arXiv subjects

Yi-Cheng Zhang

Publications and source records attributed to Yi-Cheng Zhang.

At least 73 records · Page 4Linked to original sources

arXiv2011

The reinforcing influence of recommendations on global diversification

Recommender systems are promising ways to filter the overabundant information in modern society. Their algorithms help individuals to explore decent items, but it is unclear how they allocate popularity among items. In this paper, we simulate successive recommendations and measure their influence on the dispersion of item popularity by Gini coefficient. Our result indicates that local diffusion and collaborative filtering reinforce the popularity of hot items, widening the popularity dispersion. On the other hand, the heat conduction algorithm increases the popularity of the niche items and generates smaller dispersion of item popularity. Simulations are compared to mean-field predictions. Our results suggest that recommender systems have reinforcing influence on global diversification.

physics.soc-ph↗

arXiv2011

Emergence of scale-free leadership structure in social recommender systems

The study of the organization of social networks is important for understanding of opinion formation, rumor spreading, and the emergence of trends and fashion. This paper reports empirical analysis of networks extracted from four leading sites with social functionality (Delicious, Flickr, Twitter and YouTube) and shows that they all display a scale-free leadership structure. To reproduce this feature, we propose an adaptive network model driven by social recommending. Artificial agent-based simulations of this model highlight a "good get richer" mechanism where users with broad interests and good judgments are likely to become popular leaders for the others. Simulations also indicate that the studied social recommendation mechanism can gradually improve the user experience by adapting to tastes of its users. Finally we outline implications for real online resource-sharing systems.

physics.soc-ph↗

arXiv2011

Leaders in Social Networks, the Delicious Case

Finding pertinent information is not limited to search engines. Online communities can amplify the influence of a small number of power users for the benefit of all other users. Users' information foraging in depth and breadth can be greatly enhanced by choosing suitable leaders. For instance in delicious.com, users subscribe to leaders' collection which lead to a deeper and wider reach not achievable with search engines. To consolidate such collective search, it is essential to utilize the leadership topology and identify influential users. Google's PageRank, as a successful search algorithm in the World Wide Web, turns out to be less effective in networks of people. We thus devise an adaptive and parameter-free algorithm, the LeaderRank, to quantify user influence. We show that LeaderRank outperforms PageRank in terms of ranking effectiveness, as well as robustness against manipulations and noisy data. These results suggest that leaders who are aware of their clout may reinforce the development of social networks, and thus the power of collective search.

physics.soc-ph↗

arXiv2011

Effective Mechanism for Social Recommendation of News

Recommendation systems represent an important tool for news distribution on the Internet. In this work we modify a recently proposed social recommendation model in order to deal with no explicit ratings of users on news. The model consists of a network of users which continually adapts in order to achieve an efficient news traffic. To optimize network's topology we propose different stochastic algorithms that are scalable with respect to the network's size. Agent-based simulations reveal the features and the performance of these algorithms. To overcome the resultant drawbacks of each method we introduce two improved algorithms and show that they can optimize network's topology almost as fast and effectively as other not-scalable methods that make use of much more information.

physics.soc-ph↗

arXiv2011

Transaction fees and optimal rebalancing in the growth-optimal portfolio

The growth-optimal portfolio optimization strategy pioneered by Kelly is based on constant portfolio rebalancing which makes it sensitive to transaction fees. We examine the effect of fees on an example of a risky asset with a binary return distribution and show that the fees may give rise to an optimal period of portfolio rebalancing. The optimal period is found analytically in the case of lognormal returns. This result is consequently generalized and numerically verified for broad return distributions and returns generated by a GARCH process. Finally we study the case when investment is rebalanced only partially and show that this strategy can improve the investment long-term growth rate more than optimization of the rebalancing period.

q-fin.PM↗

arXiv2010

Heterogeneity, quality, and reputation in an adaptive recommendation model

Recommender systems help people cope with the problem of information overload. A recently proposed adaptive news recommender model [Medo et al., 2009] is based on epidemic-like spreading of news in a social network. By means of agent-based simulations we study a "good get richer" feature of the model and determine which attributes are necessary for a user to play a leading role in the network. We further investigate the filtering efficiency of the model as well as its robustness against malicious and spamming behaviour. We show that incorporating user reputation in the recommendation process can substantially improve the outcome.

