The wide spreading of Internet of Things (IoT) sensors generates vast spatio-temporal data streams, but ensuring data credibility is a critical yet unsolved challenge for applications like smart homes. While spatio-temporal graph (STG) models are a leading paradigm for such data, they often fall short in dynamic, human-centric environments due to two fundamental limitations: (1) their reliance on static graph topologies, which fail to capture physical, event-driven dynamics, and (2) their tendency to confuse spurious correlations with true causality, undermining robustness in human-centric environments. To address these gaps, we propose the Dynamic Causal Spatio-Temporal Graph Network (DyC-STG), a novel framework designed for real-time data credibility analysis in IoT. Our framework features two synergistic contributions: an event-driven dynamic graph module that adapts the graph topology in real-time to reflect physical state changes, and a causal reasoning module to distill causally-aware representations by strictly enforcing temporal precedence. To facilitate the research in this domain we release two new real-world datasets. Comprehensive experiments show that DyC-STG establishes a new state-of-the-art, outperforming the strongest baselines by 1.4 percentage points and achieving an F1-Score of up to 0.930.

Federated learning (FL) enables collaborative model training across distributed nodes without exposing raw data, but its decentralized nature makes it vulnerable in trust-deficient environments. Inference attacks may recover sensitive information from gradient updates, while poisoning attacks can degrade model performance or induce malicious behaviors. Existing defenses often suffer from high communication and computation costs, or limited detection precision. To address these issues, we propose LSHFed, a robust and communication-efficient FL framework that simultaneously enhances aggregation robustness and privacy preservation. At its core, LSHFed incorporates LSHGM, a novel gradient verification mechanism that projects high-dimensional gradients into compact binary representations via multi-hyperplane locality-sensitive hashing. This enables accurate detection and filtering of malicious gradients using only their irreversible hash forms, thus mitigating privacy leakage risks and substantially reducing transmission overhead. Extensive experiments demonstrate that LSHFed maintains high model performance even when up to 50% of participants are collusive adversaries, while achieving up to a 1000× reduction in gradient verification communication compared to full-gradient methods.

Few-shot graph learning remains a fundamental yet challenging problem, especially under heterophilic graph settings where connected nodes are likely to belong to different classes. In such scenarios, two key challenges arise: (1) unreliable or noisy graph structures that hinder effective message passing, and (2) semantic inconsistency: in heterophilic graphs, aggregating messages from neighbors of different classes entangles representations and introduces misleading semantics. These issues are further exacerbated by the limited labeled data inherent to few-shot learning, making it difficult to adaptively repair structure or disentangle semantics. To address these challenges, we propose DAPrompt, a Dual Alignment Prompt framework that jointly calibrates graph structure and semantic representations across the learning pipeline. In the pretraining stage, DAPrompt incorporates a graph structure learning module to denoise and repair the underlying topology, enhancing structural reliability. In the prompt tuning stage, we introduce two coordinated modules: a structure-aware prompt learner, which employs prompt tokens to repair unreliable graph structures and capture structure-level alignment, and a semantics-aligned prompt learner, which enhances the graph using target node semantics to mitigate representation noise caused by class-mismatched propagation. Extensive experiments on both node-level and graph-level few-shot benchmarks validate its effectiveness, achieving state-of-the-art performance and highlighting the value of structure-semantic dual alignment in heterophilic few-shot graph learning.

Dataset distillation (DD) compresses large datasets into smaller ones while preserving the performance of models trained on them. Although DD is often assumed to enhance data privacy by aggregating over individual examples, recent studies reveal that standard DD can still leak sensitive information from the original dataset due to the lack of formal privacy guarantees. Existing differentially private (DP)-DD methods attempt to mitigate this risk by injecting noise into the distillation process. However, they often fail to fully leverage the original dataset, resulting in degraded realism and utility. This paper introduces DP-GENG, a novel framework that addresses the key limitations of current DP-DD by leveraging DP-generated data. Specifically, DP-GENG initializes the distilled dataset with DP-generated data to enhance realism. Then, generated data refines the DP-feature matching technique to distill the original dataset under a small privacy budget, and trains an expert model to align the distilled examples with their class distribution. Furthermore, we design a privacy budget allocation strategy to determine budget consumption across DP components and provide a theoretical analysis of the overall privacy guarantees. Extensive experiments show that DP-GENG significantly outperforms state-of-the-art DP-DD methods in terms of both dataset utility and robustness against membership inference attacks, establishing a new paradigm for privacy-preserving dataset distillation.

