scholarly journals Increase Robustness SDAE with Imputing Missing Value To Eliminate Users Sparse Data in Case E-Commerce Recommender System

2018 ◽  
Vol 7 (4.44) ◽  
pp. 137
Author(s):  
Hanafi . ◽  
Nanna Suryana ◽  
Abd Samad Hasan Basari
Keyword(s):  
Collaborative Filtering ◽  
Recommender System ◽  
Evaluation Method ◽  
Product Information ◽  
Relevant Information ◽  
Sparse Data ◽  
Extreme Condition ◽  
Missing Value ◽  
Product Recommendation ◽  
Customer Profiling

Online shopping needs a computer machine to serve product information sale for customer or buyer candidate. Relevant information served by ecommerce system famous called recommender system. The successful to applied, it will have impact to increase of marketing target achievement. The character of information served by recommender system have to be special, personalized, relevant and fit according customer profiling. There are four kind of recommender system model, however there is one model that was successful to be applied in real ecommerce industry that popular named collaborative filtering. Collaborative filtering approach need a record users or customers activity in the past to generate recommendation for example rating record, purchasing record, testimony about product.  The majority collaborative filtering approaches rely on rating as fundamental computation to calculate product recommendation. However, just a little number of consumers who willing give rating for products less than a percent, according to several convince datasets such MovieLens. This problem causes of sparse product rating that will impact to product recommendation accuracy level. Sometime, in extreme condition, it is impossible to generate product recommendation. Several efforts have been conducting to handle product sparse rating, however they fail to generate product recommendation accurately when face extreme sparse data, such as matrix factorization family include SVD, NMF, SVD++. This research aims to develop a model to handle users sparse rating involving deep SDAE. One of the efforts to produce better output in handling this data sparse, our strategy is to imputing missing value by statistical method so that the input in SDAE is closer to the feasibility of data that is not too sparse. According to our experiment involve deep learning, TensorFlow, MovieLens datasets, evaluation method by root mean square error (RMSE), our approach involves reducing input missing value could address users sparse rating and increase robustness over several existing approach.  

Identifying Attack Models for Securing Cluster-Based Recommendation System

2020 ◽  
Vol 14 ◽  
Author(s):  
Amreen Ahmad ◽  
Tanvir Ahmad ◽  
Ishita Tripathi
Keyword(s):  
Collaborative Filtering ◽  
Recommender System ◽  
Recommendation System ◽  
Relevant Information ◽  
System Function ◽  
Recommendation Algorithm ◽  
Underlying Network ◽  
Entire Dataset ◽  
Attack Models ◽  
Wide Usage

: The immense growth of information has led to the wide usage of recommender systems for retrieving relevant information. One of the widely used methods for recommendation is collaborative filtering. However, such methods suffer from two problems, scalability and sparsity. In the proposed research, the two issues of collaborative filtering are addressed and a cluster-based recommender system is proposed. For the identification of potential clusters from the underlying network, Shapley value concept is used, which divides users into different clusters. After that, the recommendation algorithm is performed in every respective cluster. The proposed system recommends an item to a specific user based on the ratings of the item’s different attributes. Thus, it reduces the running time of the overall algorithm, since it avoids the overhead of computation involved when the algorithm is executed over the entire dataset. Besides, the security of the recommender system is one of the major concerns nowadays. Attackers can come in the form of ordinary users and introduce bias in the system to force the system function that is advantageous for them. In this paper, we identify different attack models that could hamper the security of the proposed cluster-based recommender system. The efficiency of the proposed research is validated by conducting experiments on student dataset.

scholarly journals Product Recommendation Based on Eye Tracking Data Using Fixation Duration

2021 ◽  
Vol 5 (4) ◽  
pp. 109
Author(s):  
Juni Nurma Sari ◽  
Lukito Edi Nugroho ◽  
Paulus Insap Santosa ◽  
Ridi Ferdiana
Keyword(s):  
Eye Tracking ◽  
Collaborative Filtering ◽  
Fixation Duration ◽  
Product Information ◽  
Sensor Technology ◽  
Tracking Data ◽  
Eye Tracker ◽  
Product Recommendation ◽  
User Attention ◽  
Product Recommendations

