scholarly journals Incorporating Similarity Measures to Optimize Graph Convolutional Neural Networks for Product Recommendation

2021 ◽  
Vol 11 (4) ◽  
pp. 1366
Author(s):  
Wafa Shafqat ◽  
Yung-Cheol Byun
Keyword(s):  
Recommender Systems ◽  
Information Overload ◽  
Probability Distributions ◽  
Similarity Measures ◽  
Computational Time ◽  
Online Data ◽  
Product Recommendation ◽  
Research Areas ◽  
Threshold Criterion ◽  
Traditional Approaches

With the ever-growing amount of online data and information, recommender systems are becoming overwhelmingly popular as an adequate approach for overcoming the challenge of information overload. Artificial Intelligence (AI) and Deep Learning (DL) have accumulated significant interest in many research areas, and recommender systems are one of them. In this paper, a Graph Convolutional Neural Network (GCNN)-based approach was used for online product recommendation. Graph-based methods have undergone substantial consideration for several recommendation tasks, with effective results. However, handling the computational complexities and training large datasets remain a challenge for such a model. Even though they are useful, the excessive measure of the model’s boundaries obstructs their applications in real-world recommender frameworks to a great extent. The recursive way of generating neighbor node embeddings for each node in the graph makes it more challenging to train a deep and large GCNN model. Therefore, we propose a model that incorporates measures of similarity between two different nodes, and these similarity measures help us to sample the neighbors beforehand. We estimate the similarity based on their interaction probability distribution with other nodes. We use KL divergence on different probability distributions to find the distance between them. This way, we set a threshold criterion for neighbor selection and generate other clusters. These clusters are then converted to subgraphs and are used as input for the proposed GCNN model. This approach simplifies the task of neighbor sampling for GCNN, and hence, we can observe a significant improvement in the computational complexity of the GCNN model. Finally, we compared the results with those for the previously proposed OpGCN model, basic GCNN model, and other traditional approaches such as collaborative filtering and probabilistic matrix factorization. The experiments showed that the complexity and computational time were decreased by estimating the similarity among nodes and sampling the nodes before training.

State of the Art Recommendation Approaches

2020 ◽  
pp. 1621-1651
Author(s):  
Bhupesh Rawat ◽  
Sanjay K. Dwivedi
Keyword(s):  
Recommender Systems ◽  
Domain Knowledge ◽  
Information Overload ◽  
State Of The Art ◽  
New Techniques ◽  
Contextual Data ◽  
Additional Information ◽  
E Learning ◽  
Traditional Approaches

Recommender systems have been used successfully in order to deal with information overload problems in a wide variety of domains ranging from e-commerce, e-tourism, to e-learning. They typically predict the ratings of unseen items by a user and recommend the top N items based on user's profile. Moreover, the profile can be enriched further by using additional information such as contextual data, domain knowledge, and tagging information among others for improving the quality of recommendations. Traditional approaches have not been effective in exploiting these additional data sources. Hence, new techniques need to be developed for extracting and integrating them into the recommendation process. In this article, the authors present a survey on state of the art recommendation approaches their algorithms, issues and also provides further research directions for developing smart and intelligent recommender systems.

State of the Art Recommendation Approaches

2018 ◽  
Vol 10 (1) ◽  
pp. 51-76
Author(s):  
Bhupesh Rawat ◽  
Sanjay K. Dwivedi
Keyword(s):  
Recommender Systems ◽  
Domain Knowledge ◽  
Information Overload ◽  
State Of The Art ◽  
New Techniques ◽  
Contextual Data ◽  
Additional Information ◽  
E Learning ◽  
Traditional Approaches

Recommender systems have been used successfully in order to deal with information overload problems in a wide variety of domains ranging from e-commerce, e-tourism, to e-learning. They typically predict the ratings of unseen items by a user and recommend the top N items based on user's profile. Moreover, the profile can be enriched further by using additional information such as contextual data, domain knowledge, and tagging information among others for improving the quality of recommendations. Traditional approaches have not been effective in exploiting these additional data sources. Hence, new techniques need to be developed for extracting and integrating them into the recommendation process. In this article, the authors present a survey on state of the art recommendation approaches their algorithms, issues and also provides further research directions for developing smart and intelligent recommender systems.

Recommender Technologies and Emerging Applications

2019 ◽  
pp. 458-470
Author(s):  
Young Park
Keyword(s):  
Recommender Systems ◽  
Recommender System ◽  
Information Overload ◽  
Future Research ◽  
Research Topics ◽  
Emerging Trends ◽  
System Approaches ◽  
Age Of Information

This chapter presents a brief overview of the field of recommender technologies and their emerging application domains. The authors explain the current major recommender system approaches within a unifying model, discuss emerging applications of recommender systems beyond traditional e-commerce, and outline emerging trends and future research topics, along with additional readings in the area of recommender technologies and applications. They believe that personalized recommender technologies will continue to advance and be applied in a variety of traditional and emerging application domains to assist users in the age of information overload.