Large language models (LLMs) have demonstrated impressive performance in text generation tasks; however, their embedding spaces often suffer from the isotropy problem, resulting in poor discrimination of domain-specific terminology, particularly in legal and financial contexts. This weakness in term-level representation can severely hinder downstream tasks such as legal judgment prediction or financial risk analysis, where subtle semantic distinctions are critical. To address this problem, we propose TermGPT, a multi-level contrastive fine-tuning framework designed for terminology adaptation. We first construct a sentence graph to capture semantic and structural relations, and generate semantically consistent yet discriminative positive and negative samples based on contextual and topological cues. We then devise a multi-level contrastive learning approach at both the sentence and token levels, enhancing global contextual understanding and fine-grained term discrimination. To support robust evaluation, we construct the first financial terminology dataset derived from official regulatory documents. Experiments show that TermGPT outperforms existing baselines in term discrimination tasks within the finance and legal domains.

Multi-view multi-label classification (MvMLC) is indispensable for modern web applications aggregating information from diverse sources. However, real-world web-scale settings are rife with missing views and continuously emerging classes, which pose significant obstacles to robust learning. Prevailing methods are ill-equipped for this reality, as they either lack adaptability to new classes or incur exponential parameter growth when handling all possible missing-view patterns, severely limiting their scalability in web environments. To systematically address this gap, we formally introduce a novel task, termed incomplete multi-view multi-label class incremental learning (IMvMLCIL), which requires models to simultaneously address heterogeneous missing views and dynamic class expansion. To tackle this task, we propose E2PL, an Effective and Efficient Prompt Learning framework for IMvMLCIL. E2PL unifies two novel prompt designs: task-tailored prompts for class-incremental adaptation and missing-aware prompts for the flexible integration of arbitrary view-missing scenarios. To fundamentally address the exponential parameter explosion inherent in missing-aware prompts, we devise an efficient prototype tensorization module, which leverages atomic tensor decomposition to elegantly reduce the prompt parameter complexity from exponential to linear w.r.t. the number of views. We further incorporate a dynamic contrastive learning strategy explicitly model the complex dependencies among diverse missing-view patterns, thus enhancing the model's robustness. Extensive experiments on three benchmarks demonstrate that E2PL consistently outperforms state-of-the-art methods in both effectiveness and efficiency. The codes and datasets are available at https://anonymous.4open.science/r/code-for-E2PL.

Reinforcement learning-based recommendation systems (RLRS) are increasingly favored for their ability to leverage online interactive feedback, enabling adaptive and personalized decision-making. In this setting, user feedback serves as both a behavioral signal and an optimization target, making it essential for policy learning. However, collecting such feedback, e.g., clicks, ratings, and engagement traces, raises serious privacy concerns, posing critical challenges for value estimation, online adaptation, and privacy protection. In this paper, we propose FeedGuard, a critic-guided reinforcement learning framework with privacy-preserving feedback. FeedGuard enhances trajectory modeling via critic guidance, enables joint online fine-tuning with effective exploration–exploitation tradeoffs, and enforces end-to-end privacy protection across the feedback lifecycle via split federated learning and differential privacy. We further provide a formal analysis of its differential privacy guarantees. Extensive experiments on four public recommendation datasets and the VirtualTB platform show that FeedGuard performs well in both offline and online settings, while maintaining rigorous privacy guarantees with minimal degradation.

