A new algorithm for the group minimization problem (GP) is proposed. The algorithm can be broadly described as follows …-known algorithm of Glover, and checked for non-negativity. The first non-negative point is an optimal solution of (GP). Advantages and … disadvantages of the algorithm are discussed; in particular, the implementation of the algorithm (which can be easily extended so as …

objective function for the algorithm designer and a model of their information sets and interaction. We build such a model that … allows the training data to exhibit a wide range of "biases." Prevailing wisdom is that biased data change how the algorithm … is trained and whether an algorithm should be used at all. In contrast, we find two striking irrelevance results. First …

algorithm in terms of model complexity or the number of predictors to accommodate. Each firm then appoints a data analyst that … uses the chosen algorithm to estimate demand for multiple consumer segments, based on which, it devises a targeting policy …

structure is relevant in many applications. We develop the theory underlying optimal menus of non-linear schedules and prove …

new quasi-experimental tools to measure the impact of human discretion over an algorithm on the accuracy of decisions … judges in our setting underperform the algorithm when they make a discretionary override, with most making override decisions … that are no better than random. Yet the remaining 10% of judges outperform the algorithm in terms of both accuracy and …

number of possible approaches to these problems and develops a particular algorithm based on the work of Powell and Dennis …

algorithm's treatment recommendation. We then show how these four moments can be estimated by extrapolating quasi … learning algorithm discriminates against Black defendants, even though defendant race and ethnicity are not included in the … training data. The algorithm recommends releasing white defendants before trial at an 8 percentage point (11 percent) higher …