E-commerce can be used to increase companies or sellers’ profits. For consumers, e-commerce can help them shop faster. The weakness of e-commerce is that there is too much product information presented in the catalog which in turn makes consumers confused. The solution is by providing product recommendations. As the development of sensor technology, eye tracker can capture user attention when shopping. The user attention was used as data of consumer interest in the product in the form of fixation duration following the Bojko taxonomy. The fixation duration data was processed into product purchase prediction data to know consumers’ desire to buy the products by using Chandon method. Both data could be used as variables to make product recommendations based on eye tracking data. The implementation of the product recommendations based on eye tracking data was an eye tracking experiment at selvahouse.com which sells hijab and women modest wear. The result was a list of products that have similarities to other products. The product recommendation method used was item-to-item collaborative filtering. The novelty of this research is the use of eye tracking data, namely the fixation duration and product purchase prediction data as variables for product recommendations. Product recommendation that produced by eye tracking data can be solution of product recommendation’s problems, namely sparsity and cold start.

scholarly journals Exploration of Collaboration Filtering Techniques for Product Recommendation

2020 ◽  
Vol 9 (3) ◽  
pp. 799-802
Keyword(s):  
Collaborative Filtering ◽  
Search Engine ◽  
Recommender System ◽  
Recommendation System ◽  
Scientific Research ◽  
Knowledge Extraction ◽  
User Preferences ◽  
Education Economics ◽  
Product Recommendation ◽  
Filtering Techniques

Today, recommendation system has been globally adopted as the most effective and reliable search engine for knowledge extraction in the field of education, economics and scientific research. Collaborative filtering is a proven techniques used in recommender system to make predictions or recommendations of the unknown preferences for users based on the known user preferences. In this paper, collaborative filtering task and their challenges are explored, study the different recommendation techniques and evaluate their performance using different metrics.

scholarly journals Realization of Recommender Framework Based on Community Detection

2019 ◽  
pp. 57-65
Author(s):  
Karen Mkhitaryan
Keyword(s):  
Customer Satisfaction ◽  
Collaborative Filtering ◽  
Recommender Systems ◽  
Community Detection ◽  
Recommender System ◽  
Relevant Information

Recommender systems play an important role in suggesting relevant information to users based on their available preferences about items. Utilizing a recommender system allows companies to increase revenues, customer satisfaction and enable personalization and discovery. Content-based and collaborative filtering approaches are the most popular techniques in recommender systems predicting users preferences based on “collaborative” data about users and items in the system. However, their use is not justified in certain applications, particularly when user-item collaboration data is very sparse or missing. In this paper, a recommender framework based on community detection is developed outperforming other popular recommendation methods in some applications.

scholarly journals Word Sequential Using Deep LSTM and Matrix Factorization to Handle Rating Sparse Data for E-Commerce Recommender System

2021 ◽  
Vol 2021 ◽  
pp. 1-20
Author(s):  
Hanafi ◽  
Burhanuddin Mohd Aboobaider
Keyword(s):  
Collaborative Filtering ◽  
Recommender Systems ◽  
Recommender System ◽  
Matrix Factorization ◽  
Factor Model ◽  
Sparse Data ◽  
Product Review ◽  
Latent Factor ◽  
Latent Factor Model ◽  
Future Work

Recommender systems are essential engines to deliver product recommendations for e-commerce businesses. Successful adoption of recommender systems could significantly influence the growth of marketing targets. Collaborative filtering is a type of recommender system model that uses customers’ activities in the past, such as ratings. Unfortunately, the number of ratings collected from customers is sparse, amounting to less than 4%. The latent factor model is a kind of collaborative filtering that involves matrix factorization to generate rating predictions. However, using only matrix factorization would result in an inaccurate recommendation. Several models include product review documents to increase the effectiveness of their rating prediction. Most of them use methods such as TF-IDF and LDA to interpret product review documents. However, traditional models such as LDA and TF-IDF face some shortcomings, in that they show a less contextual understanding of the document. This research integrated matrix factorization and novel models to interpret and understand product review documents using LSTM and word embedding. According to the experiment report, this model significantly outperformed the traditional latent factor model by more than 16% on an average and achieved 1% on an average based on RMSE evaluation metrics, compared to the previous best performance. Contextual insight of the product review document is an important aspect to improve performance in a sparse rating matrix. In the future work, generating contextual insight using bidirectional word sequential is required to increase the performance of e-commerce recommender systems with sparse data issues.

Sign in / Sign up

Export Citation Format

Share Document