Full-complexity machine learning models, such as the deep neural network, are non-traceable black-box, whereas the classic interpretable models, such as linear regression models, are often over-simplified, leading to lower accuracy. Model interpretability limits the application of machine learning models in management problems, which requires high prediction performance, as well as the understanding of individual features’ contributions to the model outcome. To enhance model interpretability while preserving good prediction performance, we propose a hybrid interpretable model that combines a piecewise linear component and a nonlinear component. The first component describes the explicit feature contributions by piecewise linear approximation to increase the expressiveness of the model. The other component uses a multi-layer perceptron to increase the prediction performance by capturing the high-order interactions between features and their complex nonlinear transformations. The interpretability is obtained once the model is learned in the form of shape functions for the main effects. We also provide a variant to explore the higher-order interactions among features. Experiments are conducted on synthetic and real-world datasets to demonstrate that the proposed models can achieve good interpretability by explicitly describing the main effects and the interaction effects of the features while maintaining state-of-the-art accuracy.

In real-time bidding systems, ad exchanges and supply-side platforms (SSP) are switching from the second-price auction (SPA) to the first-price auction (FPA), where the advertisers should pay what they bid if they win the auction. To avoid overpaying, advertisers are motivated to conceal their truthful evaluations of impression opportunities through bid shading methods. However, advertisers are consistently facing a trade-off between the probability and cost-saving of winning, due to the information asymmetry, where advertisers lack knowledge about their competitors' bids in the market. To address this challenge, we propose a Bayes ian Multi-Armed Bandit (BayesMAB) algorithm for bid shading when the winning price is unknown to advertisers who lose the impression opportunity. BayesMAB incorporates the mechanism of FPA to infer each price interval's winning rate by progressively updating the market price hidden by SSP. In this way, BayesMAB better approximates the winning rates of price intervals and thus is able to derive the optimal shaded bid that balances the trade-off between the probability and cost-saving of winning the impression opportunity. We conducted large-scale A/B tests on Tencent's online display advertising platform. The cost-per-mile (CPM) and cost-per-action (CPA) decreased by 13.06% and 11.90%, respectively, whereas the return on investment (ROI) increased by 12.31% with only 2.7% sacrifice of the winning rate. We also validated BayesMAB's superior performance in an offline semi-simulated experiment with SPA data sets. BayesMAB has been deployed online and is impacting billions of traffic every day. Codes are available at https://github.com/BayesMAB/BayesMAB.

Artificial Intelligence (AI) in drug discovery is a rapidly evolving field that combines computational methods with biological knowledge and applications. Traditionally, the process of developing a new drug has been time-consuming and expensive, spanning several years and costing billions of dollars. The emergence of AI technologies offers the potential to significantly reduce both the timeline and cost involved in this critical endeavour. However, it is crucial to acknowledge that AI applications in pharmacy and drug discovery require a high degree of interpretability and transparency. The integration of domain knowledge into AI models becomes paramount to ensure the reliability and trustworthiness of the generated results. In light of these considerations, we propose a workshop on "Knowledge-enhanced Artificial Intelligence in Drug Discovery (KAIDD)." This workshop aims to explore the profound impact of incorporating various knowledge databases into the development of explainable AI models for drug discovery. Participants will have the opportunity to delve into cutting-edge research, methodologies, and practical applications that leverage the fusion of AI techniques with domain-specific knowledge. Authors of accepted papers will have the opportunity to submit extended versions of their work for a full-paper review process and potential publication in Philosophical Transactions of the Royal Society B.