Hash-based collaborative filtering (Hash-CF) approaches recently employ efficient Hamming distance of learned binary representations to accelerate recommendations. Benefiting from its probabilistic nature, Variational Autoencoder (VAE) enables robust Hash-CF with stronger generalization ability. However, VAE-based Hash-CF still faces two challenging problems: 1) Traditional VAE urges the latent variables of different users (or items) to fit a unified and monotonous prior distribution, and lacks considerations for distinctive characteristics of users (or items). The obtained representations of users and items with slight individual differentiation may further weaken the performance of Hash-CF for subsequent personalized recommendations. 2) Hash-CF under the VAE framework requires discrete optimization on latent Bernoulli distributions, which are discrete and NP-hard to optimize. In this paper, we propose a Dual Discrete Collaborative Filtering (DDCF) approach, including a cluster-enhanced representation generation module and a CNF-enabled discrete optimization module. The former module mainly develops cluster-aware latent space to generate discriminative representations for users or items with significantly different characteristics. The latter module employs Continuous Normalizing Flow (CNF) to achieve discrete optimization on latent Bernoulli distributions steadily and effectively. Extensive experiments conducted on multiple real-world datasets demonstrate the superiority of our DDCF compared with the state-of-art methods in terms of effectiveness and efficiency.

Data cleaning (DC) is a crucial yet challenging step for many data engineering tasks. Traditional pre-configuration DC methods rely heavily on predefined rules or constraints, demanding significant domain knowledge and manual effort. While configuration-free DC approaches have been explored, they still demand extensive feature engineering or labeled data for intensive model training. In this paper, we propose azero-training and interpretable DCsystem, named${\sf ZeroDC}$, that leverageslarge language models(LLMs) to generate data cleaning rules and chain-of-thoughts (CoTs), without the need for model training.${\sf ZeroDC}$consists of two modules,iterative detection rule generation(IDG) andtraining-free explainable correction(TEC). To generate high-quality error detection rules with minimal human feedback, IDG first bootstraps a set of rules viacontrastive rule initiationon sampled syntactic and semantic contrastive pairs. It then progressively enhances them through aniterative rule refinementworkflow that selects the most informative elements for updates. TEC constructs acontextual-relevant tuple retrieverusing aweighted cosine similarityfunction to efficiently identify the most relevant tuples for each dirty value, reducing redundancy in the LLM prompts and lowering computational costs. It further prompts for generatingcorrection CoTsfor user-corrected representative values, as well as prompts for creatingcorrection rulesandexplainable corrections, which automatically provide explanations for correction results, all without the need for model training. Extensive experiments conducted on various real-world datasets demonstrate that${\sf ZeroDC}$achieves, on average, a 5.36% increase in accuracy and an 8.16x speedup compared to state-of-the-art methods. The codes and datasets of this paper are available athttps://github.com/YangChen32768/ZeroDC.

Magnetic resonance imaging (MRI) provides highquality soft tissue contrast images and is crucial in medical diagnosis. However, systems face trade-offs between image resolution and scan time. Low-resolution MRI scans reduce scan time and patient burden but lose critical details needed for accurate diagnosis. To address this problem, super-resolution techniques have been developed to improve the clarity of lowresolution input images. Single-image super-resolution (SISR), which minimizes patient scanning time, has gradually become a research focus, but existing methods often struggle to balance the reconstruction of low-frequency structural information and high-frequency details. In this paper, we propose a novel superresolution up-sampling pipeline that enhances both the highfrequency and low-frequency components of magnetic resonance imaging. In addition, we introduce an enhanced loss function that includes symmetry and edge constraints to preserve critical structural details for improved diagnostic accuracy. The extensive experiments across multiple datasets validate the effectiveness of our SISR model. Source code will be made publicly available.

Correcting missing or erroneous data values is an essential task in data cleaning. Traditional pre-configuration error correction (EC) methods rely heavily on predefined rules or constraints, demanding significant domain knowledge and manual effort. While configuration-free EC approaches have been explored, they still demand extensive feature engineering or labeled data for intensive model training. In this paper, we propose a zero-training and interpretable EC system, named ZeroEC, that leverages large language models (LLMs) to generate chain-of-thoughts (CoTs) and correction rules for EC, without the need for model training. ZeroEC consists of two modules, contextual-relevant tuple search (CTS) and training-free explainable correction (TEC). CTS constructs a contextual-relevant tuple retriever using a weighted cosine similarity function to efficiently identify the most relevant tuples for each dirty tuple, reducing redundancy in the LLM prompts and lowering computational costs. TEC employs a clustering-based representative tuple sampling strategy to alleviate “hallucination” risk by exposing LLMs to diverse types of data errors. It further prompts for generating correction CoTs for user-corrected representative tuples, as well as prompts for creating correction rules and explainable ECs, which automatically provide explanations for EC, all without the need for model training. Extensive experiments conducted on various real-world datasets demonstrate that ZeroEC achieves a 66.82% increase in accuracy and a 6.87x speedup compared to state-of-the-art methods. The codes and datasets of this paper are available at https://github.com/YangChen32768/ZeroEC.

Loan default prediction is a crucial component of risk management in financial loan services. In practice, significant monetary losses often stem from initially creditworthy loans that later default unexpectedly. This phenomenon arises because such loans, while assessed as low-risk at disbursement initially, have a high default-intention to arise, in a delayed manner, at an indeterminate time during the repayment period after disbursement. We term such default-intention as Delayed Defaultintention. In this paper, we present a new and pressing task, namely, Delayed Default-intention based Default prediction ($\mathrm{D}^{3}$), which is of practical significance but has been rarely studied in prior research. The core challenge of$D^{3}$task lies in its farsighted inference of delayed default-intention, as it does not manifest immediately after disbursement. To address this, we propose a survival analysis framework for the$\mathrm{D}^{3}$task and a novel RW-D${ }^{3}$method, which models the repayment willingness (RW) in a loan as a negatively correlated alternative to delayed default-intention. RW-D${ }^{3}$systematically initializes, dynamizes, and recovers the original RW representations based on user behavior sequences, enhancing their predictive capacity from a short-term to a long-term perspective. Additionally, RW-D${ }^{3}$provides a comprehensive prediction of defaults triggered by delayed default-intention by jointly considering repayment status and timing. Extensive experiments demonstrate the superiority of RW-D${ }^{3}$over state-of-the-art methods in both its predictive effectiveness and explainability in financial loan services.

Missing values in multivariate time series data present significant challenges to effective analysis. Existing methods for multivariate time series analysis either ignore missing data, sacrificing performance, or follow the impute-then-analyze paradigm, which suffers from redundant training and error accumulation, leading to biased results and suboptimal performance. In this paper, we propose INTER, a novel end-to-end framework for incomplete multivariate time series analysis, which bypasses imputation by leveraging pre-trained language models to learn the distribution of incomplete time series data. INTER incorporates two novel components: the missing-rate-aware time series patch-dropping (MPD) strategy and the missing-aware Transformer block, both of which we propose to enhance model generalization, robustness, and the ability to capture underlying patterns in the observed incomplete time series. Moreover, we theoretically prove that the MPD strategy exhibits lower sample variance for time series with the same dropout rate compared to other dropping strategies. Extensive experiments on 11 public real-world time series datasets demonstrate that INTER improves accuracy by over 20% compared to state-of-the-art methods, while maintaining competitive computational efficiency.

Incomplete multi-view partial multi-label classification (IMvPMLC), which tackles the combined challenges of incompleteness in both multi-view and multi-label problems, has drawn considerable attention. Existing IMvPMLC methods have made progress but still face several challenges: (i) They mainly focus on the consistency of representations across multiple views but overlook the relationships among instances, leading to suboptimal representations. (ii) They primarily utilize only the available labels for supervised learning, ignoring the missing label distribution and limiting their ability to capture label correlations. In this paper, we propose a novel model named Dual Structure-guided Contrastive Network (DSCN) for IMvPMLC. Specifically, we introduce a similarity-guided instance-level contrastive learning mechanism to achieve multi-view consistent and discriminative representations across instances by leveraging instance structures, while a multi-view attention-based fusion strategy dynamically facilitates the fusion of multi-view representations to derive a robust consensus representation. Then, we design a multi-view shared classifier integrated with a correlation-guided label-level contrastive learning mechanism to enhance predictions by leveraging complementary information across multiple views and capturing label structures, effectively exploiting missing label distribution. Extensive experiments on five benchmark datasets demonstrate that, DSCN yields a more than 13% accuracy, compared with the state-of-the-art approaches. The code and datasets are available at https://anonymous.4open.science/r/DSCN-D471.

