Therefore, CDRSs generally generate recommendation items with improved accuracy even with a sparse dataset of a target domain ( Vo, Hong & Jung, 2020). These latent features enhance the recommendation in the target domain ( Taneja & Arora, 2018). In particular, the CDRS learns the latent features between users and items from multiple domains. One of the practical solutions showing efficiency in overcoming the sparsity and cold-start problems is deploying cross-domain recommendation services (CDRS) by using overlapped associations between different domains. Many recent studies have proposed solutions for these problems, but they are still not completely solved. That is challenging for recommendation services with two major problems, cold-start issues, and data sparsity. This leads to the data having a lot of noise, useless information, etc. However, data is increasing daily in the real world through social media and e-commercial sites. This means the RS must be designed to collect as much information as possible from users. The most important goal in an RS is to increase the accuracy of items recommended to users ( Vuong Nguyen et al., 2021). The recommended results of these methods achieve acceptable accuracy. Some of the traditional methods in recommendation systems (RSs) such as matrix factorization (MF) ( Koren, RM & Volinsky, 2009 Salakhutdinov & Mnih, 2007) or neural collaborative factoring (CF) ( Cheng et al., 2016 Dziugaite & Roy, 2015 He et al., 2017 Nguyen, Nguyen & Jung, 2020c) are applied to several specific datasets collected from several sources. Recommendation services aim to model user preferences based on user history interactions, such as item ratings ( Nguyen et al., 2020a Hong & Jung, 2018 Nguyen, Jung & Hwang, 2020b Vuong Nguyen et al., 2021). In particular, the highest performance of the three recommendation methods is user-based CF when using 10 synthetic datasets generated from DaGzang (0.437 at MAE and 0.465 at RMSE). Mean absolute error (MAE) and root mean square error (RMSE) metrics are measured to evaluate the performance of collaborative filtering (CF) CDRS. We then evaluate the recommendations generated from DakGalBi with collaborative filtering (CF) algorithms, user-based CF, and item-based CF. To validate the usefulness of the synthetic datasets generated from DaGzang, we embed these datasets into our cross-domain recommender system, called DakGalBi. The real-world datasets in our experiments were collected from Amazon’s e-commercial website. The DaGzang platform works according to the complete loop, and it consists of the following three steps: (i) detecting the overlap association (data distribution pattern) between the real-world datasets, (ii) generating synthetic datasets based on these overlap associations, and (iii) evaluating the quality of the generated synthetic datasets. Considering these issues, this study aims to present a synthetic data generation platform (called DaGzang) for cross-domain recommendation systems. In addition, finding these overlapping associations in the real world is generally tricky, and it makes its application to actual services hard. Nonetheless, if there is no dataset belonging to a specific domain, it is a challenge to generate recommendations in CDRS. Research on cross-domain recommendation systems (CDRS) has shown efficiency by leveraging the overlapping associations between domains in order to generate more encompassing user models and better recommendations.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |