Search

The use of Artificial Intelligence (AI) based on data-driven algorithms has become ubiquitous in today's society. Yet, in many cases and especially when stakes are high, humans still make final decisions. The critical question, therefore, is whether AI helps humans make better decisions as compared to a human alone or AI an alone. We introduce a new methodological framework that can be used to answer experimentally this question with no additional assumptions. We measure a decision maker's ability to make correct decisions using standard classification metrics based on the baseline potential outcome. We consider a single-blinded experimental design, in which the provision of AI-generated recommendations is randomized across cases with a human making final decisions. Under this experimental design, we show how to compare the performance of three alternative decision-making systems--human-alone, human-with-AI, and AI-alone. We apply the proposed methodology to the data from our own randomized controlled trial of a pretrial risk assessment instrument. We find that AI recommendations do not improve the classification accuracy of a judge's decision to impose cash bail. Our analysis also shows that AI-alone decisions generally perform worse than human decisions with or without AI assistance. Finally, AI recommendations tend to impose cash bail on non-white arrestees more often than necessary when compared to white arrestees.

Data-driven decision making plays an important role even in high stakes settings like medicine and public policy. Learning optimal policies from observed data requires a careful formulation of the utility function whose expected value is maximized across a population. Although researchers typically use utilities that depend on observed outcomes alone, in many settings the decision maker's utility function is more properly characterized by the joint set of potential outcomes under all actions. For example, the Hippocratic principle to "do no harm" implies that the cost of causing death to a patient who would otherwise survive without treatment is greater than the cost of forgoing life-saving treatment. We consider optimal policy learning with asymmetric counterfactual utility functions of this form that consider the joint set of potential outcomes. We show that asymmetric counterfactual utilities lead to an unidentifiable expected utility function, and so we first partially identify it. Drawing on statistical decision theory, we then derive minimax decision rules by minimizing the maximum expected utility loss relative to different alternative policies. We show that one can learn minimax loss decision rules from observed data by solving intermediate classification problems, and establish that the finite sample excess expected utility loss of this procedure is bounded by the regret of these intermediate classifiers. We apply this conceptual framework and methodology to the decision about whether or not to use right heart catheterization for patients with possible pulmonary hypertension.

Liquid crystalline networks (LCNs, including liquid crystalline elastomers), a type of stimuli-responsive polymers with reversible and macroscopic deformations induced by order-disorder phase transition, are promising candidates for building stimuli-controlled deformable, mobile and soft robotic systems. In the past few decades, numerous methods have been exploited to prepare sophisticated LCN actuators, such as four-dimensional printing, pattern-crosslinking and photoalignment. Although the LCN field has undergone explosive development, the fabricated LCN cannot be reprogrammed to exhibit a different actuation behavior, or reprocessed into a new on-demand geometry because of the covalent crosslinking, which limits the application of LCN actuators. To eliminate these drawbacks, dynamic covalent bonds (DCB), especially reversibly exchangeable bonds (such as exchangeable ester bonds, carbamate bonds, siloxane bonds, etc.) are introduced into LCN to replace permanent covalent bonds. These liquid crystalline dynamic networks (LCDNs) can be easily programmed into monodomain actuators through topological rearrangement of polymer networks and further exhibit thermomechanical or photomechanical responses. Meanwhile, DCB can also endow LCN actuators with some other important features, such as reprocessablility, recyclability and self-healing capability, due to their dynamic nature. However, there is still a need to develop novel LCDN actuators to further enhance the ability to fabricate actuators with any desired shapes and optimize the manufacturing conditions. On the one hand, the reprogramming of LCDNs based on exchangeable bonds requires reshaping the material and maintaining its deformation under harsh conditions (such as high temperature) for a long period, and these exchangeable networks cannot be fabricated into complex geometries through solution casting or melt processing because they are insoluble and infusible. These issues limit the actuation diversity, Les réseaux cristallins liquides, abrégé en LCN (liquid crystalline network), sont des matériaux choix pour faire des actionneurs capables de déformer de manière réversible sous stimuli, résultant de la transition entre une phase LC (ordre) et l’état isotrope (désordre). En vue de leur application pour la robotique souple, il est important de développer des actionneurs LCN pouvant être reconfigurés ou reprogrammés. Par reconfiguration, on parle d’un même actionneur qui, après sa fabrication et selon le traitement imposé sur lui, peut montrer un changement de forme différent sous l’effet de la même stimulation. Quant à un actionneur reprogrammable, il peut simplement être remis en œuvre pour un nouvel actionneur avec une nouvelle architecture (ou géométrie) et un nouveau mode de déformation. L’obtention de ces fonctionnalités n’est pas chose facile à cause de la réticulation de chaînes qui, comme dans tous les polymères réticulés par liaisons covalentes, empêche la remise en forme. L’objectif de cette thèse est donc d’explorer l’utilisation des liaisons covalentes dynamiques pour la réticulation dans les actionneurs LCN et de développer de nouvelles approches menant à la reconfiguration ou à la reprogrammation d’actionneurs LCN. Pour la reconfiguration, basé sur un design rationnel, nous avons synthétisé un LCN portant l’anthracène dans des groupes latéraux, ce qui confère au LCN une réticulation de chaînes ajustable par une photoréaction réversible. En effet, la dimérisation du chromophore par absorption de la lumière ultraviolet (UV) aux alentours de 365 nm permet la réticulation, alors qu’une irradiation UV aux longueurs d’onde plus courtes, environ 254 nm, peut briser le dimère et ainsi déréticuler le LCN. Nous avons démontré qu’après la préparation d’un actionneur ayant un alignement uniaxe des mésogènes et une réticulation uniforme, la dé-réticulation peut être appliquée de façon progressive pour supprimer la fonction d’actionnement dans des zones sélectionnées