The sparse portfolio optimization (SPO) problem is increasingly crucial in portfolio management, focusing on selecting a few stocks with the potential for strong market performance. However, sparse portfolio strategies often face significant short-term drawdowns during periods of market volatility. To this end, a news-driven portfolio strategy offers valuable insights to capture sudden market changes. Nevertheless, it encounters two main challenges:how to reasonably map the relationships between news and stocksandhow to effectively utilize the irregular timing of news releases. To tackle the SPO problem in fluctuating markets while addressing these challenges, we propose a novel news-driven sparse portfolio strategy, named SPIN. Specifically, SPIN not only leverages industry-specific group structures existing among stocks for a more reasonable news-stock mapping and models news sequential patterns based on our devised novel news-driven forecaster to handle the irregularity of news releases. We rigorously prove that SPIN achieves a sub-linear regret. Extensive experiments on three real-world datasets demonstrate SPIN's superiority over state-of-the-art portfolio strategies in terms of cumulative wealth and short-term drawdowns.

Large language model-based explainable recommendation (LLM-based ER) systems can provide remarkable human-like explanations and have widely received attention from researchers. However, the original LLM-based ER systems face three low-quality problems in their generated explanations, i.e., lack of personalization, inconsistency, and questionable explanation data. To address these problems, we propose a novel LLM-based ER model denoted as LLM2ER to serve as a backbone and devise two innovative explainable quality reward models for fine-tuning such a backbone in a reinforcement learning paradigm, ultimately yielding a fine-tuned model denoted as LLM2ER-EQR, which can provide high-quality explanations. LLM2ER-EQR can generate personalized, informative, and consistent high-quality explanations learned from questionable-quality explanation datasets. Extensive experiments conducted on three real-world datasets demonstrate that our model can generate fluent, diverse, informative, and highly personalized explanations.

Stock movement prediction serves an important role in quantitative trading. Despite advances in existing models that enhance stock movement prediction by incorporating stock relations, these prediction models face two limitations, i.e., constructing either insufficient or static stock relations, which fail to effectively capture the complex dynamic stock relations because such complex dynamic stock relations are influenced by various factors in the ever-changing financial market. To tackle the above limitations, we propose a novel stock movement prediction model ECHO-GL based on stock relations derived from earnings calls. ECHO-GL not only constructs comprehensive stock relations by exploiting the rich semantic information in the earnings calls but also captures the movement signals between related stocks based on multimodal and heterogeneous graph learning. Moreover, ECHO-GL customizes learnable stock stochastic processes based on the post earnings announcement drift (PEAD) phenomenon to generate the temporal stock price trajectory, which can be easily plugged into any investment strategy with different time horizons to meet investment demands. Extensive experiments on two financial datasets demonstrate the effectiveness of ECHO-GL on stock price movement prediction tasks together with high prediction accuracy and trading profitability.

Log anomaly detection in digital service networks is challenging due to the heterogeneity and complexity of log formats and semantics. Traditional log anomaly detection methods struggle with two main challenges: the inability to directly correlate heterogeneous logs and the semantic heterogeneity across and within logs. To address these challenges, we propose a novel framework, HEDGE, which constructs a dynamic heterogeneous log graph to capture spatio-temporal relationships between logs, reflecting fine-grained semantic correlations and evolutionary properties of sequential logs comprehensively and detecting log anomalies effectively. To capture log representations under heterogeneity from both semantic and spatio-temporal perspectives, HEDGE not only pre-trains a dual-tower SemanticFormer based on BERT to align global and local semantic information for heterogeneous nodes but also adopts a dynamic heterogeneous graph model to learn spatio-temporal topological features within inner-snapshot and intra-snapshot contexts. Extensive experiments on public datasets demonstrate the superiority of our framework compared to state-of-the-art baselines.

