DLDuen-Ren Liu

Duen-Ren Liu

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Duen-Ren Liu has a total of 44 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Generative AI-augmented multimodal graph model with parallel contrastive learning for game recommendation

    by Yang Huang, Duen-Ren Liu, Chi-Yun Chao

    The video game industry has grown rapidly, driven by increased online gaming engagement and diverse game genres. To help users discover potential games amid data overload, effective recommendation models are essential for online platforms. Although recent research addresses cold start issues by integrating multimodal contents, current approaches focus on the implicit modeling of collaborative connections between items and users, neglecting latent semantic associations within content attributes. Additionally, they fail to effectively integrate diverse modalities, relying on simplistic fusion techniques that overlook intricate content. This paper proposed a novel generative AI-augmented multimodal graph-based recommender with parallel-stage contrastive learning framework (GAIMG-CL), constructs the latent semantic item-item and user-user relationships based on image and textual data and incorporates the concept of multimodal contrastive learning. By leveraging modality-aware latent relationships, graph convolutions are employed to integrate both item and user correlations into explicit modality-aware representations. Moreover, our innovative contrastive learning framework enhances fine-grained multimodal fusion. We also leverage GAI for valuable information extraction, enhancing representation learning quality. This approach also enables the integration of enhanced item and user representations into collaborative filtering techniques. Our proposed approach outperforms other recommendation methods and notably boosts cold start recommendation performance, as evidenced by the experimental results.


  • News recommendations based on collaborative topic modeling and collaborative filtering with generative adversarial networks

    by Duen-Ren Liu, Yang Huang, Jhen-Jie Jhao, Shin-Jye Lee

    Purpose: Online news websites provide huge amounts of timely news, bringing the challenge of recommending personalized news articles. Generative adversarial networks (GAN) based on collaborative filtering (CFGAN) can achieve effective recommendation quality. However, CFGAN ignores item contents, which contain more latent preference features than just user ratings. It is important to consider both ratings and item contents in making preference predictions. This study aims to improve news recommendation by proposing a GAN-based news recommendation model considering both ratings (implicit feedback) and the latent features of news content.Design/methodology/approach: The collaborative topic modeling (CTM) can improve user preference prediction by combining matrix factorization (MF) with latent topics of item content derived from latent topic modeling. This study proposes a novel hybrid news recommendation model, Hybrid-CFGAN, which modifies the architecture of the CFGAN model with enhanced preference learning from the CTM. The proposed Hybrid-CFGAN model contains parallel neural networks – original rating-based preference learning and CTM-based preference learning, which consider both ratings and news content with user preferences derived from the CTM model. A tunable parameter is used to adjust the weights of the two preference learnings, while concatenating the preference outputs of the two parallel neural networks.Findings: This study uses the dataset collected from an online news website, NiusNews, to conduct an experimental evaluation. The results show that the proposed Hybrid-CFGAN model can achieve better performance than the state-of-the-art GAN-based recommendation methods. The proposed novel Hybrid-CFGAN model can enhance existing GAN-based recommendation and increase the performance of preference predictions on textual content such as news articles.Originality/value: As the existing CFGAN model does not consider content information and solely relies on history logs, it may not be effective in recommending news articles. Our proposed Hybrid-CFGAN model modified the architecture of the CFGAN generator by adding a parallel neural network to gain the relevant information from news content and user preferences derived from the CTM model. The novel idea of adjusting the preference learning from two parallel neural networks – original rating-based preference learning and CTM-based preference learning – contributes to improve the recommendation quality of the proposed model by considering both ratings and latent preferences derived from item contents. The proposed novel recommendation model can improve news recommendation, thereby increasing the commercial value of news media platforms.


