The evaluation of auto insurance risks is a fundamental task for financial institutions, crucial for setting equitable premiums and managing risks effectively. Traditional machine learning algorithms often struggle to capture the intricate relationships necessary for accurate risk assessment. In contrast, deep learning methods, while capable of processing complex data structures, lack the ability to model feature interactions and provide interpretability, which are essential for transparent decision-making in the insurance industry. To address these challenges, we introduce the Actuarial Transformer (AT)–a pioneering model that leverages the self-attention mechanism of the Transformer architecture to meticulously map feature interactions. The AT integrates advanced residual models with tree-based methods, enhancing its predictive accuracy. Additionally, it incorporates the SHAP (SHapley Additive exPlanations) model, which uses Shapley values from cooperative game theory to ensure interpretability and transparency in its risk assessments. Our empirical analysis, conducted on a representative dataset of auto insurance risks, demonstrates the AT’s superior performance in risk prediction. The SHAP analysis further validates the model’s ability to prioritize features logically, providing clear insights into the decision-making process. The AT not only improves the precision of auto insurance risk evaluations but also enhances the interpretability of these evaluations, making it a valuable tool for both industry practitioners and clients.

In the rapidly evolving online marketplace, accurately predicting the demand for pre-owned items presents a significant challenge for sellers, impacting pricing strategies, product presentation, and marketing investments. Traditional demand prediction methods, while foundational, often fall short in addressing the dynamic and heterogeneous nature of e-commerce data, which encompasses textual descriptions, visual elements, geographic contexts, and temporal dynamics. This paper introduces a novel approach utilizing the Graph Neural Network (GNN) to enhance demand prediction accuracy by leveraging the spatial relationships inherent in online sales data, named SGNN. Drawing from the rich dataset provided in the fourth Kaggle competition, we construct a spatially aware graph representation of the marketplace, integrating advanced attention mechanisms to refine predictive accuracy. Our methodology defines the product demand prediction problem as a regression task on an attributed graph, capturing both local and global spatial dependencies that are fundamental to accurate predicting. Through attention-aware message propagation and node-level demand prediction, our model effectively addresses the multifaceted challenges of e-commerce demand prediction, demonstrating superior performance over traditional statistical methods, machine learning techniques, and even deep learning models. The experimental findings validate the effectiveness of our GNN-based approach, offering actionable insights for sellers navigating the complexities of the online marketplace. This research not only contributes to the academic discourse on e-commerce demand prediction but also provides a scalable and adaptable framework for future applications, paving the way for more informed and effective online sales strategies.

Image guided depth completion is the task of generating a dense depth map from a sparse depth map and a high quality image. In this task, how to fuse the color and depth modalities plays an important role in achieving good performance. This paper proposes a two-branch backbone that consists of a color-dominant branch and a depth-dominant branch to exploit and fuse two modalities thoroughly. More specifically, one branch inputs a color image and a sparse depth map to predict a dense depth map. The other branch takes as inputs the sparse depth map and the previously predicted depth map, and outputs a dense depth map as well. The depth maps predicted from two branches are complimentary to each other and therefore they are adaptively fused. In addition, we also propose a simple geometric convolutional layer to encode 3D geometric cues. The geometric encoded backbone conducts the fusion of different modalities at multiple stages, leading to good depth completion results. We further implement a dilated and accelerated CSPN++ to refine the fused depth map efficiently. The proposed full model ranks 1st in the KITTI depth completion online leaderboard at the time of submission. It also infers much faster than most of the top ranked methods. The code of this work is available at https://github.com/JUGGHM/PENet_ICRA2021.