scholarly journals Job Recommendation System using Content and Collaborative Filtering based Techniques

2019 ◽  
Vol 9 (3) ◽  
pp. 8-15 ◽  
Keyword(s):  
Collaborative Filtering ◽  
Recommendation System ◽  
Information Overload ◽  
Pearson Correlation ◽  
Job Applicants ◽  
K Nearest Neighbors ◽  
Data Set ◽  
Proposed Model ◽  
Job Recommendation ◽  
Fitting In

Internet based recruiting platforms decrease advertisement cost, but they suffer from information overload problem. The job recommendation systems (JRS) have achieved success in e-recruitment process but still they are not able to capture the complexity of matching between candidates’ desires and organizations’ requirements. Thus, we propose a hybrid JRS which combines recommendations of content-based filtering (CBF) and collaborative filtering (CF) to overcome their individual major shortcomings namely overspecialization and over-fitting. In proposed system, CBF model makes recommendations based on candidates’ skills identified from past jobs in which they have applied and CF model makes recommendations based on jobs in which similar users have applied and also those jobs in which that user has applied frequently together in very similar contexts using Word2Vec’s skip-gram model. We used k-Nearest Neighbors technique and Pearson Correlation Coefficient. The recall of our proposed model is found to be 63.97% on a data set which had nearly 1900+ jobs and 23,000 job applicants

scholarly journals Cognitive Similarity-Based Collaborative Filtering Recommendation System

2020 ◽  
Vol 10 (12) ◽  
pp. 4183 ◽  
Author(s):  
Luong Vuong Nguyen ◽  
Min-Sung Hong ◽  
Jason J. Jung ◽  
Bong-Soo Sohn
Keyword(s):  
Performance Evaluation ◽  
Collaborative Filtering ◽  
Similarity Measure ◽  
Recommendation System ◽  
Pearson Correlation ◽  
Cognitive Network ◽  
Data Set ◽  
New Approach ◽  
Layered Architecture ◽  
F Measure

This paper provides a new approach that improves collaborative filtering results in recommendation systems. In particular, we aim to ensure the reliability of the data set collected which is to collect the cognition about the item similarity from the users. Hence, in this work, we collect the cognitive similarity of the user about similar movies. Besides, we introduce a three-layered architecture that consists of the network between the items (item layer), the network between the cognitive similarity of users (cognition layer) and the network between users occurring in their cognitive similarity (user layer). For instance, the similarity in the cognitive network can be extracted from a similarity measure on the item network. In order to evaluate our method, we conducted experiments in the movie domain. In addition, for better performance evaluation, we use the F-measure that is a combination of two criteria P r e c i s i o n and R e c a l l . Compared with the Pearson Correlation, our method more accurate and achieves improvement over the baseline 11.1% in the best case. The result shows that our method achieved consistent improvement of 1.8% to 3.2% for various neighborhood sizes in MAE calculation, and from 2.0% to 4.1% in RMSE calculation. This indicates that our method improves recommendation performance.

NINU: An Incremental User-Based Algorithm for Data Sparsity Recommender Systems

2012 ◽  
Vol 201-202 ◽  
pp. 428-432
Author(s):  
Yang Zhang ◽  
Hua Shen ◽  
Guo Shun Zhou
Keyword(s):  
Collaborative Filtering ◽  
Recommender Systems ◽  
Web Sites ◽  
Rapid Growth ◽  
Information Overload ◽  
Pearson Correlation ◽  
Sparse Data ◽  
Data Set ◽  
Online Prediction

Collaborative Filtering (CF) algorithms are widely used in recommender systems to deal with information overload. However, with the rapid growth in the amount of information and the number of visitors to web sites in recent years, CF researchers are facing challenges with improving the quality of recommendations for users with sparse data and improving the scalability of the CF algorithms. To address these issues, an incremental user-based algorithm combined with item-based approach is proposed in this paper. By using N-nearest users and N-nearest items in the prediction generation, the algorithm requires an O(N) space for storing necessary similarities for the online prediction computation and at the same time gets improvement of scalability. The experiments suggest that the incremental user-based algorithm provides better quality than the best available classic Pearson correlation-based CF algorithms when the data set is sparse.

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.