  • Open Access

    Random RotBoost: An Ensemble Classification Method Based on Rotation Forest and AdaBoost in Random Subsets and Its Application to Clinical Decision Support

    by Shin-Jye Lee, Ching-Hsun Tseng, Hui-Yu Yang, Xin Jin, Qian Jiang, Bin Pu, Wei-Huan Hu, Duen-Ren Liu, Yang Huang, Na Zhao

    In the era of bathing in big data, it is common to see enormous amounts of data generated daily. As for the medical industry, not only could we collect a large amount of data, but also see each data set with a great number of features. When the number of features is ramping up, a common dilemma is adding computational cost during inferring. To address this concern, the data rotational method by PCA in tree-based methods shows a path. This work tries to enhance this path by proposing an ensemble classification method with an AdaBoost mechanism in random, automatically generating rotation subsets termed Random RotBoost. The random rotation process has replaced the manual pre-defined number of subset features (free pre-defined process). Therefore, with the ensemble of the multiple AdaBoost-based classifier, overfitting problems can be avoided, thus reinforcing the robustness. In our experiments with real-world medical data sets, Random RotBoost reaches better classification performance when compared with existing methods. Thus, with the help from our proposed method, the quality of clinical decisions can potentially be enhanced and supported in medical tasks.


  • Credit default swap prediction based on generative adversarial networks

    by Shu-Ying Lin, Duen-Ren Liu, Hsien-Pin Huang

    Purpose: Financial price forecast issues are always a concern of investors. However, the financial applications based on machine learning methods mainly focus on stock market predictions. Few studies have explored credit risk predictions. Understanding credit risk trends can help investors avoid market risks. The purpose of this study is to investigate the prediction model that can effectively predict credit default swaps (CDS).Design/methodology/approach: A novel generative adversarial network (GAN) for CDS prediction is proposed. The authors take three features into account that are highly relevant to the future trends of CDS: historical CDS price, news and financial leverage. The main goal of this model is to improve the existing GAN-based regression model by adding finance and news feature extraction approaches. The proposed model adopts an attentional long short-term memory network and convolution network to process historical CDS data and news information, respectively. In addition to enhancing the effectiveness of the GAN model, the authors also design a data sampling strategy to alleviate the overfitting issue.Findings: The authors conduct an experiment with a real dataset and evaluate the performance of the proposed model. The components and selected features of the model are evaluated for their ability to improve the prediction performance. The experimental results show that the proposed model performs better than other machine learning algorithms and traditional regression GAN.Originality/value: There are very few studies on prediction models for CDS. With the proposed novel approach, the authors can improve the performance of CDS predictions. The proposed work can thereby increase the commercial value of CDS predictions to support trading decisions.


  • Air pollution prediction based on factory-aware attentional LSTM neural network

    by Duen-Ren Liu, Yi-Kuan Hsu, Hsing-Yu Chen, Huan-Jian Jau


  • Open Access

    Rating Prediction Based on Merge-CNN and Concise Attention Review Mining

    by Yun-Cheng Chou, Hsing-Yu Chen, Duen-Ren Liu, Der-Shiuan Chang

    Online review websites provide an open platform for users to write reviews or give ratings on items (business services) as well as share their consumption experience. However, the volume of reviews is large, while the rating scores provide users with a quick picture of the items without reading all reviews. Recommendation systems can help users find items of interest by predicting user’s ratings on unrated items. Review contents contain more personalized preference features than simply user ratings. Therefore, it is important to consider both ratings and review contents when making rating predictions. This research proposes a novel approach that combines deep learning and review mining with attention mechanism for rating predictions. Review mining with attention mechanism is adopted to extract concise attention reviews with important words and sentences. A merge convolutional neural network (merge-CNN) model is proposed to consider both the target user’s preference features and performance features of target business for rating prediction. This method extracts quality business performance features from the quality reviews written by elite (credible) users. Moreover, the proposed method uses the concise attention reviews of target user’s neighbors to simulate target users’ reviews on unrated target business. Experiments were conducted on Yelp data sets to evaluate our proposed methods. The results show that the proposed method, i.e. considering concise attention reviews and quality reviews written by elite users, outperforms traditional methods in improving prediction accuracy. The experiment result also shows that our review simulation methods can well simulate target user’s reviews on unrated target business.