The real-time bidding (RTB) paradigm allows the advertisers to submit a bid for each impression in online display advertising. A usual demand of the advertisers is to maximize the total value of winning impressions under constraints on some key performance indicators. Unfortunately, the existing RTB research in industrial applications can hardly achieve the optimum due to the stochastic decision scenarios and complex consumer behaviors. In this study, we address the application of RTB to mobile gaming where the in-app purchase action is of high uncertainty, making it challenging to evaluate individual impression opportunities. We first formulate the bidding process into a constrained optimization problem and then propose an actor-critic reinforcement learning (ACRL) model for obtaining the optimal policy under a dynamic decision environment. To avoid feeding too many samples with zero labels to the model, we provide a new way to quantify impression opportunities by integrating the in-app actions, such as conversion and purchase, and the characteristics of the candidate ad inventories. Moreover, the proposed ACRL learns a Gaussian distribution to simulate the audience's decision in a more real bidding scenario by taking additional contextual side information about both media and the audience. We also introduce how to deploy the learned model online to help adjust the final bid. At last, we conduct comprehensive offline experiments to demonstrate the effectiveness of ACRL and carefully set an online A/B testing experiment. The online experimental results verify the efficacy of the proposed ACRL in terms of multiple critical commercial indicators. ACRL has been deployed in the Tencent online display advertising platform and impacts billions of traffic every day. We believe proposed modifications for optimal bidding problems in RTB are practically innovative and can inspire the relative works in this field.

Abstract Collaborator recommendation is of great significance for facilitating research collaboration. Proximities have been demonstrated to be significant factors and determinants of research collaboration. Research leadership is associated with not only the capability to integrate resources to launch and sustain the research project but also the production and academic impact of the collaboration team. However, existing studies mainly focus on social or cognitive proximity, failing to integrate critical proximities comprehensively. Besides, existing studies focus on recommending relationships among all the coauthors, ignoring leadership in research collaboration. In this article, we propose a proximity‐aware research leadership recommendation (PRLR) model to systematically integrate critical node attribute information (critical proximities) and network features to conduct research leadership recommendation by predicting the directed links in the research leadership network. PRLR integrates cognitive, geographical, and institutional proximity as node attribute information and constructs a leadership‐aware coauthorship network to preserve the research leadership information. PRLR learns the node attribute information, the local network features, and the global network features with an autoencoder model, a joint probability constraint, and an attribute‐aware skip‐gram model, respectively. Extensive experiments and ablation studies have been conducted, demonstrating that PRLR significantly outperforms the state‐of‐the‐art collaborator recommendation models in research leadership recommendation.

Ordinal regression predicts the objects’ labels that exhibit a natural ordering, which is vital to decision-making problems such as credit scoring and clinical diagnosis. In these problems, the ability to explain how the individual features and their interactions affect the decisions is as critical as model performance. Unfortunately, the existing ordinal regression models in the machine learning community aim at improving prediction accuracy rather than explore explainability. To achieve high accuracy while explaining the relationships between the features and the predictions, we propose a new method for ordinal regression problems, namely the Explainable Ordinal Factorization Model (XOFM). XOFM uses piecewise linear functions to approximate the shape functions of individual features, and renders the pairwise features interaction effects as heat-maps. The proposed XOFM captures the nonlinearity in the main effects and ensures the interaction effects’ same flexibility. Therefore, the underlying model yields comparable performance while remaining explainable by explicitly describing the main and interaction effects. To address the potential sparsity problem caused by discretizing the whole feature scale into several sub-intervals, XOFM integrates the Factorization Machines (FMs) to factorize the model parameters. Comprehensive experiments with benchmark real-world and synthetic datasets demonstrate that the proposed XOFM leads to state-of-the-art prediction performance while preserving an easy-to-understand explainability.

Abstract Characterizing the leadership in research is important to revealing the interaction pattern and organizational structure through research collaboration. This research defines the leadership role based on the corresponding author's affiliation, and presents the first quantitative research on the factors and evolution of 5 proximity dimensions (geographical, cognitive, institutional, social, and economic) of research leadership. The data to capture research leadership consist of a set of multi‐institution articles in the fields of “Life Sciences & Biomedicine,” “Technology,” “Physical Sciences,” “Social Sciences,” and “Humanities & Arts” during 2013–2017 from the Web of Science Core Citation Database. A Tobit regression‐based gravity model indicates that the mass of research leadership of both the leading and participating institutions and the geographical, cognitive, institutional, social, and economic proximities are important factors for the flow of research leadership among Chinese institutions. In general, the effect of these proximities for research leadership flow has been declining recently. The outcome of this research sheds light on the leadership evolution and flow among Chinese institutions, and thus can provide evidence and support for grant allocation policies to facilitate scientific research and collaborations.