Learning to predict characteristics for engineering service projects

2016 ◽  
Vol 31 (3) ◽  
pp. 313-326 ◽  
Author(s):  
Lei Shi ◽  
Linda Newnes ◽  
Steve Culley ◽  
Bruce Allen
Keyword(s):  
Information Overload ◽  
Machine Learning Techniques ◽  
Data Set ◽  
Service Project ◽  
Learning Techniques ◽  
Proposed Model ◽  
Service Projects ◽  
Project Characteristics ◽  
Project Data ◽  
Analytical Approaches

AbstractAn engineering service project can be highly interactive, collaborative, and distributed. The implementation of such projects needs to generate, utilize, and share large amounts of data and heterogeneous digital objects. The information overload prevents the effective reuse of project data and knowledge, and makes the understanding of project characteristics difficult. Toward solving these issues, this paper emphasized the using of data mining and machine learning techniques to improve the project characteristic understanding process. The work presented in this paper proposed an automatic model and some analytical approaches for learning and predicting the characteristics of engineering service projects. To evaluate the model and demonstrate its functionalities, an industrial data set from the aerospace sector is considered as a the case study. This work shows that the proposed model could enable the project members to gain comprehensive understanding of project characteristics from a multidimensional perspective, and it has the potential to support them in implementing evidence-based design and decision making.

scholarly journals Enhancing Item-Based Collaborative Filtering with Item Correlations for Music Recommendation System

2020 ◽  
Vol 9 (1) ◽  
pp. 1548-1553
Keyword(s):  
Collaborative Filtering ◽  
Digital Libraries ◽  
Correlation Matrix ◽  
Recommendation System ◽  
Pearson Correlation ◽  
Recommendation Systems ◽  
Vital Role ◽  
Music Recommendation ◽  
Filtering Method ◽  
Music Recommendation System

Music recommendation systems are playing a vital role in suggesting music to the users from huge volumes of digital libraries available. Collaborative filtering (CF) is a one of the well known method used in recommendation systems. CF is either user centric or item centric. The former is known as user-based CF and later is known as item-based CF. This paper proposes an enhancement to item-based collaborative filtering method by considering correlation among items. Lift and Pearson Correlation coefficient are used to find the correlation among items. Song correlation matrix is constructed by using correlation measures. Proposed method is evaluated on the benchmark dataset and results obtained are compared with basic item-based CF

scholarly journals Enhanced Collaborative Filtering for Personalized E-Government Recommendation

2021 ◽  
Vol 11 (24) ◽  
pp. 12119
Author(s):  
Ninghua Sun ◽  
Tao Chen ◽  
Wenshan Guo ◽  
Longya Ran
Keyword(s):  
Collaborative Filtering ◽  
Recommendation System ◽  
Information Overload ◽  
State Of The Art ◽  
Interaction Matrix ◽  
Implicit Feedback ◽  
Item Information ◽  
Negative Item ◽  
Latent Features ◽  
Government Websites

The problems with the information overload of e-government websites have been a big obstacle for users to make decisions. One promising approach to solve this problem is to deploy an intelligent recommendation system on e-government platforms. Collaborative filtering (CF) has shown its superiority by characterizing both items and users by the latent features inferred from the user–item interaction matrix. A fundamental challenge is to enhance the expression of the user or/and item embedding latent features from the implicit feedback. This problem negatively affected the performance of the recommendation system in e-government. In this paper, we firstly propose to learn positive items’ latent features by leveraging both the negative item information and the original embedding features. We present the negative items mixed collaborative filtering (NMCF) method to enhance the CF-based recommender system. Such mixing information is beneficial for extending the expressiveness of the latent features. Comprehensive experimentation on a real-world e-government dataset showed that our approach improved the performance significantly compared with the state-of-the-art baseline algorithms.

Recommending valuable ideas in an open innovation community

2018 ◽  
Vol 118 (4) ◽  
pp. 683-699 ◽  
Author(s):  
Hanjun Lee ◽  
Keunho Choi ◽  
Donghee Yoo ◽  
Yongmoo Suh ◽  
Soowon Lee ◽  
...  
Keyword(s):  
Open Innovation ◽  
Recommendation System ◽  
Information Overload ◽  
Idea Generation ◽  
Large Data ◽  
Classification Models ◽  
Data Set ◽  
Content Type ◽  
Strategic Assets ◽  
Innovation Community

PurposeOpen innovation communities are a growing trend across diverse industries because they provide opportunities of collaborating with customers and exploiting their knowledge effectively. Although open innovation communities can be strategic assets that can help firms innovate, firms nonetheless face the challenge of information overload incurred due to the characteristic of the community. The purpose of this paper is to mitigate the problem of information overload in an open innovation environment.Design/methodology/approachThis study chose MyStarbucksIdea.com (MSI) as a target open innovation community in which customers share their ideas. The authors analyzed a large data set collected from MSI utilizing text mining techniques including TF-IDF and sentiment analysis, while considering both term and non-term features of the data set. Those features were used to develop classification models to calculate the adoption probability of each idea.FindingsThe results showed that term and non-term features play important roles in predicting the adoptability of ideas and the best classification accuracy was achieved by the hybrid classification models. In most cases, the precisions of classification models decreased as the number of recommendations increased, while the models’ recalls and F1s increased.Originality/valueThis research dealt with the problem of information overload in an open innovation context. A large amount of customer opinions from an innovation community were examined and a recommendation system to mitigate the problem was proposed. Using the proposed system, the firm can get recommendations for ideas that could be valuable for its business innovation in the idea generation phase, thereby resolving the information overload and enhancing the effectiveness of open innovation.