Positive Unlabeled (PU) learning, which has a wide range of applications, is becoming increasingly prevalent. However, it suffers from problems such as data imbalance, selection bias, and prior agnostic in real scenarios. Existing studies focus on addressing part of these problems, which fail to provide a unified perspective to understand these problems. In this paper, we first rethink these problems by analyzing a typical PU scenario and come up with an insightful point of view that all these problems are inherently connected to one problem, i.e., positive distribution pollution, which refers to the inaccuracy in estimating positive data distribution under very little labeled data. Then, inspired by this insight, we devise a variational model named CoVPU, which addresses all three problems in a unified perspective by targeting the positive distribution pollution problem. CoVPU not only accurately separates the positive data from the unlabeled data based on discrete normalizing flows, but also effectively approximates the positive distribution based on our derived unbiased rebalanced risk estimator and supervises the approximation based on a novel prior-free variational loss. Rigorous theoretical analysis proves the convergence of CoVPU to an optimal Bayesian classifier. Extensive experiments demonstrate the superiority of CoVPU over the state-of-the-art PU learning methods under these problems.

News-driven quantitative trading (NQT) has been popularly studied in recent years. Most existing NQT methods are performed in a two-step paradigm, i.e., first analyzing markets by a financial prediction task and then making trading decisions, which is doomed to failure due to the nearly futile financial prediction task. To bypass the financial prediction task, in this paper, we focus on reinforcement learning (RL) based NQT paradigm, which leverages news to make profitable trading decisions directly. In this paper, we propose a novel NQT framework SpotlightTrader based on decision trajectory optimization, which can effectively stitch together a continuous and flexible sequence of trading decisions to maximize profits. In addition, we enhance this framework by constructing a spotlight-driven state trajectory that obeys a stochastic process with irregular abrupt jumps caused by spotlight news. Furthermore, in order to adapt to non-stationary financial markets, we propose an effective training pipeline for this framework, which blends offline pretraining with online finetuning to balance exploration and exploitation effectively during online tradings. Extensive experiments on three real-world datasets demonstrate our proposed model’s superiority over the state-of-the-art NQT methods.

In financial scenarios, influenced by common factors such as global macroeconomic and sector-specific factors, stocks exhibit varying degrees of correlations with each other, which is essential in risk-averse portfolio allocation. Because the real risk matrix is unobservable, the covariance-based correlation matrix is widely used for constructing diversified stock portfolios. However, studies have seldom focused on dynamic correlation matrix estimation under the non-stationary financial market. Moreover, as the number of stocks in the market grows, existing correlation matrix estimation methods face more serious challenges with regard to efficiency and effectiveness. In this paper, we propose a novel hash-based dynamic correlation forecasting model (HDCF) to estimate dynamic stock correlations. Under structural assumptions on the correlation matrix, HDCF learns the hash representation based on normalizing flows instead of the real-valued representation, which performs extremely efficiently in high-dimensional settings. Experiments show that our proposed model outperforms baselines on portfolio decisions in terms of effectiveness and efficiency.

User post-click conversion prediction is of high interest to researchers and developers. Recent studies employ multi-task learning to tackle the selection bias and data sparsity problem, two severe challenges in post-click behavior prediction, by incorporating click data. However, prior works mainly foucsed on pointwise learning and the orders of labels (i.e., click and post-click) are not well explored, which naturally poses a listwise learning problem. Inspired by recent advances on differentiable sorting, in this paper, we propose a novel multi-task framework that leverages orders of user behaviors to predict user post-click conversion in an end-to-end approach. Specifically, we define an aggregation operator to combine predicted outputs of different tasks to a unified score, then we use the computed scores to model the label relations via differentiable sorting. Extensive experiments on public and industrial datasets show the superiority of our proposed model against competitive baselines.

