Sahar Barmomanesh

profile image

PhD candidate, Lecturer



  • Bachelor of Science (Applied Mathematics), The University of Auckland
  • Master of Analytics (First Class Honours), Auckland University of Technology

Memberships and Affiliations:


Sahar is currently working as a lecturer in the School of Economics, teaching the Quantitative Foundation Skills paper. She has previously worked as teaching assistant in mathematics departments at both University of Auckland and AUT.

Teaching Areas:

  • Mathematics and Statistics

Research Areas:

  • Algorithmic fairness

Research Summary:

Machine learning (ML) is a field of computer science that provides computer systems with the ability to learn from historical data, without being explicitly programmed. Machine learning algorithms look for patterns in data and construct mathematical models that will assist in making predictions on the future data. Nowadays, predictive models are increasingly being used to make decisions for people and about people. Use of such models in making decision about individuals has raised concerns about their potential unfairness toward certain groups. Even though effectiveness of PRM has been proven in many fields (i.e. Insurance, Finance, Health), it has only lately been applied to the classification of risk in Child Protective Services (CPS). The main concern, when using predictive modelling in child welfare setting is predictive bias. If the predictive risk models are developed based on biased data to produce a risk score for a child, then this can aggravate the original bias. To improve decision making in the child welfare domain with the help of predictive risk models, it’s vital to ensure the model is fair and discrimination-free. The main objective of Sahar’s research is to create a fair algorithm and further to develop a non-discriminatory predictive risk model.

Current Research Projects:

  • Non-discriminatory predictive risk modelling in relation to child maltreatment


  1. Barmomanesh, S. & Vodanovich, S. (2017, April). Use of touch screen devices among children 0–5 years of age: Parental perception. In Computer Supported Cooperative Work in Design (CSCWD), 2017 IEEE 21st International Conference on (pp. 121-126). IEEE.


  • SAS joint certificate in Advanced Analytics