Furkan Gürsoy

Furkan Gursoy, Ioannis A. Kakadiaris

Decisions impacting human lives are increasingly being made or assisted by automated decision-making algorithms. Many of these algorithms process personal data for predicting recidivism, credit risk analysis, identifying individuals using face recognition, and more. While potentially improving efficiency and effectiveness, such algorithms are not inherently free from bias, opaqueness, lack of explainability, maleficence, and the like. Given that the outcomes of these algorithms have a significant impact on individuals and society and are open to analysis and contestation after deployment, such issues must be accounted for before deployment. Formal audits are a way of ensuring algorithms meet the appropriate accountability standards. This work, based on an extensive analysis of the literature and an expert focus group study, proposes a unifying framework for a system accountability benchmark for formal audits of artificial intelligence-based decision-aiding systems. This work also proposes system cards to serve as scorecards presenting the outcomes of such audits. It consists of 56 criteria organized within a four-by-four matrix composed of rows focused on (i) data, (ii) model, (iii) code, (iv) system, and columns focused on (a) development, (b) assessment, (c) mitigation, and (d) assurance. The proposed system accountability benchmark reflects the state-of-the-art developments for accountable systems, serves as a checklist for algorithm audits, and paves the way for sequential work in future research.

Furkan Gursoy, Ioannis A. Kakadiaris

The applications of Artificial Intelligence (AI) surround decisions on increasingly many aspects of human lives. Society responds by imposing legal and social expectations for the accountability of such automated decision systems (ADSs). Fairness, a fundamental constituent of AI accountability, is concerned with just treatment of individuals and sensitive groups (e.g., based on sex, race). While many studies focus on fair learning and fairness testing for the classification tasks, the literature is rather limited on how to examine fairness in regression tasks. This work presents error parity as a regression fairness notion and introduces a testing methodology to assess group fairness based on a statistical hypothesis testing procedure. The error parity test checks whether prediction errors are distributed similarly across sensitive groups to determine if an ADS is fair. It is followed by a suitable permutation test to compare groups on several statistics to explore disparities and identify impacted groups. The usefulness and applicability of the proposed methodology are demonstrated via a case study on COVID-19 projections in the US at the county level, which revealed race-based differences in forecast errors. Overall, the proposed regression fairness testing methodology fills a gap in the fair machine learning literature and may serve as a part of larger accountability assessments and algorithm audits.

Furkan Gursoy, Ioannis A. Kakadiaris

As artificial intelligence plays an increasingly substantial role in decisions affecting humans and society, the accountability of automated decision systems has been receiving increasing attention from researchers and practitioners. Fairness, which is concerned with eliminating unjust treatment and discrimination against individuals or sensitive groups, is a critical aspect of accountability. Yet, for evaluating fairness, there is a plethora of fairness metrics in the literature that employ different perspectives and assumptions that are often incompatible. This work focuses on group fairness. Most group fairness metrics desire a parity between selected statistics computed from confusion matrices belonging to different sensitive groups. Generalizing this intuition, this paper proposes a new equal confusion fairness test to check an automated decision system for fairness and a new confusion parity error to quantify the extent of any unfairness. To further analyze the source of potential unfairness, an appropriate post hoc analysis methodology is also presented. The usefulness of the test, metric, and post hoc analysis is demonstrated via a case study on the controversial case of COMPAS, an automated decision system employed in the US to assist judges with assessing recidivism risks. Overall, the methods and metrics provided here may assess automated decision systems' fairness as part of a more extensive accountability assessment, such as those based on the system accountability benchmark.

Eric Ingram, Furkan Gursoy, Ioannis A. Kakadiaris

Criminal recidivism models are tools that have gained widespread adoption by parole boards across the United States to assist with parole decisions. These models take in large amounts of data about an individual and then predict whether an individual would commit a crime if released on parole. Although such models are not the only or primary factor in making the final parole decision, questions have been raised about their accuracy, fairness, and interpretability. In this paper, various machine learning-based criminal recidivism models are created based on a real-world parole decision dataset from the state of Georgia in the United States. The recidivism models are comparatively evaluated for their accuracy, fairness, and interpretability. It is found that there are noted differences and trade-offs between accuracy, fairness, and being inherently interpretable. Therefore, choosing the best model depends on the desired balance between accuracy, fairness, and interpretability, as no model is perfect or consistently the best across different criteria.