A Novel Similarity Measure Based on Weighted Bipartite Network for Collaborative Filtering Recommendation

2012 ◽  
Vol 263-266 ◽  
pp. 1834-1837 ◽  
Author(s):  
Jian Xun Xia ◽  
Fei Wu ◽  
Chang Sheng Xie
Keyword(s):  
Collaborative Filtering ◽  
Pearson Correlation ◽  
Bipartite Network ◽  
Similarity Matrix ◽  
Data Set ◽  
User Similarity ◽  
Novel Approach ◽  
Weighted Matrix ◽  
Recommendation Algorithms ◽  
Recommendation Accuracy

This paper presents a novel approach to compute user similarity based on weighted bipartite network and resource allocation principle for collaborative filtering recommendation. The key is to calculate the asymmetric user weighted matrix and translate it into a symmetric user similarity matrix. We carry out extensive experiments over Movielens data set and demonstrate that the proposed approach can yield better recommendation accuracy and can partly to alleviate the trouble of sparseness. Compare with traditional collaborative filtering recommendation algorithms based on Pearson correlation similarity and adjusted cosine similarity, the proposed method can improve the average predication accuracy by 6.7% and 0.6% respectively.

scholarly journals Attention neural collaboration filtering based on GRU for recommender systems

2021 ◽  
Author(s):  
Hongbin Xia ◽  
Yang Luo ◽  
Yuan Liu
Keyword(s):  
Deep Learning ◽  
Collaborative Filtering ◽  
Recommendation System ◽  
Auxiliary Information ◽  
User Preferences ◽  
Feature Representation ◽  
Long Distance ◽  
Data Set ◽  
Filtering Method ◽  
The Impact

AbstractThe collaborative filtering method is widely used in the traditional recommendation system. The collaborative filtering method based on matrix factorization treats the user’s preference for the item as a linear combination of the user and the item latent vectors, and cannot learn a deeper feature representation. In addition, the cold start and data sparsity remain major problems for collaborative filtering. To tackle these problems, some scholars have proposed to use deep neural network to extract text information, but did not consider the impact of long-distance dependent information and key information on their models. In this paper, we propose a neural collaborative filtering recommender method that integrates user and item auxiliary information. This method fully integrates user-item rating information, user assistance information and item text assistance information for feature extraction. First, Stacked Denoising Auto Encoder is used to extract user features, and Gated Recurrent Unit with auxiliary information is used to extract items’ latent vectors, respectively. The attention mechanism is used to learn key information when extracting text features. Second, the latent vectors learned by deep learning techniques are used in multi-layer nonlinear networks to learn more abstract and deeper feature representations to predict user preferences. According to the verification results on the MovieLens data set, the proposed model outperforms other traditional approaches and deep learning models making it state of the art.

scholarly journals A Study on the Accuracy of Prediction in Recommendation System Based on Similarity Measures

2019 ◽  
Vol 16 (1(Suppl.)) ◽  
pp. 0263
Author(s):  
AL-Bakri Et al.
Keyword(s):  
Collaborative Filtering ◽  
Recommendation System ◽  
Similarity Measures ◽  
Huge Amount ◽  
Data Set ◽  
Advantages And Disadvantages ◽  
Target User ◽  
Global Meaning ◽  
System Memory ◽  
Accuracy Of Prediction

Recommender Systems are tools to understand the huge amount of data available in the internet world. Collaborative filtering (CF) is one of the most knowledge discovery methods used positively in recommendation system. Memory collaborative filtering emphasizes on using facts about present users to predict new things for the target user. Similarity measures are the core operations in collaborative filtering and the prediction accuracy is mostly dependent on similarity calculations. In this study, a combination of weighted parameters and traditional similarity measures are conducted to calculate relationship among users over Movie Lens data set rating matrix. The advantages and disadvantages of each measure are spotted. From the study, a new measure is proposed from the combination of measures to cope with the global meaning of data set ratings. After conducting the experimental results, it is shown that the proposed measure achieves major objectives that maximize the accuracy Predictions.

Sign in / Sign up

Export Citation Format

Share Document