The ever-increasing data scale of user-item interactions makes it challenging for an effective and efficient recommender system. Recently, hash-based collaborative filtering (Hash-CF) approaches employ efficient Hamming distance of learned binary representations of users and items to accelerate recommendations. However, Hash-CF often faces two challenging problems, i.e., optimization on discrete representations and preserving semantic information in learned representations. To address the above two challenges, we propose HCFRec, a novel Hash-CF approach for effective and efficient recommendations. Specifically, HCFRec not only innovatively introduces normalized flow to learn the optimal hash code by efficiently fitting a proposed approximate mixture multivariate normal distribution, a continuous but approximately discrete distribution, but also deploys a cluster consistency preserving mechanism to preserve the semantic structure in representations for more accurate recommendations. Extensive experiments conducted on six real-world datasets demonstrate the superiority of our HCFRec compared to the state-of-art methods in terms of effectiveness and efficiency.

In this paper, we study a new kind of portfolio problem, named trading point aware portfolio optimization (TPPO), which aims to obtain excess intraday profit by deciding the portfolio weights and their trading points simultaneously based on microscopic information. However, a strategy for the TPPO problem faces two challenging problems, i.e., modeling the ever-changing and irregular microscopic stock price time series and deciding the scattering candidate trading points. To address these problems, we propose a novel TPPO strategy named STrader based on normalizing flows. STrader is not only promising in reversibly transforming the geometric Brownian motion process to the unobservable and complicated stochastic process of the microscopic stock price time series for modeling such series, but also has the ability to earn excess intraday profit by capturing the appropriate trading points of the portfolio. Extensive experiments conducted on three public datasets demonstrate STrader's superiority over the state-of-the-art portfolio strategies.

CVaR-sensitive online portfolio selection (CS-OLPS) becomes increasingly important for investors because of its effectiveness to minimize conditional value at risk (CVaR) and control extreme losses. However, the non-stationary nature of financial markets makes it very difficult to address the CS-OLPS problem effectively. To address the CS-OLPS problem in non-stationary markets, we propose an effective news-driven method, named CAND, which adaptively exploits news to determine the adjustment tendency and adjustment scale for tracking the dynamic optimal portfolio with minimal CVaR in each trading round. In addition, we devise a filtering mechanism to reduce the errors caused by the noisy news for further improving CAND's effectiveness. We rigorously prove a sub-linear regret of CAND. Extensive experiments on three real-world datasets demonstrate CAND’s superiority over the state-of-the-art portfolio methods in terms of returns and risks.

Online portfolio selection (OLPS) is a fundamental and challenging problem in financial engineering, which faces two practical constraints during the real trading, i.e., cardinality constraint and non-zero transaction costs. In order to achieve greater feasibility in financial markets, in this paper, we propose a novel online portfolio selection method named LExp4.TCGP with theoretical guarantee of sublinear regret to address the OLPS problem with the two constraints. In addition, we incorporate side information into our method based on contextual bandit, which further improves the effectiveness of our method. Extensive experiments conducted on four representative real-world datasets demonstrate that our method significantly outperforms the state-of-the-art methods when cardinality constraint and non-zero transaction costs co-exist.

Artificial intelligence (AI) is the core technology of technological revolution and industrial transformation. As one of the new intelligent needs in the AI 2.0 era, financial intelligence has elicited much attention from the academia and industry. In our current dynamic capital market, financial intelligence demonstrates a fast and accurate machine learning capability to handle complex data and has gradually acquired the potential to become a “financial brain.” In this paper, we survey existing studies on financial intelligence. First, we describe the concept of financial intelligence and elaborate on its position in the financial technology field. Second, we introduce the development of financial intelligence and review state-of-the-art techniques in wealth management, risk management, financial security, financial consulting, and blockchain. Finally, we propose a research framework called FinBrain and summarize four open issues, namely, explainable financial agents and causality, perception and prediction under uncertainty, risk-sensitive and robust decision-making, and multi-agent game and mechanism design. We believe that these research directions can lay the foundation for the development of AI 2.0 in the finance field.