DLDik Lun Lee

Dik Lun Lee

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

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Dik Lun Lee has a total of 136 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    From GARCH to Neural Network for Volatility Forecast

    by Pengfei Zhao, Haoren Zhu, Wilfred Siu Hung Ng, Dik Lun Lee

    Volatility, as a measure of uncertainty, plays a crucial role in numerous financial activities such as risk management. The Econometrics and Machine Learning communities have developed two distinct approaches for financial volatility forecasting: the stochastic approach and the neural network (NN) approach. Despite their individual strengths, these methodologies have conventionally evolved in separate research trajectories with little interaction between them. This study endeavors to bridge this gap by establishing an equivalence relationship between models of the GARCH family and their corresponding NN counterparts. With the equivalence relationship established, we introduce an innovative approach, named GARCH-NN, for constructing NN-based volatility models. It obtains the NN counterparts of GARCH models and integrates them as components into an established NN architecture, thereby seamlessly infusing volatility stylized facts (SFs) inherent in the GARCH models into the neural network. We develop the GARCH-LSTM model to showcase the power of GARCH-NN approach. Experiment results validate that amalgamating the NN counterparts of the GARCH family models into established NN models leads to enhanced outcomes compared to employing the stochastic and NN models in isolation.


  • Open Access

    From GARCH to Neural Network for Volatility Forecast

    by Pengfei Zhao, Haoren Zhu, Wilfred Siu Hung Ng, Dik Lun Lee

    Volatility, as a measure of uncertainty, plays a crucial role in numerous financial activities such as risk management. The Econometrics and Machine Learning communities have developed two distinct approaches for financial volatility forecasting: the stochastic approach and the neural network (NN) approach. Despite their individual strengths, these methodologies have conventionally evolved in separate research trajectories with little interaction between them. This study endeavors to bridge this gap by establishing an equivalence relationship between models of the GARCH family and their corresponding NN counterparts. With the equivalence relationship established, we introduce an innovative approach, named GARCH-NN, for constructing NN-based volatility models. It obtains the NN counterparts of GARCH models and integrates them as components into an established NN architecture, thereby seamlessly infusing volatility stylized facts (SFs) inherent in the GARCH models into the neural network. We develop the GARCH-LSTM model to showcase the power of the GARCH-NN approach. Experiment results validate that amalgamating the NN counterparts of the GARCH family models into established NN models leads to enhanced outcomes compared to employing the stochastic and NN models in isolation.


  • Open Access

    Asset Dependence Prediction Utilizing Spatiotemporal Patterns

    by Haoren Zhu, Shih-Yang Liu, Pengfei Zhao, Yingying Chen, Dik Lun Lee

    Financial assets exhibit dependence structures and knowing the dependencies of the assets can help investors to create a diversified portfolio that can reduce portfolio risk due to the high volatility of the financial market. Since asset dependency changes with time in complex patterns, asset dependency forecasting is an important problem in finance. In this paper, we organize pairwise asset dependencies in an Asset DependencyMatrix (ADM ) and formulate the problem of asset dependency fore-cast as the prediction of future ADM s given a sequence of past ADM s.To exploit the spatiotemporal dependencies between the assets, we propose a novel idea that views ADM sequence as an image sequence, where an ADM corresponds to an image and an entry in the ADM to a pixel. This enables us to apply video prediction methods to capture the spatiotemporal dependencies among the assets. In this paper, we propose a novel Asset Dependency Neural Network (ADNN) to tackle the ADM prediction problem. It adopts ConvLSTM, a highly successful method for video prediction, and the novelty of ADNN is the introduction of a transformation function between ADM and ConvLSTM and an end-to-end approach to learn the transformation function. We conducted extensive experiments to evaluate the performance of ADNN and show that our proposed framework consistently outperforms the baselines on future ADM prediction and portfolio risk reduction tasks.

  • Open Access

    Influential Recommender System

    by Haoren Zhu, Hao Ge, Xiaodong Gu, Pengfei Zhao, Dik Lun Lee

    Traditional recommender systems are typically passive in that they try to adapt their recommendations to the user's historical interests. However, it is highly desirable for commercial applications, such as e-commerce, advertisement placement, and news portals, to be able to expand the users' interests so that they would accept items that they were not originally aware of or interested in to increase customer interactions. In this paper, we present Influential Recommender System (IRS), a new recommendation paradigm that aims to proactively lead a user to like a given objective item by progressively recommending to the user a sequence of carefully selected items (called an influence path). We propose the Influential Recommender Network (IRN), which is a Transformer-based sequential model to encode the items' sequential dependencies. Since different people react to external influences differently, we introduce the Personalized Impressionability Mask (PIM) to model how receptive a user is to external influence to generate the most effective influence path for the user. To evaluate IRN, we design several performance metrics to measure whether or not the influence path can smoothly expand the user interest to include the objective item while maintaining the user's satisfaction with the recommendation. Experimental results show that IRN significantly outperforms the baseline recommenders and demonstrates its capability of influencing users' interests.

