In recent years, managers' self-interest motivation has been attracting more and more attention from both the academia and practice.Therefore, the ways and depth of managers' self-interest motivation influencing lis...In recent years, managers' self-interest motivation has been attracting more and more attention from both the academia and practice.Therefore, the ways and depth of managers' self-interest motivation influencing listed companies' operating performance has become a hot research area with important theoretical and practical significance. Based on the samples of A-share companies listed in Shanghai and Shenzhen stock exchange during 2012-2014. we studied different effects of managers' self-interest motivation on listed company's business performance under different situations.The innovation of this paper mainly lies in the following two points: on the one hand, we did not adopt the previous research methods which does not distinguish different kinds of company's business performance. Therefore, we divided business performance into two types firstly, then we made empirical text of the influences of managers' self-interest motivation on business performance by virtue of Hausman Model and drew related conclusions under different situations of operating performance. On the other hand, the index measuring managers' self-interest is relatively new.展开更多
随着基于位置的社交网络在日常生活中的广泛应用,有效提取用户的隐藏兴趣和行为序列模式并向用户提供满足其个性化需求的下一个兴趣点推荐服务成为推荐领域的热点问题之一.针对下一个兴趣点推荐中的用户偏好挖掘问题,提出基于用户兴趣...随着基于位置的社交网络在日常生活中的广泛应用,有效提取用户的隐藏兴趣和行为序列模式并向用户提供满足其个性化需求的下一个兴趣点推荐服务成为推荐领域的热点问题之一.针对下一个兴趣点推荐中的用户偏好挖掘问题,提出基于用户兴趣点类别周期性偏好和短期兴趣相结合的兴趣点推荐模型(Combining Periodic and Spatio-Temporal Intervals'Network,CPSTIN).该模型将用户的签到记录按小时时段模式嵌入时间窗口并使用多头自注意力机制提取用户结合用户兴趣点类别的周期性偏好;同时,将非连续时空间隔信息送入可学习矩阵,使用线性插值法提取用户基于高阶关联性的短期兴趣.最后,在两个真实数据集上验证了该模型的有效性,证明其能有效地利用用户高阶关联性短期兴趣和结合兴趣点类别的周期偏好,更准确地预测用户最有可能访问的下一个兴趣点.展开更多
针对目前在微博推荐领域主要使用单一向量表示用户兴趣且缺乏对兴趣之间复杂关系的捕捉能力,导致用户兴趣表示不全面,推荐准确性较低的问题,提出了基于双重注意力机制的多兴趣动态路由微博推荐算法(multi-interest network with dynamic...针对目前在微博推荐领域主要使用单一向量表示用户兴趣且缺乏对兴趣之间复杂关系的捕捉能力,导致用户兴趣表示不全面,推荐准确性较低的问题,提出了基于双重注意力机制的多兴趣动态路由微博推荐算法(multi-interest network with dynamic routing microblogging recommendation algorithm based on dual attention mechanism,MINDDouAtt),用于提高用户兴趣的表征能力。首先,通过动态路由从用户行为数据中提取多个兴趣胶囊,并将这些兴趣胶囊输入到自注意力机制中以对不同兴趣胶囊之间的关联信息进行交叉学习,提高兴趣的表征能力。然后,通过引入标签感知注意力机制来调节不同兴趣胶囊之间的重要性,以更好地满足用户的个性化推荐需求。实验表明,MINDDouAtt算法在亚马逊图书、天猫和微博数据集上的S HR@10值相较于最好的对比模型分别提升了33.66%、10.49%、9.60%。该算法能够在电子商务等领域为用户提供更准确和个性化的推荐结果。展开更多
文摘In recent years, managers' self-interest motivation has been attracting more and more attention from both the academia and practice.Therefore, the ways and depth of managers' self-interest motivation influencing listed companies' operating performance has become a hot research area with important theoretical and practical significance. Based on the samples of A-share companies listed in Shanghai and Shenzhen stock exchange during 2012-2014. we studied different effects of managers' self-interest motivation on listed company's business performance under different situations.The innovation of this paper mainly lies in the following two points: on the one hand, we did not adopt the previous research methods which does not distinguish different kinds of company's business performance. Therefore, we divided business performance into two types firstly, then we made empirical text of the influences of managers' self-interest motivation on business performance by virtue of Hausman Model and drew related conclusions under different situations of operating performance. On the other hand, the index measuring managers' self-interest is relatively new.
文摘随着基于位置的社交网络在日常生活中的广泛应用,有效提取用户的隐藏兴趣和行为序列模式并向用户提供满足其个性化需求的下一个兴趣点推荐服务成为推荐领域的热点问题之一.针对下一个兴趣点推荐中的用户偏好挖掘问题,提出基于用户兴趣点类别周期性偏好和短期兴趣相结合的兴趣点推荐模型(Combining Periodic and Spatio-Temporal Intervals'Network,CPSTIN).该模型将用户的签到记录按小时时段模式嵌入时间窗口并使用多头自注意力机制提取用户结合用户兴趣点类别的周期性偏好;同时,将非连续时空间隔信息送入可学习矩阵,使用线性插值法提取用户基于高阶关联性的短期兴趣.最后,在两个真实数据集上验证了该模型的有效性,证明其能有效地利用用户高阶关联性短期兴趣和结合兴趣点类别的周期偏好,更准确地预测用户最有可能访问的下一个兴趣点.
文摘针对目前在微博推荐领域主要使用单一向量表示用户兴趣且缺乏对兴趣之间复杂关系的捕捉能力,导致用户兴趣表示不全面,推荐准确性较低的问题,提出了基于双重注意力机制的多兴趣动态路由微博推荐算法(multi-interest network with dynamic routing microblogging recommendation algorithm based on dual attention mechanism,MINDDouAtt),用于提高用户兴趣的表征能力。首先,通过动态路由从用户行为数据中提取多个兴趣胶囊,并将这些兴趣胶囊输入到自注意力机制中以对不同兴趣胶囊之间的关联信息进行交叉学习,提高兴趣的表征能力。然后,通过引入标签感知注意力机制来调节不同兴趣胶囊之间的重要性,以更好地满足用户的个性化推荐需求。实验表明,MINDDouAtt算法在亚马逊图书、天猫和微博数据集上的S HR@10值相较于最好的对比模型分别提升了33.66%、10.49%、9.60%。该算法能够在电子商务等领域为用户提供更准确和个性化的推荐结果。