physics.soc-ph↗

arXiv2010

Self-organized model of cascade spreading

We study simultaneous price drops of real stocks and show that for high drop thresholds they follow a power-law distribution. To reproduce these collective downturns, we propose a minimal self-organized model of cascade spreading based on a probabilistic response of the system elements to stress conditions. This model is solvable using the theory of branching processes and the mean-field approximation. For a wide range of parameters, the system is in a critical state and displays a power-law cascade-size distribution similar to the empirically observed one. We further generalize the model to reproduce volatility clustering and other observed properties of real stocks.

physics.soc-ph↗

arXiv2010

Time-aware Collaborative Filtering with the Piecewise Decay Function

In this paper, we determine the appropriate decay function for item-based collaborative filtering (CF). Instead of intuitive deduction, we introduce the Similarity-Signal-to-Noise-Ratio (SSNR) to quantify the impacts of rated items on current recommendations. By measuring the variation of SSNR over time, drift in user interest is well visualized and quantified. Based on the trend changes of SSNR, the piecewise decay function is thus devised and incorporated to build our time-aware CF algorithm. Experiments show that the proposed algorithm strongly outperforms the conventional item-based CF algorithm and other time-aware algorithms with various decay functions.

cs.IR↗

arXiv2010

Solving the Cold-Start Problem in Recommender Systems with Social Tags

In this paper, based on the user-tag-object tripartite graphs, we propose a recommendation algorithm, which considers social tags as an important role for information retrieval. Besides its low cost of computational time, the experiment results of two real-world data sets, \emph{Del.icio.us} and \emph{MovieLens}, show it can enhance the algorithmic accuracy and diversity. Especially, it can obtain more personalized recommendation results when users have diverse topics of tags. In addition, the numerical results on the dependence of algorithmic accuracy indicates that the proposed algorithm is particularly effective for small degree objects, which reminds us of the well-known \emph{cold-start} problem in recommender systems. Further empirical study shows that the proposed algorithm can significantly solve this problem in social tagging systems with heterogeneous object degree distributions.

cs.IR↗

arXiv2010

Solving the apparent diversity-accuracy dilemma of recommender systems

Recommender systems use data on past user preferences to predict possible future likes and interests. A key challenge is that while the most useful individual recommendations are to be found among diverse niche objects, the most reliably accurate results are obtained by methods that recommend objects based on user or object similarity. In this paper we introduce a new algorithm specifically to address the challenge of diversity and show how it can be used to resolve this apparent dilemma when combined in an elegant hybrid with an accuracy-focused algorithm. By tuning the hybrid appropriately we are able to obtain, without relying on any semantic or context-specific information, simultaneous gains in both accuracy and diversity of recommendations.

cs.IR↗

arXiv2010

Building reputation systems for better ranking

How to rank web pages, scientists and online resources has recently attracted increasing attention from both physicists and computer scientists. In this paper, we study the ranking problem of rating systems where users vote objects by discrete ratings. We propose an algorithm that can simultaneously evaluate the user reputation and object quality in an iterative refinement way. According to both the artificially generated data and the real data from MovieLens and Amazon, our algorithm can considerably enhance the ranking accuracy. This work highlights the significance of reputation systems in the Internet era and points out a way to evaluate and compare the performances of different reputation systems.

cs.IR↗

arXiv2009

Adaptive information filtering for dynamic recommender systems

The dynamic environment in the real world calls for the adaptive techniques for information filtering, namely to provide real-time responses to the changes of system data. Where many incremental algorithms are designed for this purpose, they are usually challenged by the worse and worse performance resulted from the cumulative errors over time. In this Letter, we propose two incremental diffusion-based algorithms for the personalized recommendations, which integrate some pieces of local and fast updatings to achieve the approximate results. In addition to the fast responses, the errors of the proposed algorithms do not cumulate over time, that is to say, the global recomputing is unnecessary. This remarkable advantage is demonstrated by several metrics on algorithmic accuracy for two movie recommender systems and a social bookmarking system.