  • Air pollution forecasting based on attention‐based LSTM neural network and ensemble learning

    by Duen‐Ren Liu, Shin‐Jye Lee, Yang Huang, Chien‐Ju Chiu

    With air pollution having become a global concern, scientists are committed to working on its amelioration. In the field of air pollution prediction, there have been good results in experimental research so far, but few studies have integrated weather forecast information and the properties of air pollution drift. In this work, we propose a novel wind‐sensitive attention mechanism with a long short‐term memory (LSTM) neural network model to predict the air pollution ‐ PM2.5 concentrations by considering the influence of wind direction and speed on the changes of spatial–temporal PM2.5 concentrations in neighbouring areas. Preliminary predictions for PM2.5 are then made by an LSTM neural network regarding neighbouring pollution; these predictions are “paid attention to” and we finally apply an ensemble learning method based on eXtreme Gradient Boosting (XGBoost) to combine the preliminary predictions with weather forecasting to make second phase predictions of PM2.5. The experiment is conducted using PM2.5 data and weather forecast data. Our results illustrate that the proposed method is superior to other methods in predicting PM2.5 concentrations, including multi‐layer perceptron, support vector regression, LSTM neural network, and extreme gradient boosting algorithm.


  • Advertisement recommendation based on personal interests and ad push fairness

    by Duen-Ren Liu, Yu-Shan Liao, Ya-Han Chung, Kuan-Yu Chen

    Purpose: Online advertisement brings huge revenue to many websites. There are many types of online advertisement; this paper aims to focus on the online banner ads which are usually placed in a particular news website. The investigated news website adopts a pay-per-ad payment model, where the advertisers are charged when they rent a banner from the website during a particular period. In this payment model, the website needs to ensure that the ad pushed frequency of each ad on the banner is similar. Under such advertisement push rules, an ad-recommendation mechanism considering ad push fairness is required. Design/methodology/approach: The authors proposed a novel ad recommendation method that considers both ad-push fairness and personal interests. The authors take every ad’s exposure time into consideration and investigate users’ three different usage experiences in the website to identify the main factors affecting the interests of users. Online ad recommendation is conducted on the investigated news website. Findings: The results of the experiments show that the proposed approach performs better than the traditional approach. This method can not only enhance the average click rate of all ads in the website but also ensure reasonable fairness of exposure frequency of each ad. The online experiment results demonstrate the effectiveness of this approach. Originality/value: Existing researches had not considered both the advertisement recommendation and ad-push fairness together. With the proposed novel ad recommendation model, the authors can improve the ad click-through rate of ads with reasonable push fairness. The website provider can thereby increase the commercial value of advertising and user satisfaction.


  • News Recommendation Based on Collaborative Semantic Topic Models and Recommendation Adjustment

    by Yu-Shan Liao, Jun-Yi Lu, Duen-Ren Liu

    Providing news recommendations is an important trend for online news websites to attract more users and create more benefits. In this research, we propose a novel recommendation approach for recommending news articles. We propose A Collaborative Semantic Topic Model and an ensemble model to predict user preferences based on combining Matrix Factorization with articles' semantic latent topics derived from word embedding and Latent Dirichlet Allocation. The proposed ensemble model is further integrated with a recommendation adjustment mechanism to adjust users' online recommendation lists. We evaluate the proposed approach via offline experiments and online evaluation on a real news website. The experimental result demonstrates that our proposed approach can improve the recommendation quality of recommending news articles.


  • Churn prediction and social neighbour influences for different types of user groups in virtual worlds

    by Duen‐Ren Liu, Hsiu‐Yu Liao, Kuan‐Yu Chen, Yi‐Ling Chiu

    In virtual worlds (VWs), users have more VW games alternatives, whereas VW companies consequently suffer from high customer turnover rate and low customer loyalty. Therefore, building a churn prediction model to facilitate subsequent churn management and customer retention is important. The churn behaviours and the impact of social neighbour influences to customer churn may be different for different types of users. Accordingly, we segment users into stable, unstable, and solitary user groups according to their social contact behaviours in VWs. Novel segmentation‐based churn prediction approaches are proposed for churn prediction in VWs by building prediction models for each type of user groups and considering the effect of social neighbour influences for different user groups. The proposed approaches are evaluated by conducting experiments with a dataset collected from a VW platform. The experimental results show different churn prediction performances under different user groups. The segmentation‐based churn prediction approaches perform better than do general approaches without considering user groups. Moreover, the results also reveal that social neighbour influences have a positive impact on stable and unstable users. The proposed work contributes to investigating the social neighbour influences on churn prediction for different types of user groups in VWs.