The retail industry faces increasing challenges in matching supply with demand due to evolving consumer behaviors, market volatility, and supply chain disruptions. While existing approaches employ statistical and machine learning methods for demand forecasting, they often fail to capture complex temporal dependencies and lack the ability to simultaneously optimize inventory decisions. This paper proposes a novel multi-agent deep reinforcement learning framework that jointly optimizes demand forecasting and inventory management in retail supply chains, leveraging data from IoT sensors, RFID tracking systems, and smart shelf monitoring devices. Our approach combines transformer-based sequence modeling for demand patterns with hierarchical reinforcement learning agents that coordinate inventory decisions across distribution networks. The framework integrates both historical sales data and real-time sensor measurements, employing attention mechanisms to capture seasonal patterns, promotional effects, and environmental conditions detected through temperature and humidity sensors. Through extensive experiments on large-scale retail datasets incorporating sensor network data, we demonstrate that our method achieves 18.2% lower forecast error and 23.5% reduced stockout rates compared with state-of-the-art baselines. The results show particular improvements in handling promotional events and seasonal transitions, where traditional methods often struggle. Our work provides new insights into leveraging deep reinforcement learning for integrated retail operations optimization and offers a scalable solution for modern sensor-enabled supply chain challenges.

With the proliferation of mobile devices and payment systems in modern financial services, there is an increasing need to process and analyze continuous streams of transaction data for credit risk assessment. Leveraging the inherent symmetries in financial markets and data structures, this paper introduces DeepCreditRisk, a symmetry-aware deep learning framework that addresses key challenges while maintaining critical invariance properties in financial data representation. The framework incorporates three main components: an adaptive temporal fusion mechanism, a heterogeneous graph neural network, and an attention-based interpretable output layer. The temporal fusion mechanism effectively models both short-term fluctuations and long-term trends in financial time series, while the heterogeneous graph neural network captures intricate relationships within the financial ecosystem. The framework maintains important symmetrical properties in both temporal and structural representations, ensuring balanced feature learning and invariant risk assessment. The attention-based output layer preserves representation symmetry while enhancing model interpretability. Extensive experiments on a large-scale credit risk dataset demonstrate DeepCreditRisk’s superior performance, achieving a 7.2% improvement in the Area Under the Receiver Operating Characteristic Curve (AUC-ROC) and an 18.6% improvement in the Kolmogorov–Smirnov (KS) statistic over state-of-the-art baseline models. The framework maintains high predictive power across various time horizons and provides interpretable insights into feature importance. DeepCreditRisk represents a significant advancement in applying deep learning to credit risk assessment, offering financial institutions a more accurate, robust, and transparent approach for evaluating creditworthiness and managing risk.

Maximizing information transfer across different structural scales is critical for effective molecular representation learning. Current molecular graph neural networks fail to fully capture the multi-scale nature of molecular geometry, leading to suboptimal information propagation between local and global structural features. We propose Multi-Scale Geometric Pre-training (MSG-Pre), an information-theoretic framework that hierarchically integrates molecular information across atomic, functional group, and conformer levels through entropy-guided mechanisms. Our approach employs a scale-adaptive attention mechanism that dynamically weights geometric features based on their information content, coupled with a hierarchical contrastive learning scheme that maximizes mutual information between complementary structural views. This is further reinforced by a geometric regularization strategy that minimizes information loss of essential conformational properties. Rigorous empirical validation on 14 molecular benchmark datasets demonstrates state-of-the-art performance with improvements up to 5.2% over previous methods. Notably, MSG-Pre significantly enhances information extraction for nanomedicine applications including nanoparticle-protein interactions and surface functionalization efficacy. Theoretical analysis reveals that MSG-Pre effectively maximizes cross-scale mutual information while minimizing intra-scale redundancy, maintaining an optimal information-entropy balance in molecular representations. Our work establishes an information-theoretic foundation for geometric pre-training that improves molecular understanding and enhances prediction capabilities for both drug discovery and nanomaterial design applications.

