component.

Predicting readers’ domain knowledge based on eye-tracking measures

2018 ◽  
Vol 36 (6) ◽  
pp. 1027-1042 ◽  
Author(s):  
Quan Lu ◽  
Jiyue Zhang ◽  
Jing Chen ◽  
Ji Li
Keyword(s):  
Logistic Regression ◽  
Eye Tracking ◽  
Information Search ◽  
Domain Knowledge ◽  
Fixation Duration ◽  
Baseline Model ◽  
Content Type ◽  
Knowledge Based ◽  
Total Fixation ◽  
Negative Predictor

Purpose This paper aims to examine the effect of domain knowledge on eye-tracking measures and predict readers’ domain knowledge from these measures in a navigational table of contents (N-TOC) system. Design/methodology/approach A controlled experiment of three reading tasks was conducted in an N-TOC system for 24 postgraduates of Wuhan University. Data including fixation duration, fixation count and inter-scanning transitions were collected and calculated. Participants’ domain knowledge was measured by pre-experiment questionnaires. Logistic regression analysis was leveraged to build the prediction model and the model’s performance was evaluated based on baseline model. Findings The results showed that novices spent significantly more time in fixating on text area than experts, because of the difficulty of understanding the information of text area. Total fixation duration on text area (TFD_T) was a significantly negative predictor of domain knowledge. The prediction performance of logistic regression model using eye-tracking measures was better than baseline model, with the accuracy, precision and F(β = 1) scores to be 0.71, 0.86, 0.79. Originality/value Little research has been reported in literature on investigation of domain knowledge effect on eye-tracking measures during reading and prediction of domain knowledge based on eye-tracking measures. Most studies focus on multimedia learning. With respect to the prediction of domain knowledge, only some studies are found in the field of information search. This paper makes a good contribution to the literature on the effect of domain knowledge on eye-tracking measures during N-TOC reading and predicting domain knowledge.

Domain Knowledge-Based Compaction

2013 ◽  
pp. 125-145
Author(s):  
T. Ravindra Babu ◽  
M. Narasimha Murty ◽  
S. V. Subrahmanya
Keyword(s):  
Domain Knowledge ◽  
Knowledge Based

scholarly journals Group Relationship Mining of College Students Based on Predictive Social Network

2022 ◽  
Vol 2022 ◽  
pp. 1-9
Author(s):  
Huazhang Liu
Keyword(s):  
College Students ◽  
Social Networks ◽  
Social Network ◽  
Complex Network ◽  
Link Prediction ◽  
Rapid Development ◽  
Combination Method ◽  
Prediction Algorithm ◽  
The Social ◽  
Random Block

With the rapid development of the Internet, social networks have shown an unprecedented development trend among college students. Closer social activities among college students have led to the emergence of college students with new social characteristics. The traditional method of college students’ group classification can no longer meet the current demand. Therefore, this paper proposes a social network link prediction method-combination algorithm, which combines neighbor information and a random block. By mining the social networks of college students’ group relationships, the classification of college students’ groups can be realized. Firstly, on the basis of complex network theory, the essential relationship of college student groups under a complex network is analyzed. Secondly, a new combination algorithm is proposed by using the simplest linear combination method to combine the proximity link prediction based on neighbor information and the likelihood analysis link prediction based on a random block. Finally, the proposed combination algorithm is verified by using the social data of college students’ networks. Experimental results show that, compared with the traditional link prediction algorithm, the proposed combination algorithm can effectively dig out the group characteristics of social networks and improve the accuracy of college students’ association classification.

Sign in / Sign up

Export Citation Format

Share Document