Accurate workload forecasting is critical for efficient resource management in cloud computing systems, enabling effective scheduling and autoscaling. Despite recent advances with transformer-based forecasting models, challenges remain due to the non-stationary, nonlinear characteristics of workload time series and the long-term dependencies. In particular, inconsistent performance between long-term history and near-term forecasts hinders long-range predictions. This paper proposes a novel framework leveraging self-supervised multiscale representation learning to capture both long-term and near-term workload patterns. The long-term history is encoded through multiscale representations while the near-term observations are modeled via temporal flow fusion. These representations of different scales are fused using an attention mechanism and characterized with normalizing flows to handle non-Gaussian/non-linear distributions of time series. Extensive experiments on 9 benchmarks demonstrate superiority over existing methods.

Industrial-scale linear assignment problems (LAPs) are frequently encountered in various industrial scenarios, e.g., asset allocation within the domain of credit management. However, optimization algorithms for such problems (e.g., PJ-ADMM) are highly sensitive to hyper-parameters. Existing solving systems rely on empirical parameter selection, which is challenging to achieve convergence and extremely time-consuming. Additionally, the resulting parameter rules are often inefficient. To alleviate this issue, we propose RL-ISLAP, an efficient and lightweight Reinforcement Learning framework for Industrial-Scale Linear Assignment Problems. We formulate the hyper-parameter selection for PJ-ADMM as a sequential decision problem and leverage reinforcement learning to enhance its convergence. Addressing the sparse reward challenge inherent in learning policies for such problems, we devise auxiliary rewards to provide dense signals for policy optimization, and present a rollback mechanism to prevent divergence in the solving process. Experiments on OR-Library benchmark demonstrate that our method is competitive to SOTA stand-alone solvers. Furthermore, the scale-independent design of observations enables us to transfer the acquired hyper-parameter policy to a scenario of LAPs in varying scales. On two real-world industrial-scale LAPs with up to 10 millions of decision variables, our proposed RL-ISLAP achieves solutions of comparable quality in 2/3 of the time when compared to the SOTA distributed solving system employing fine-tuned empirical parameter rules.

Customer segmentation plays a crucial role in credit risk assessment by dividing users into specific risk levels based on their credit scores. Previous methods fail to comprehensively consider the stability in the segmentation process, resulting in frequent changes and inconsistencies in users' risk levels over time. This increases potential risks to a company. To this end, this paper at first introduces and formalizes the concept of stability regret in the segmentation process. However, evaluating stability is challenging due to its black-box nature and the computational burden posed by vast user data sets. To address these challenges, this paper proposes a large-scale stable customer segmentation approach named LASCA. LASCA consists of two phases: high-quality dataset construction (HDC) and reliable data-driven optimization (RDO). Specifically, HDC utilizes an evolutionary algorithm to collect high-quality binning solutions. RDO subsequently builds a reliable surrogate model to search for the most stable binning solution based on the collected dataset. Extensive experiments conducted on real-world large-scale datasets (up to 0.8 billion) show that LASCA surpasses the state-of-the-art binning methods in finding the most stable binning solution. Notably, HDC greatly enhances data quality by 50%. RDO efficiently discovers more stable binning solutions with a 36% improvement in stability, accelerating the optimization process by 25 times via data-driven evaluation. Currently, LASCA has been successfully deployed in the large-scale credit risk assessment system of Alipay.

The fraudulent insurance claim is critical for the insurance industry.Insurance companies or agency platforms aim to confidently estimate the fraud risk of claims by gathering data from various sources.Although more data sources can improve the estimation accuracy, they inevitably lead to increased costs.Therefore, a great challenge of fraud risk verification lies in well balancing these two aspects.To this end, this paper proposes a framework named cost-efficient fraud risk optimization with submodularity (CEROS) to optimize the process of fraud risk verification.CEROS efficiently allocates investigation resources across multiple information sources, balancing the trade-off between accuracy and cost.CEROS consists of two parts that we propose: a submodular set-wise classification model * Equal Contribution.

Autoscaling is a critical mechanism in cloud computing, enabling the autonomous adjustment of computing resources in response to dynamic workloads. This is particularly valuable for co-located, long-running applications with diverse workload patterns. The primary objective of autoscaling is to regulate resource utilization at a desired level, effectively balancing the need for resource optimization with the fulfillment of Service Level Objectives (SLOs). Many existing proactive autoscaling frameworks may encounter prediction deviations arising from the frequent fluctuations of cloud workloads. Reactive frameworks, on the other hand, rely on realtime system feedback, but their hysteretic nature could lead to violations of stringent SLOs. Hybrid frameworks, while prevalent, often feature independently functioning proactive and reactive modules, potentially leading to incompatibility and undermining the overall decision-making efficacy. In addressing these challenges, we propose OptScaler, a collaborative autoscaling framework that integrates proactive and reactive modules through an optimization module. The proactive module delivers reliable future workload predictions to the optimization module, while the reactive module offers a self-tuning estimator for real-time updates. By embedding a Model Predictive Control (MPC) mechanism and chance constraints into the optimization module, we further enhance its robustness. Numerical results have demonstrated the superiority of our workload prediction model and the collaborative framework, leading to over a 36% reduction in SLO violations compared to prevalent reactive, proactive, or hybrid autoscalers. Notably, OptScaler has been successfully deployed at Alipay, providing autoscaling support for the world-leading payment platform.

Given the enormous number of users and items, industrial cascade recommendation systems (RS) are continuously expanded in size and complexity to deliver relevant items, such as news, services, and commodities, to the appropriate users. In a real-world scenario with hundreds of thousands requests per second, significant computation is required to infer personalized results for each request, resulting in a massive energy consumption and carbon emission that raises concern. This paper proposes GreenFlow, a practical computation allocation framework for RS, that considers both accuracy and carbon emission during inference. For each stage (e.g., recall, pre-ranking, ranking, etc.) of a cascade RS, when a user triggers a request, we define two actions that determine the computation: (1) the trained instances of models with different computational complexity; and (2) the number of items to be inferred in the stage. We refer to the combinations of actions in all stages as action chains. A reward score is estimated for each action chain, followed by dynamic primal-dual optimization considering both the reward and computation budget. Extensive experiments verify the effectiveness of the framework, reducing computation consumption by 41% in an industrial mobile application while maintaining commercial revenue. Moreover, the proposed framework saves approximately 5000kWh of electricity and reduces 3 tons of carbon emissions per day.

Transformer-based models have achieved tremendous success in sequential recommendation (SR), but they suffer from consuming excessive computational resources, particularly in the inference stage. Thus, developing lightweight yet effective SR models has become a frequent demand in industrial applications, which is also in line with the ideals of Green AI and Green IR. In this applied paper, we introduce GreenSeq deployed in Alipay to automatically design Green networks that can provide appropriate recommendations with lower computational consumption in SR. Specifically, GreenSeq uses a novel multi-layer search space that allows for flexible network design and a Greenness-aware loss term for balancing efficiency and effectiveness. Experiments on benchmark datasets and A/B testing show that GreenSeq performs well while using fewer resources. GreenSeq also reduces electricity and carbon emissions in Alipay.