Posted on Categories:Complex Network, 复杂网络, 数据科学代写, 统计代写, 统计代考

# 数据科学代写|复杂网络代写Complex Network代考|Results and Analysis

avatest™

## avatest™帮您通过考试

avatest™的各个学科专家已帮了学生顺利通过达上千场考试。我们保证您快速准时完成各时长和类型的考试，包括in class、take home、online、proctor。写手整理各样的资源来或按照您学校的资料教您，创造模拟试题，提供所有的问题例子，以保证您在真实考试中取得的通过率是85%以上。如果您有即将到来的每周、季考、期中或期末考试，我们都能帮助您！

•最快12小时交付

•200+ 英语母语导师

•70分以下全额退款

## 数据科学代写|复杂网络代写Complex Network代考|Results and Analysis

We first compare FairEA to the baseline algorithms in order to evaluate its performance algorithmically. Next, we use real intra-organizational networks to demonstrate how FairEA might be used in practice.

Here, we compare FairEA and baseline algorithms with respect to diversity and fitness. Figure 2 shows results for percentage improvement in fitness and percentage improvement in assortativity, where the number of candidates is equal to the number of open positions, with fitness function $F_1$ (candidates are qualified for positions across the network) and $10 \%$ open positions. The ideal solution (high fitness and diversity) is in the top right depicted as a star. Results for fitness functions $F_2$ (candidates are qualified for positions in a specific area) are similar.
In most cases, results for FairEA, IPOPT and Hungarian are in a nondominated set, with results of FairEA having the lowest crowding distance. More simply, we see that Hungarian does very well with respect to diversity (especially when the network was already diverse), IPOPT does very well with respect to increasing fitness, and FairEA does well at increasing both.

To summarize results, we compute the average percentage improvement in fitness and average percentage improvement in assortativity over all datasets with high, medium and low levels of assortativity for each method. When the size of the candidate pool is equal to the number of open positions, FairEA achieves at least $97 \%$ of the maximum fitness score while improving the assortativity coefficient value by $39 \%, 56 \%$ and $67 \%$ for $10 \%, 20 \%$ and $30 \%$ of open positions respectively. (Results were similar for other experimental settings.) Overall, while IPOPT increases fitness, it performs poorly on diversity. This demonstrates that simply considering the number of neighbors of a node from each class for newly assigned candidates is not sufficient. Hungarian performs well when the number of open positions is small, but performance decreases as the number of open positions increases. In contrast, FairEA consistently does well.

## 数据科学代写|复杂网络代写Complex Network代考|Example Usage of FairEA

We next illustrate how FairEA can be used in practice- i.e., to evaluate an organization’s hiring/assignment practices- on the intra-organizational networks CC and RT, which contain position level-related annotations. In such a setting, the organization would identify the set of all positions that have been open in the recent past (whatever timespan is desired), and would use the actual applicants to those positions to form the candidate pool. Because we do not have access to this data, we mark a random $p \%$ of the positions as open and consider the employees that fill those position as candidates. We say that individuals are fit for positions at their level.

Recall that in addition to optimizing for diversity and fitness, FairEA can accommodate constraints related to isolation (ensuring that minority individuals are not too far away from other minority individuals, which can have a negative effect on effectiveness [4]), and such constraints may affect performance with respect to fitness and diversity. Here, in addition to evaluating fitness and diversity, we also evaluate the effect of such a constraint. We compute the Percentage Improvement in Fitness, Percentage Improvement in Assortativity and Percentage Isolation Score of FairEA’s results when requiring that the number of minority group individuals in each group is at least $\left{0,2,0.05 \cdot\left|k_i\right|, 0.1 \cdot\left|k_i\right|, 0.2 \cdot\left|k_i\right|\right}$ where $\left|k_i\right|$ is size of team team t .

We consider networks $\mathbf{C C}(\mathbf{H})$ and $\mathbf{R T}(\mathbf{H})$, both of which are extremely segregated: the original networks have (Assortativity Coefficient \& Isolation Score) (0.38\&0.07) and $(0.43 \& 0.02)$ respectively. Both of these networks are extremely segregated and have fewer than $10 \%$ minorities in each team.

When applying FairEA, $20 \%$ and $30 \%$ of the positions are open, with different threshold levels for isolation, we see huge improvements in segregation. Figure 3 shows the results of Assortativity Coefficient and Isolation Score: these large improvements in both assortativity and isolation indicate that both networks have great potential to become more fair.

## MATLAB代写

MATLAB 是一种用于技术计算的高性能语言。它将计算、可视化和编程集成在一个易于使用的环境中，其中问题和解决方案以熟悉的数学符号表示。典型用途包括：数学和计算算法开发建模、仿真和原型制作数据分析、探索和可视化科学和工程图形应用程序开发，包括图形用户界面构建MATLAB 是一个交互式系统，其基本数据元素是一个不需要维度的数组。这使您可以解决许多技术计算问题，尤其是那些具有矩阵和向量公式的问题，而只需用 C 或 Fortran 等标量非交互式语言编写程序所需的时间的一小部分。MATLAB 名称代表矩阵实验室。MATLAB 最初的编写目的是提供对由 LINPACK 和 EISPACK 项目开发的矩阵软件的轻松访问，这两个项目共同代表了矩阵计算软件的最新技术。MATLAB 经过多年的发展，得到了许多用户的投入。在大学环境中，它是数学、工程和科学入门和高级课程的标准教学工具。在工业领域，MATLAB 是高效研究、开发和分析的首选工具。MATLAB 具有一系列称为工具箱的特定于应用程序的解决方案。对于大多数 MATLAB 用户来说非常重要，工具箱允许您学习应用专业技术。工具箱是 MATLAB 函数（M 文件）的综合集合，可扩展 MATLAB 环境以解决特定类别的问题。可用工具箱的领域包括信号处理、控制系统、神经网络、模糊逻辑、小波、仿真等。