University of Arkansas

About: University of Arkansas is a education organization based out in Fayetteville, Arkansas, United States. It is known for research contribution in the topics: Population & Poison control. The organization has 17225 authors who have published 33329 publications receiving 941102 citations. The organization is also known as: Arkansas & UA.

Going with the Flow: Predicting Online Purchase Intentions

Abstract: A theoretical model that combines flow theory with the Theory of Reasoned Action is proposed and empirically tested. Data was gathered via a sample survey, which was completed by 342 undergraduate college students. Two-phase structural equation modeling was utilized to verify construct validity and test proposed relationships. The study establishes the psychological state of flow as an important independent variable influencing both Web exploratory behavior and attitude toward purchasing online. In turn, attitude toward purchasing online was found to influence behavioral intentions to engage in online purchase transactions. Exploratory behavior was also identified as an independent variable exerting a significant effect on online purchasing attitude. The resultant model explains 60% of individuals' intentions to make purchases online. Key theoretical and managerial implications are discussed.

FairGAN: Fairness-aware Generative Adversarial Networks

Abstract: Fairness-aware learning is increasingly important in data mining. Discrimination prevention aims to prevent discrimination in the training data before it is used to conduct predictive analysis. In this paper, we focus on fair data generation that ensures the generated data is discrimination free. Inspired by generative adversarial networks (GAN), we present fairness-aware generative adversarial networks, called FairGAN, which are able to learn a generator producing fair data and also preserving good data utility. Compared with the naive fair data generation models, FairGAN further ensures the classifiers which are trained on generated data can achieve fair classification on real data. Experiments on a real dataset show the effectiveness of FairGAN.