Enhancing Citizens' Participation via Recommender Systems

2020 ◽  
pp. 624-650
Author(s):  
Luis Terán
Keyword(s):  
Decision Making ◽  
Semantic Web ◽  
Private Sector ◽  
Web 2.0 ◽  
Recommender Systems ◽  
Search Engines ◽  
Information Overload ◽  
Relevant Information ◽  
Research Topic ◽  
Government Services

With the introduction of Web 2.0, which includes users as content generators, finding relevant information is even more complex. To tackle this problem of information overload, a number of different techniques have been introduced, including search engines, Semantic Web, and recommender systems, among others. The use of recommender systems for e-Government is a research topic that is intended to improve the interaction among public administrations, citizens, and the private sector through reducing information overload on e-Government services. In this chapter, the use of recommender systems on eParticipation is presented. A brief description of the eGovernment Framework used and the participation levels that are proposed to enhance participation. The highest level of participation is known as eEmpowerment, where the decision-making is placed on the side of citizens. Finally, a set of examples for the different eParticipation types is presented to illustrate the use of recommender systems.

Intelligent Demand Forecasting and Replenishment System by Using Nature-Inspired Computing

2017 ◽  
pp. 190-205
Author(s):  
Pragyan Nanda ◽  
Sritam Patnaik ◽  
Srikanta Patnaik
Keyword(s):  
Demand Forecasting ◽  
Apparel Industry ◽  
Computational Time ◽  
Hunting Behaviour ◽  
Sudden Rise ◽  
Nature Inspired Computing ◽  
Multi Agent ◽  
Fashion Apparel ◽  
Group Hunting ◽  
Traditional Approaches

The fashion apparel industry is too diverse, volatile and uncertain due to the fast changing market scenario. Forecasting demands of consumers has become survival necessity for organizations dealing with this field. Many traditional approaches have been proposed for improving the computational time and accuracy of the forecasting system. However, most of the approaches have over-looked the uncertainty existing in the fashion apparel market due to certain unpredictable events such as new trends, new promotions and advertisements, sudden rise and fall in economic conditions and so on. In this chapter, an intelligent multi-agent based demand forecasting and replenishment system has been proposed that adopts features from nature-inspired computing for handling uncertainty of the fashion apparel industry. The proposed system is inspired from the group hunting behaviour of crocodiles such as they form temporary alliances with other crocodiles for their own benefit even after being territorial creatures.

Toward Geospatial Collaborative Tourism Recommender Systems

2018 ◽  
pp. 212-248
Author(s):  
Zahra Bahramian ◽  
Rahim Ali Abbaspour ◽  
Christophe Claramunt
Keyword(s):  
Recommender Systems ◽  
Recommender System ◽  
World Wide ◽  
Information Overload ◽  
Spatial Information ◽  
User Profile ◽  
User Preferences ◽  
Research Issues ◽  
The World ◽  
Information Finding

Tourism activities are highly dependent on spatial information. Finding the most interesting travel destinations and attractions and planning a trip are still open research issues to GIScience research applied to the tourism domain. Nowadays, huge amounts of information are available over the world wide web that may be useful in planning a visit to destinations and attractions. However, it is often time consuming for a user to select the most interesting destinations and attractions and plan a trip according to his own preferences. Tourism recommender systems (TRSs) can be used to overcome this information overload problem and to propose items taking into account the user preferences. This chapter reviews related topics in tourism recommender systems including different tourism recommendation approaches and user profile representation methods applied in the tourism domain. The authors illustrate the potential of tourism recommender systems as applied to the tourism domain by the implementation of an illustrative geospatial collaborative recommender system using the Foursquare dataset.

A Semantic Approach for News Recommendation

2011 ◽  
pp. 102-121 ◽  
Author(s):  
Flavius Frasincar ◽  
Wouter IJntema ◽  
Frank Goossen ◽  
Frederik Hogenboom
Keyword(s):  
Recommender Systems ◽  
Similarity Measures ◽  
Extraction Methods ◽  
Decision Processes ◽  
Semantic Approach ◽  
Business Decision ◽  
Term Extraction ◽  
Cosine Similarity Measure ◽  
News Recommendation ◽  
F Measure

News items play an increasingly important role in the current business decision processes. Due to the large amount of news published every day it is difficult to find the new items of one’s interest. One solution to this problem is based on employing recommender systems. Traditionally, these recommenders use term extraction methods like TF-IDF combined with the cosine similarity measure. In this chapter, we explore semantic approaches for recommending news items by employing several semantic similarity measures. We have used existing semantic similarities as well as proposed new solutions for computing semantic similarities. Both traditional and semantic recommender approaches, some new, have been implemented in Athena, an extension of the Hermes news personalization framework. Based on the performed evaluation, we conclude that semantic recommender systems in general outperform traditional recommenders systems with respect to accuracy, precision, and recall, and that the new semantic recommenders have a better F-measure than existing semantic recommenders.

