Measuring the gender discrimination: A machine learning approach

Gender discrimination is a widely analyzed problem, which seems to affect different countries and cultures over time. Nowadays, we are witnesses of the social inequality reflected by the salary difference between women and men for the same employment. Since the incorporation of women into the labor market in the 1980s, the wage gap between males and females has been a subject of study. One of the traditional arguments has been linked to the feminized occupations associated with sex stereotypes, as well as, low wage, birth, and discrimination in the labor categories. In the present work, we apply clustering algorithms to the PHOGUE dataset to analyze salary difference between males and females in Spain and England.

[1]  D. Grimshaw,et al.  The Gender Pay Gap and Gender Mainstreaming Pay Policy in EU Member States [Synthesis Report for the Equal Opportunities Unit in the European Commission] , 2003 .

[2]  D. Rubin,et al.  Maximum likelihood from incomplete data via the EM - algorithm plus discussions on the paper , 1977 .

[3]  Franco Turini,et al.  Discrimination-aware data mining , 2008, KDD.

[4]  Ghazala Azmat,et al.  Gender and the Labor Market: What Have We Learned from Field and Lab Experiments? , 2014, SSRN Electronic Journal.

[5]  Hans-Peter Kriegel,et al.  A Density-Based Algorithm for Discovering Clusters in Large Spatial Databases with Noise , 1996, KDD.

[6]  B. Ripley,et al.  Pattern Recognition , 1968, Nature.

[7]  J. Mincer.  Schooling, Experience, and Earnings , 1976 .

[8]  Hans-Peter Kriegel,et al.  OPTICS: ordering points to identify the clustering structure , 1999, SIGMOD '99.

[9]  Steffen Staab,et al.  Data Mining and Automated Discrimination: A Mixed Legal/Technical Perspective , 2016, IEEE Intelligent Systems.

[10]  R. Oaxaca.  Male-Female Wage Differentials in Urban Labor Markets , 1973 .

[11]  Diferencias salariales, características del puesto de trabajo y cualificación: un análisis para el período 2005-2010* , 2012 .

[12]  Luca Scrucca,et al.  mclust 5: Clustering, Classification and Density Estimation Using Gaussian Finite Mixture Models , 2016, R J..

[13]  Gary S. Becker,et al.  Human Capital Revisited , 1994 .

[14]  Josep Domingo-Ferrer,et al.  A Methodology for Direct and Indirect Discrimination Prevention in Data Mining , 2013, IEEE Transactions on Knowledge and Data Engineering.