My research interests lie broadly in Statistical Methodology, Statistical Machine Learning, and especially Fairness, Accountability and Transparency in Machine Learning. I am also very excited about targeting applied problems, particulary in the social sciences and education. Here are some recent projects.
Publications & Presentations
- Akpinar, Nil-Jana, Chouldechova, A. (2021) The effect of differential victim crime reporting on predictive policing systems. Conference on Fairness, Accountability, and Transparency (FAccT 2021), [paper, code].
- Akpinar, Nil-Jana, Ramdas, A., Acar, U. (2020) Analyzing Student Strategies In Blended Courses Using Clickstream Data. Thirteenth International Conference on Educational Data Mining (EDM 2020), [arXiv, video presentation].
- Akpinar, Nil-Jana, Kratzwald, B., Feuerriegel, S. (2020) Sample Complexity Bounds for Recurrent Neural Networks with Application to Combinatorial Graph Problems. Thirty-Fourth Conference on Artifical Intelligence (AAAI 2020) (Student Abstract), [long version, short version, poster].
- Akpinar, Nil-Jana, Feuerriegel, S. (2017) A Model-free Solver For Arbitrary Graph Problems: Predicting Solutions With Deep Learning, INFORMS Annual Meeting, Houston, Texas. (Presented by S. Feuerriegel).
- Akpinar, Nil-Jana, Alfano, S., Kersten, G., Yu, B. (2017). The Role of Sentiment and Cultural Differences in the Communation Process of e-Negotiations. In: Schoop M., Kilgour D. (eds) Group Decision and Negotiation. A Socio-Technical Perspective. GDN 2017. Springer, p.132-144, [paper].