scholarly journals An ensemble based on neural networks with random weights for online data stream regression

2019 ◽  
Vol 24 (13) ◽  
pp. 9835-9855 ◽  
Author(s):  
Ricardo de Almeida ◽  
Yee Mey Goh ◽  
Radmehr Monfared ◽  
Maria Teresinha Arns Steiner ◽  
Andrew West
Keyword(s):  
Data Stream ◽  
Prediction Accuracy ◽  
Concept Drift ◽  
Learning Algorithms ◽  
Data Distribution ◽  
Machine Learning Algorithms ◽  
Computational Time ◽  
Online Data ◽  
Data Prediction ◽  
Random Weights

Abstract Most information sources in the current technological world are generating data sequentially and rapidly, in the form of data streams. The evolving nature of processes may often cause changes in data distribution, also known as concept drift, which is difficult to detect and causes loss of accuracy in supervised learning algorithms. As a consequence, online machine learning algorithms that are able to update actively according to possible changes in the data distribution are required. Although many strategies have been developed to tackle this problem, most of them are designed for classification problems. Therefore, in the domain of regression problems, there is a need for the development of accurate algorithms with dynamic updating mechanisms that can operate in a computational time compatible with today’s demanding market. In this article, the authors propose a new bagging ensemble approach based on neural network with random weights for online data stream regression. The proposed method improves the data prediction accuracy as well as minimises the required computational time compared to a recent algorithm for online data stream regression from literature. The experiments are carried out using four synthetic datasets to evaluate the algorithm’s response to concept drift, along with four benchmark datasets from different industries. The results indicate improvement in data prediction accuracy, effectiveness in handling concept drift, and much faster updating times compared to the existing available approach. Additionally, the use of design of experiments as an effective tool for hyperparameter tuning is demonstrated.

An Effective Recommender System Based on Clustering Technique for TED Talks

2020 ◽  
Vol 15 (1) ◽  
pp. 35-51 ◽  
Author(s):  
Faiz Maazouzi ◽  
Hafed Zarzour ◽  
Yaser Jararweh
Keyword(s):  
Collaborative Filtering ◽  
Recommender Systems ◽  
Recommender System ◽  
Information Overload ◽  
State Of The Art ◽  
Pearson Correlation ◽  
Enormous Amount ◽  
Powerful Mechanism ◽  
Ted Talks

With the enormous amount of information circulating on the Web, it is becoming increasingly difficult to find the necessary and useful information quickly and efficiently. However, with the emergence of recommender systems in the 1990s, reducing information overload became easy. In the last few years, many recommender systems employ the collaborative filtering technology, which has been proven to be one of the most successful techniques in recommender systems. Nowadays, the latest generation of collaborative filtering methods still requires further improvements to make the recommendations more efficient and accurate. Therefore, the objective of this article is to propose a new effective recommender system for TED talks that first groups users according to their preferences, and then provides a powerful mechanism to improve the quality of recommendations for users. In this context, the authors used the Pearson Correlation Coefficient (PCC) method and TED talks to create the TED user-user matrix. Then, they used the k-means clustering method to group the same users in clusters and create a predictive model. Finally, they used this model to make relevant recommendations to other users. The experimental results on real dataset show that their approach significantly outperforms the state-of-the-art methods in terms of RMSE, precision, recall, and F1 scores.

scholarly journals Recommendation as Collaboration in Web Search

AI Magazine ◽  
2011 ◽  
Vol 32 (3) ◽  
pp. 35-45 ◽  
Author(s):  
Barry Smyth ◽  
Jill Freyne ◽  
Maurice Coyle ◽  
Peter Briggs
Keyword(s):  
Recommender Systems ◽  
Search Engines ◽  
Web Search ◽  
Online Information ◽  
Information Discovery ◽  
Proactive Approach ◽  
Systems Research ◽  
Traditional Approaches ◽  
New Generation

Recommender systems now play an important role in online information discovery, complementing traditional approaches such as search and navigation, with a more proactive approach to discovery that is informed by the users interests and preferences. To date recommender systems have been deployed within a variety of e-commerce domains, covering a range of products such as books, music, movies, and have proven to be a successful way to convert browsers into buyers. Recommendation technologies have a potentially much greater role to play in information discovery however and in this article we consider recent research that takes a fresh look at web search as a fertile platform for recommender systems research as users demand a new generation of search engines that are less susceptible to manipulation and more responsive to searcher needs and preferences.

Sign in / Sign up

Export Citation Format

Share Document