Furkan Gürsoy, Bertan Badur

Human migration patterns influence the redistribution of population characteristics over the geography and since such distributions are closely related to social and economic outcomes, investigating the structure and dynamics of internal migration plays a crucial role in understanding and designing policies for such systems. We provide an in-depth investigation into the structure and dynamics of the internal migration in Turkey from 2008 to 2020. We identify a set of classical migration laws and examine them via various methods for signed network analysis, ego network analysis, representation learning, temporal stability analysis, community detection, and network visualization. The findings show that, in line with the classical migration laws, most migration links are geographically bounded with several exceptions involving cities with large economic activity, major migration flows are countered with migration flows in the opposite direction, there are well-defined migration routes, and the migration system is generally stable over the investigated period. Apart from these general results, we also provide unique and specific insights into Turkey. Overall, the novel toolset we employ for the first time in the literature allows the investigation of selected migration laws from a complex networks perspective and sheds light on future migration research on different geographies.

Mahsun Altın, Furkan Gürsoy, Lina Xu

Deep-learning based computer vision models have proved themselves to be ground-breaking approaches to human activity recognition (HAR). However, most existing works are dedicated to improve the prediction accuracy through either creating new model architectures, increasing model complexity, or refining model parameters by training on larger datasets. Here, we propose an alternative idea, differing from existing work, to increase model accuracy and also to shape model predictions to align with human understandings through automatically creating higher-level summarizing labels for similar groups of human activities. First, we argue the importance and feasibility of constructing a hierarchical labeling system for human activity recognition. Then, we utilize the predictions of a black box HAR model to identify similarities between different activities. Finally, we tailor hierarchical clustering methods to automatically generate hierarchical trees of activities and conduct experiments. In this system, the activity labels on the same level will have a designed magnitude of accuracy and reflect a specific amount of activity details. This strategy enables a trade-off between the extent of the details in the recognized activity and the user privacy by masking some sensitive predictions; and also provides possibilities for the use of formerly prohibited invasive models in privacy-concerned scenarios. Since the hierarchy is generated from the machine's perspective, the predictions at the upper levels provide better accuracy, which is especially useful when there are too detailed labels in the training set that are rather trivial to the final prediction goal. Moreover, the analysis of the structure of these trees can reveal the biases in the prediction model and guide future data collection strategies.

Furkan Gürsoy, Mounir Haddad, Cécile Bothorel

Representation learning (RL) methods learn objects' latent embeddings where information is preserved by distances. Since distances are invariant to certain linear transformations, one may obtain different embeddings while preserving the same information. In dynamic systems, a temporal difference in embeddings may be explained by the stability of the system or by the misalignment of embeddings due to arbitrary transformations. In the literature, embedding alignment has not been defined formally, explored theoretically, or analyzed empirically. Here, we explore the embedding alignment and its parts, provide the first formal definitions, propose novel metrics to measure alignment and stability, and show their suitability through synthetic experiments. Real-world experiments show that both static and dynamic RL methods are prone to produce misaligned embeddings and such misalignment worsens the performance of dynamic network inference tasks. By ensuring alignment, the prediction accuracy raises by up to 90% in static and by 40% in dynamic RL methods.

Furkan Gursoy, Ahmet Onur Durahim

Diffusion reach probability between two nodes on a network is defined as the probability of a cascade originating from one node reaching to another node. An infinite number of cascades would enable calculation of true diffusion reach probabilities between any two nodes. However, there exists only a finite number of cascades and one usually has access only to a small portion of all available cascades. In this work, we addressed the problem of estimating diffusion reach probabilities given only a limited number of cascades and partial information about underlying network structure. Our proposed strategy employs node representation learning to generate and feed node embeddings into machine learning algorithms to create models that predict diffusion reach probabilities. We provide experimental analysis using synthetically generated cascades on two real-world social networks. Results show that proposed method is superior to using values calculated from available cascades when the portion of cascades is small.