cs.IR↗

arXiv2009

Adaptive model for recommendation of news

Most news recommender systems try to identify users' interests and news' attributes and use them to obtain recommendations. Here we propose an adaptive model which combines similarities in users' rating patterns with epidemic-like spreading of news on an evolving network. We study the model by computer agent-based simulations, measure its performance and discuss its robustness against bias and malicious behavior. Subject to the approval fraction of news recommended, the proposed model outperforms the widely adopted recommendation of news according to their absolute or relative popularity. This model provides a general social mechanism for recommender systems and may find its applications also in other types of recommendation.

cs.IR↗

arXiv2009

Collaborative filtering with diffusion-based similarity on tripartite graphs

Collaborative tags are playing more and more important role for the organization of information systems. In this paper, we study a personalized recommendation model making use of the ternary relations among users, objects and tags. We propose a measure of user similarity based on his preference and tagging information. Two kinds of similarities between users are calculated by using a diffusion-based process, which are then integrated for recommendation. We test the proposed method in a standard collaborative filtering framework with three metrics: ranking score, Recall and Precision, and demonstrate that it performs better than the commonly used cosine similarity.

cs.IR↗

arXiv2009

Highly accurate recommendation algorithm based on high-order similarities

In this Letter, we introduce a modified collaborative filtering (MCF) algorithm, which has remarkably higher accuracy than the standard collaborative filtering. In the MCF, instead of the standard Pearson coefficient, the user-user similarities are obtained by a diffusion process. Furthermore, by considering the second order similarities, we design an effective algorithm that depresses the influence of mainstream preferences. The corresponding algorithmic accuracy, measured by the ranking score, is further improved by 24.9% in the optimal case. In addition, two significant criteria of algorithmic performance, diversity and popularity, are also taken into account. Numerical results show that the algorithm based on second order similarity can outperform the MCF simultaneously in all three criteria.

physics.data-an↗

arXiv2009

Effect of user tastes on personalized recommendation

In this paper, based on a weighted projection of the user-object bipartite network, we study the effects of user tastes on the mass-diffusion-based personalized recommendation algorithm, where a user's tastes or interests are defined by the average degree of the objects he has collected. We argue that the initial recommendation power located on the objects should be determined by both of their degree and the users' tastes. By introducing a tunable parameter, the user taste effects on the configuration of initial recommendation power distribution are investigated. The numerical results indicate that the presented algorithm could improve the accuracy, measured by the average ranking score, more importantly, we find that when the data is sparse, the algorithm should give more recommendation power to the objects whose degrees are close to the users' tastes, while when the data becomes dense, it should assign more power on the objects whose degrees are significantly different from user's tastes.

physics.data-an↗

arXiv2009

Minority games, evolving capitals and replicator dynamics

We discuss a simple version of the Minority Game (MG) in which agents hold only one strategy each, but in which their capitals evolve dynamically according to their success and in which the total trading volume varies in time accordingly. This feature is known to be crucial for MGs to reproduce stylised facts of real market data. The stationary states and phase diagram of the model can be computed, and we show that the ergodicity breaking phase transition common for MGs, and marked by a divergence of the integrated response is present also in this simplified model. An analogous majority game turns out to be relatively void of interesting features, and the total capital is found to diverge in time. Introducing a restraining force leads to a model akin to replicator dynamics of evolutionary game theory, and we demonstrate that here a different type of phase transition is observed. Finally we briefly discuss the relation of this model with one strategy per player to more sophisticated Minority Games with dynamical capitals and several trading strategies per agent.

physics.soc-ph↗

arXiv2009

Degree correlation effect of bipartite network on personalized recommendation

In this paper, by introducing a new user similarity index base on the diffusion process, we propose a modified collaborative filtering (MCF) algorithm, which has remarkably higher accuracy than the standard collaborative filtering. In the proposed algorithm, the degree correlation between users and objects is taken into account and embedded into the similarity index by a tunable parameter. The numerical simulation on a benchmark data set shows that the algorithmic accuracy of the MCF, measured by the average ranking score, is further improved by 18.19% in the optimal case. In addition, two significant criteria of algorithmic performance, diversity and popularity, are also taken into account. Numerical results show that the presented algorithm can provide more diverse and less popular recommendations, for example, when the recommendation list contains 10 objects, the diversity, measured by the hamming distance, is improved by 21.90%.

physics.data-an↗