Based on the multi-agent model, an artificial stock market with four types of traders is constructed. On this basis, this paper focuses on comparing the effects of liquidation behavior on market liquidity, volatility, price discovery efficiency and long memory of absolute returns when the institutional trader adopts equal-order strategy, Volume Weighted Average Price (VWAP) strategy and Implementation Shortfall (IS) strategy respectively. The results show the following: (1) the artificial stock market based on multi-agent model can reproduce the stylized facts of real stock market well; (2) among these three algorithmic trading strategies, IS strategy causes the longest liquidation time and the lowest liquidation cost; (3) the liquidation behavior of institutional trader will significantly reduce market liquidity, price discovery efficiency and long memory of absolute returns, and increase market volatility; (4) in comparison, IS strategy has the least impact on market liquidity, volatility and price discovery efficiency, while VWAP strategy has the least impact on long memory of absolute returns.
随着复杂储层地震资料特征筛选的机器学习技术的进步,如何有效地对参与地震属性优选和储层反演的地震样本进行采集和分析,成为目前智能地震预测领域的一个研究热点。目前的方法多着重于模型分类算法的改进,在标签的制作和采集方面不仅耗费大量时间进行人工标注,还存在标签不平衡情况下类内可靠性、类间平衡性不强等问题。为此,提出基于稀疏强特征提取的三维地震数据完备方法。首先,基于多数决原则的样本分割(Sample Segmentation Based on Majority Rule, SSMR)寻迹多尺度、多标签三维地震样本,进行采集、自动标注;然后,改进标签洗牌平衡方法(Improved Label Shuffling Balance Method, ILSB),通过“2+1”的样本增广平衡策略进行数据完备处理,改善样本采样不平衡性导致的模型训练偏向性;最后,利用基于最小L1范数稀疏表示对奇异值分解结果进行强特征提取(Minimum L1-norm Based Sparse Representation for Feature Extraction, L 相似文献
The application and development of 3D printing technology are greatly restricted due to the poor performance and single-function of the manufactured products. Therefore, it is still an important topic to develop 3D printing products with excellent performance and multi-functions. In this study, a novel graphite-filled polypropylene/polyamide 6 composite was successfully prepared using fused deposition modeling (FDM, one of the most popular 3D printing technologies). The effects of graphite on printing quality, melt-crystallization behavior and thermal stability of the composites were studied. In addition, the influence of different printing arrangements on the electrical conductivity and mechanical properties of the composite were also studied, and the existing performance regulation mechanisms were deeply explored through the microscopic morphology characterization (graphite sheet orientation and void distribution) and force analysis. This work demonstrates that components with specific performance requirements can be tuned and manufactured using FDM, which further expands the application and development of 3D printing technology in the field of functional composite materials. 相似文献