Transparency and accountability in machine learning

Fairness-aware machine learning algorithms

Nowadays, many decisions are made using predictive models built on historical data, for example, automated CV screening of job applicants, credit scoring for loans, or profiling of potential suspects by the police. Algorithms decide upon the prices we pay, the people we meet, or the medicine we take. 

Growing evidence in the media and research suggests that decision making by algorithms can potentially discriminate people. This may happen even if the computing process is fair and well-intentioned. This is because most data mining methods are based upon assumptions that the historical data is correct, and represents the population well, which is often not true in reality. Moreover, usually predictive models are optimized for performing well in the majority of the cases, not taking into account who is affected the worst by the remaining inaccuracies.

Fairness-aware machine learning studies in which circumstances algorithms may become discriminatory, and how to make predictive models free from discrimination, when data, on which they are built, may be biased, incomplete, or even contain past discriminatory decisions. 

Selected publications

  • Measuring discrimination in algorithmic decision making by Žliobaitė 2017 in Data Mining and Knowledge DiscoveryPDF  DOI
  • Using sensitive personal data may be necessary for avoiding discrimination in data-driven decision models by Žliobaitė and Custers 2016 in Artificial Intelligence and LawDOI  PDF
  • On the relation between accuracy and fairness in binary classification by Žliobaitė 2015 in FATML workshop PDF  arXiv 
  • Why Unbiased Computational Processes Can Lead to Discriminative Decision Procedures by Calders and Žliobaitė 2013, a book chapterDOI  PDF
  • Explainable and Non-explainable Discrimination in Classification by Kamiran and Žliobaitė 2013, a book chapterDOI  PDF
  • Handling Conditional Discrimination by Žliobaitė et al. 2011 in IEEE ICDMDOI  PDF

Selected talks

  • May 2016 » Ethical machines: data mining and fairness AID-Forum, Helsinki summary
  • Jul 2015 » Can algorithms discriminate? at EU Fundamental Rights Agency, Vienna, Austria slides
  • May 2015 » Can machines discriminate? and how to avoid that, seminar talk at HIIT slides