A gradient boosting decision tree approach for insider trading identification: An empirical model evaluation of China stock market

Insider trading is a kind of criminal behavior in stock market by using nonpublic information. In recent years, it has become the major illegal activity in China’s stock market. In this study, a combination approach of GBDT (Gradient Boosting Decision Tree) and DE (Differential Evolution) is proposed to identify insider trading activities by using data of relevant indicators. First, insider trading samples occurred from year 2007 to 2017 and corresponding non-insider trading samples are collected. Next, the proposed method is trained by the GBDT, and initial parameters of the GBDT are optimized by the DE. Finally, out-of-samples are classified by the trained GBDT–DE model and its performances are evaluated. The experiment results show that our proposed method performed the best for insider trading identification under time window length of ninety days, indicating the relevant indicators under 90-days time window length are relatively more useful. Additionally, under all three time window lengths, relative importance result shows that several indicators are consistently crucial for insider trading identification. Furthermore, the proposed approach significantly outperforms other benchmark methods, demonstrating that it could be applied as an intelligent system to improve identification accuracy and efficiency for insider trading regulation in China stock market.     

Computational analysis of thin coating layer failure using a cohesive model and gradient plasticity

Thermal barrier coatings (TBC) are widely used to prevent transient high temperature attack and allow components high durability. Due to strong inhomogeneous material properties the TBC failure often initiates near the interface between the brittle oxide layer and the ductile substrate. A reliable prediction of the TBC failure requires detailed information about the crack tip field and the consequent fracture criteria. In the present paper both cohesive model and gradient plasticity are used to simulate the failure process and to study interdependence of the interface stress distribution with the specific fracture energies. Computations confirm that combination of the two models is able to simulate different failure mechanisms in the TBC system. The computational model has the potential to give a realistic prediction of the crack propagation process.     

Fast determination of critical eluent composition for polymers by gradient chromatography

Gradient chromatography was applied in order to calculate the composition at elution for different methacrylates on normal phase columns. In addition the composition at elution was determined for polyethyleneoxide on a reverse phase column. It is shown that high molar mass polymers elute for a given homopolymer irrespective of their molar mass at the same eluent composition, which varies only slightly with gradient slope. In general the composition at elution in gradient chromatography is expected to be slightly lower than the true critical composition. For high molar mass polymers we found this composition to be close to the critical composition determined by isocratic experiments. The difference between the composition at elution and the true critical composition for a variety of polymethacrylates and for polyethyleneglycol was found to be only between 0.2 and 5%. Thus, after estimating the composition at elution, only a small number of additional isocratic experiments is needed to find the exact critical composition.     

Synthesis and characterization of functional gradient copolymers of glycidyl methacrylate and butyl acrylate

Epoxy-functional spontaneous gradient copolymers of glycidyl methacrylate (G) and n-butyl acrylate (B) were synthesized via atom transfer radical polymerization (ATRP). The copolymerization reactions were carried out in toluene solution at 70 °C, using methyl 2-bromopropionate (MBrP) as initiator and copper chloride with N,N,N′,N′′,N′′-pentamethyldiethylenetriamine (PMDETA) as the catalyst system. The kinetic behaviour of the statistical copolymerizations was studied in a wide composition interval with molar fractions of G ranging from 0.10 to 0.75. The synthesized copolymers were characterized by size exclusion chromatography (SEC) and nuclear magnetic resonance (NMR) spectroscopy. ¹H NMR was employed to determine the copolymer composition, demonstrating the gradient character of the copolymers along the main chain in the whole monomer conversion interval. Apart from this, the sequence distribution and stereoregularity were analyzed. These microstructural experimental data agreed well with those calculated from Mayo-Lewis terminal model (MLTM) and a Bernoullian statistic with an isotacticity parameter of σ_G = 0.28 and a coisotacticity parameter of σ = 0.30.     

自聚焦共焦探测系统轴向分辨率的影响因素

从微小内尺度测量角度出发，研究了针孔尺寸、探测器位置、透镜的数值孔径、放大倍率和杂散光等对自聚焦共焦式探测系统轴向分辨率的影响。结果表明，为提高系统的轴向分辨率，需将有效针孔尺寸控制在≤2.5；探测器需配以精密微调整装置以实现横向精确定位；选用差动共焦光路及大数值孔径和大放大倍率的自聚焦透镜，同时，偏振光路的使用将有效的提高系统的信噪比。     

An optimization algorithm based on stochastic sensitivity analysis for noisy objective landscapes

A function minimization algorithm that updates solutions based on approximated derivative information is proposed. The algorithm generates sample points with Gaussian white noise, and approximates derivatives based on stochastic sensitivity analysis. Unlike standard trust region methods which calculate gradients with n or more sample points, where n is the number of variables, the proposed algorithm allows the number of sample points M to be less than n. Furthermore, it ignores small amounts of noise within a trust region. This paper addresses the following two questions: how does the derivative approximation become worse when the number of sample points is small? Can the algorithm find good solutions with inexact derivative information when the objective landscape is noisy? Through intensive numerical experiments using quadratic functions, the algorithm is shown to be able to approximate derivatives when M is about n/10 or more. The experiments using a formulation of the traveling salesman problem show that the algorithm can find reasonably good solutions for noisy objective landscapes with inexact derivatives information.     

基于约束优化的联想记忆模型学习算法

本文提出了一种对称互连神经元网络的学习策略,利用全局约束优化方法确定连接权。优化过程采用了梯度下降技术。这种学习算法可以保证训练样本成为系统的稳定吸引子,并且具有优化意义上的最大吸引域。本文讨论了网络的存储容量,训练样本的渐近稳定性和吸引域大小。计算机实验结果说明了学习算法的优越性。     

Information cut for clustering using a gradient descent approach

We introduce a new graph cut for clustering which we call the Information Cut. It is derived using Parzen windowing to estimate an information theoretic distance measure between probability density functions. We propose to optimize the Information Cut using a gradient descent-based approach. Our algorithm has several advantages compared to many other graph-based methods in terms of determining an appropriate affinity measure, computational complexity, memory requirements and coping with different data scales. We show that our method may produce clustering and image segmentation results comparable or better than the state-of-the art graph-based methods.     

Negative effects of sufficiently small initial weights on back-propagation neural networks

In the training of feedforward neural networks,it is usually suggested that the initial weights should be small in magnitude in order to prevent premature saturation.The aim of this paper is to point out the other side of the story:In some cases,the gradient of the error functions is zero not only for infinitely large weights but also for zero weights.Slow convergence in the beginning of the training procedure is often the result of sufficiently small initial weights.Therefore,we suggest that,in these cases,the initial values of the weights should be neither too large,nor too small.For instance,a typical range of choices of the initial weights might be something like(0.4,0.1) ∪(0.1,0.4),rather than(0.1,0.1) as suggested by the usual strategy.Our theory that medium size weights should be used has also been extended to a few commonly used transfer functions and error functions.Numerical experiments are carried out to support our theoretical findings.     

用混合式遗传算法进行给水管网现状分析

将广义简约梯度法(GRG)思想应用于传统遗传算法,提出一种新的混合式遗传算法(HGA),此方法具有很强的全局和局部搜索能力,并且无需复杂的编码、解码过程,可以准确解决多变量、多峰值的给水管网现状分析问题。采用此算法,绝大多数的计算值与实测值的误差可减小到1%以下,能准确反映管网的实际工况。