  • Ranking Users in Social Networks with Motif-based PageRank

    by Huan Zhao, Xiaogang Xu, Yangqiu Song, Dik Lun Lee, Zhao Chen, Han Gao

    PageRank has been widely used to measure the authority or the influence of a user in social networks. However, conventional PageRank only makes use of edge-based relations, which represent first-order relations between two connected nodes. It ignores higher-order relations that may exist between nodes. In this paper, we propose a novel framework, motif-based PageRank (MPR), to incorporate higher-order relations into the conventional PageRank computation. Motifs are subgraphs consisting of a small number of nodes. We use motifs to capture higher-order relations between nodes in a network and introduce two methods, one linear and one non-linear, to combine PageRank with higher-order relations. We conduct extensive experiments on three real-world networks, namely, DBLP, Epinions, and Ciao. We study different types of motifs, including 3-node simple and anchor motifs, 4-node and 5-node motifs. Besides using single motif, we also run MPR with ensemble of multiple motifs. We also design a learning task to evaluate the abilities of authority prediction with motif-based features. All experimental results demonstrate that MPR can significantly improve the performance of user ranking in social networks compared to the baseline methods.


  • Open Access

    Collaborative Filtering with Social Local Models

    by Huan Zhao, Quanming Yao, James T. Kwok, Dik Lun Lee

    Matrix Factorization (MF) is a very popular method for recommendation systems. It assumes that the underneath rating matrix is low-rank. However, this assumption can be too restrictive to capture complex relationships and interactions among users and items. Recently, Local LOw-Rank Matrix Approximation (LLORMA) has been shown to be very successful in addressing this issue. It just assumes the rating matrix is composed of a number of low-rank submatrices constructed from subsets of similar users and items. Although LLORMA outperforms MF, how to construct such submatrices remains a big problem. Motivated by the availability of rich social connections in today's recommendation systems, we propose a novel framework, i.e., Social LOcal low-rank Matrix Approximation (SLOMA), to address this problem. To the best of our knowledge, SLOMA is the first work to incorporate social connections into the local low-rank framework. Furthermore, we enhance SLOMA by applying social regularization to submatrices factorization, denoted as SLOMA++. Therefore, the proposed model can benefit from both social recommendation and the local low-rank assumption. Experimental results from two real-world datasets, Yelp and Douban, demonstrate the superiority of the proposed models over LLORMA and MF.

  • Querying Distributed Spatial Datasets with Unknown Regions

    by Qijun Zhu, Dik Lun Lee, Wang-Chien Lee

    This paper studies the problem of querying Bounded Spatial Datasets (BSDs). A BSD contains i) objects with known locations, and ii) unknown regions, each of which bounds an unknown number of objects, within a coverage area. We consider applications where each BSD is hosted on a server or site connected to a communication network and the BSDs overlap in their coverage areas. The challenge is to query the distributed BSDs to retrieve all objects and to minimize the unknown regions which may contain objects satisfying the query, while minimizing the data transmission volume and number of interactions between the query client and the sites. We develop query processing algorithms for two important types of spatial queries, namely, range and k-nearest-neighbor (kNN) queries. We develop the site-based approach and the area-based approach for efficiently processing range and kNN queries on distributed BSDs. They aim to process only a subset of the sites to obtain the full answer for a query. Thus, optimal site selection and the corresponding site querying methods are important problems studied in this paper. In the area-based approach, we prove an optimal division and derive a practical heuristic to partition a query and select the best processing site for each partition, hence achieving even better efficiency than the site-based approach. Simulation results based on three real spatial datasets show that our proposed approaches significantly outperform the baseline that uses a centralized approach in terms of data transmission volume and the number of interactions between the query client and the distributed sites.


  • PMSE: A Personalized Mobile Search Engine

    by Kenneth Wai-Ting Leung, Dik Lun Lee, Wang-Chien Lee

    We propose a personalized mobile search engine (PMSE) that captures the users' preferences in the form of concepts by mining their clickthrough data. Due to the importance of location information in mobile search, PMSE classifies these concepts into content concepts and location concepts. In addition, users' locations (positioned by GPS) are used to supplement the location concepts in PMSE. The user preferences are organized in an ontology-based, multifacet user profile, which are used to adapt a personalized ranking function for rank adaptation of future search results. To characterize the diversity of the concepts associated with a query and their relevances to the user's need, four entropies are introduced to balance the weights between the content and location facets. Based on the client-server model, we also present a detailed architecture and design for implementation of PMSE. In our design, the client collects and stores locally the clickthrough data to protect privacy, whereas heavy tasks such as concept extraction, training, and reranking are performed at the PMSE server. Moreover, we address the privacy issue by restricting the information in the user profile exposed to the PMSE server with two privacy parameters. We prototype PMSE on the Google Android platform. Experimental results show that PMSE significantly improves the precision comparing to the baseline.