Algorithmic recommendations and decisions have become ubiquitous in today's society. Many of these and other data-driven policies, especially in the realm of public policy, are based on known, deterministic rules to ensure their transparency and interpretability. For example, algorithmic pre-trial risk assessments, which serve as our motivating application, provide relatively simple, deterministic classification scores and recommendations to help judges make release decisions. How can we use the data based on existing deterministic policies to learn new and better policies? Unfortunately, prior methods for policy learning are not applicable because they require existing policies to be stochastic rather than deterministic. We develop a robust optimization approach that partially identifies the expected utility of a policy, and then finds an optimal policy by minimizing the worst-case regret. The resulting policy is conservative but has a statistical safety guarantee, allowing the policy-maker to limit the probability of producing a worse outcome than the existing policy. We extend this approach to common and important settings where humans make decisions with the aid of algorithmic recommendations. Lastly, we apply the proposed methodology to a unique field experiment on pre-trial risk assessment instruments. We derive new classification and recommendation rules that retain the transparency and interpretability of the existing instrument while potentially leading to better overall outcomes at a lower cost.

Cross domain recommender system constitutes a powerful method to tackle the cold-start and sparsity problem by aggregating and transferring user preferences across multiple category domains. Therefore, it has great potential to improve click-through-rate prediction performance in online commerce platforms having many domains of products. While several cross domain sequential recommendation models have been proposed to leverage information from a source domain to improve CTR predictions in a target domain, they did not take into account bidirectional latent relations of user preferences across source-target domain pairs. As such, they cannot provide enhanced cross-domain CTR predictions for both domains simultaneously. In this paper, we propose a novel approach to cross-domain sequential recommendations based on the dual learning mechanism that simultaneously transfers information between two related domains in an iterative manner until the learning process stabilizes. In particular, the proposed Dual Attentive Sequential Learning (DASL) model consists of two novel components Dual Embedding and Dual Attention, which jointly establish the two-stage learning process: we first construct dual latent embeddings that extract user preferences in both domains simultaneously, and subsequently provide cross-domain recommendations by matching the extracted latent embeddings with candidate items through dual-attention learning mechanism. We conduct extensive offline experiments on three real-world datasets to demonstrate the superiority of our proposed model, which significantly and consistently outperforms several state-of-the-art baselines across all experimental settings. We also conduct an online A/B test at a major video streaming platform Alibaba-Youku, where our proposed model significantly improves business performance over the latest production system in the company., Comment: Accepted to KDD21

Classical recommender system methods typically face the filter bubble problem when users only receive recommendations of their familiar items, making them bored and dissatisfied. To address the filter bubble problem, unexpected recommendations have been proposed to recommend items significantly deviating from user's prior expectations and thus surprising them by presenting "fresh" and previously unexplored items to the users. In this paper, we describe a novel Personalized Unexpected Recommender System (PURS) model that incorporates unexpectedness into the recommendation process by providing multi-cluster modeling of user interests in the latent space and personalized unexpectedness via the self-attention mechanism and via selection of an appropriate unexpected activation function. Extensive offline experiments on three real-world datasets illustrate that the proposed PURS model significantly outperforms the state-of-the-art baseline approaches in terms of both accuracy and unexpectedness measures. In addition, we conduct an online A/B test at a major video platform Alibaba-Youku, where our model achieves over 3\% increase in the average video view per user metric. The proposed model is in the process of being deployed by the company., Comment: Accepted to RecSys20

Using the concept of principal stratification from the causal inference literature, we introduce a new notion of fairness, called principal fairness, for human and algorithmic decision-making. The key idea is that one should not discriminate among individuals who would be similarly affected by the decision. Unlike the existing statistical definitions of fairness, principal fairness explicitly accounts for the fact that individuals can be impacted by the decision. Furthermore, we explain how principal fairness differs from the existing causality-based fairness criteria. In contrast to the counterfactual fairness criteria, for example, principal fairness considers the effects of decision in question rather than those of protected attributes of interest. We briefly discuss how to approach empirical evaluation and policy learning problems under the proposed principal fairness criterion.

Despite an increasing reliance on fully-automated algorithmic decision-making in our day-to-day lives, human beings still make highly consequential decisions. As frequently seen in business, healthcare, and public policy, recommendations produced by algorithms are provided to human decision-makers to guide their decisions. While there exists a fast-growing literature evaluating the bias and fairness of such algorithmic recommendations, an overlooked question is whether they help humans make better decisions. We develop a statistical methodology for experimentally evaluating the causal impacts of algorithmic recommendations on human decisions. We also show how to examine whether algorithmic recommendations improve the fairness of human decisions and derive the optimal decision rules under various settings. We apply the proposed methodology to preliminary data from the first-ever randomized controlled trial that evaluates the pretrial Public Safety Assessment (PSA) in the criminal justice system. A goal of the PSA is to help judges decide which arrested individuals should be released. On the basis of the preliminary data available, we find that providing the PSA to the judge has little overall impact on the judge's decisions and subsequent arrestee behavior. However, our analysis yields some potentially suggestive evidence that the PSA may help avoid unnecessarily harsh decisions for female arrestees regardless of their risk levels while it encourages the judge to make stricter decisions for male arrestees who are deemed to be risky. In terms of fairness, the PSA appears to increase the gender bias against males while having little effect on any existing racial differences in judges' decision. Finally, we find that the PSA's recommendations might be unnecessarily severe unless the cost of a new crime is sufficiently high.