Machine-learning models routinely outperform the generalized linear models (GLMs) that dominate regulated underwriting practice, yet they rarely reach production because their predictions cannot be decomposed into the auditable rating factors that internal validation, filing, and governance processes require, and because their behaviour in thinly supported regions of the portfolio is difficult to certify. We propose Credibility-Gated Anchored Boosting (CGAB), a hybrid architecture with three tightly coupled components: (i) a rating-band GLM whose linear predictor anchors a gradient-boosting machine through its offset, so that the machine-learning layer learns only a multiplicative correction to the regulatory tariff; (ii) domain monotonicity constraints imposed on the correction, followed by a one-constant balance recalibration of the composite model; and (iii) a novel credibility gate that shrinks every leaf of the fitted ensemble by the Bühlmann factor zℓ = Eℓ/(Eℓ +κ), where Eℓ is the training exposure routed to leaf ℓ, implemented by direct model surgery on the fitted ensemble. Because the gate acts linearly on leaf values, the gated model remains a standard tree ensemble: exact TreeSHAP attributions in the log link decompose every prediction, without approximation error, into per-factor multiplicative relativities that combine with the GLM tariff into a policy-level audit sheet. On 677,991 French motor third-party liability policies, CGAB improves test Poisson deviance by 0.83% and Gini lift by nine percent relative to the GLM, while conceding 1.38% of deviance to an unconstrained LightGBM of identical capacity-an explicit, quantified price for the guarantee bundle of monotonicity, tariff traceability, and credibility control, with each component's individual cost isolated by ablation. The credibility gate implements graceful degradation towards the filed tariff: under 5-10% training subsamples it improves deviance over ungated boosting by more than one percent, and on a small Australian portfolio, where no machine-learning model beats the GLM, it recovers most of the lost ground while unanchored boosting falls furthest behind; on heavy-tailed severity data, unanchored gamma boosting diverges catastrophically while the anchored model remains close to the GLM and attains the best mean absolute error. The audit decomposition is exact to machine precision (maximum reconstruction error 3.8 × 10-15), turning every prediction into a verifiable rate calculation rather than a post-hoc approximation.

The inverse design of resilient infrastructure materials is hindered by the combinatorial complexity inherent in optimizing stochastic, heterogeneous microstructures. Traditional Euclidean deep learning architectures, such as Convolutional Neural Networks (CNNs), fail to efficiently encode the sparse, non-local topology of disordered porous media, resulting in prohibitive computational redundancy. This work articulates a comprehensive graph-theoretic framework for the predictive modeling and optimization of self-healing cementitious composites. We propose a robust methodology for discretizing volumetric tomography into permutation-invariant heterogeneous graphs, where nodes encode discrete physical entities (aggregates, pores, and microcapsules) and edges represent mechanical and hydraulic connectivity. To capture global fracture dynamics and local transport phenomena, we employ specialized architectures, specifically Pore-GNNs and Long-Short-Edge MeshGraphNets, which function as high-speed surrogate models for multiphysics simulations. Computational validation against high-fidelity numerical solvers confirms the system’s efficacy: the proposed architecture achieves approximately 1.1×105-fold acceleration (inference plus preprocessing) in permeability prediction relative to Lattice Boltzmann Method simulations, while maintaining a prediction accuracy of R2 > 0.94 (mean±std over five random splits); the inference-only speedup, which excludes one-time graph-construction preprocessing, is approximately 1.8×106-fold. We note that the end-to-end figure (1.1×105) supersedes the inference-only figure quoted in the original submission metadata. Furthermore, the framework autonomously navigated the high-dimensional design space to isolate a non-intuitive geometric optimum within just 30 high-fidelity oracle evaluations: anisotropic microcapsules (ρc≈2.5) oriented at 45∘ relative to the shear plane. This configuration is predicted to resolve the conflicting physical constraints of the system, maximizing the probability of crack interception for effective healing. These results demonstrate that physics-informed graph learning can effectively decouple prediction accuracy from computational intensity, offering a scalable paradigm for the discovery of advanced functional materials.

The inverse design of resilient infrastructure materials is hindered by the combinatorial complexity inherent in optimizing stochastic, heterogeneous microstructures. Traditional Euclidean deep learning architectures, such as Convolutional Neural Networks (CNNs), fail to efficiently encode the sparse, non-local topology of disordered porous media, resulting in prohibitive computational redundancy. This work articulates a comprehensive graph-theoretic framework for the predictive modeling and optimization of self-healing cementitious composites. We propose a robust methodology for discretizing volumetric tomography into permutation-invariant heterogeneous graphs, where nodes encode discrete physical entities (aggregates, pores, and microcapsules) and edges represent mechanical and hydraulic connectivity. To capture global fracture dynamics and local transport phenomena, we employ specialized architectures, specifically Pore-GNNs and Long-Short-Edge MeshGraphNets, which function as high-speed surrogate models for multiphysics simulations. Computational validation against high-fidelity numerical solvers confirms the system’s efficacy: the proposed architecture achieves approximately 1.1×105-fold acceleration (inference plus preprocessing) in permeability prediction relative to Lattice Boltzmann Method simulations, while maintaining a prediction accuracy of R2 > 0.94 (mean±std over five random splits); the inference-only speedup, which excludes one-time graph-construction preprocessing, is approximately 1.8×106-fold. We note that the end-to-end figure (1.1×105) supersedes the inference-only figure quoted in the original submission metadata. Furthermore, the framework autonomously navigated the high-dimensional design space to isolate a non-intuitive geometric optimum within just 30 high-fidelity oracle evaluations: anisotropic microcapsules (ρc≈2.5) oriented at 45∘ relative to the shear plane. This configuration is predicted to resolve the conflicting physical constraints of the system, maximizing the probability of crack interception for effective healing. These results demonstrate that physics-informed graph learning can effectively decouple prediction accuracy from computational intensity, offering a scalable paradigm for the discovery of advanced functional materials.