arXiv subjects

Ryohei Hisano

Publications and source records attributed to Ryohei Hisano.

At least 19 recordsLinked to original sources

arXiv2026

No Data Is Not No Risk: Visibility Aware Graph-Based Inference of Business Conduct Risk

The monitoring of business conduct risk is hindered by sparse, uneven, and visibility-biased data. Prior studies show that business conduct risk information and media coverage propagate through supply chain, peer, and corporate structure networks, yet incident records remain incomplete for many firms. As a result, the absence of reported events could reflect limited coverage rather than the absence of underlying business conduct risk. This paper examines whether inter-firm relationships can improve the prediction of future recorded conduct related incidents, particularly among firms with limited prior visibility. We formulate the task as Positive--Unlabeled node classification on a corporate ownership graph, where firms with recorded incidents are treated as labeled positives and firms without recorded incidents remain unlabeled. We then propose a visibility- and relation-aware GCNII framework that combines relation specific message passing with non-negative Positive--Unlabeled learning to account for positive contamination in the unlabeled set. In a forward-looking evaluation, the proposed approach achieved the strongest observed ranking performance relative to non-graph- and simple graph-based benchmarks. The results further show that graph-based inference retains its predictive value among firms without prior recorded incidents. These findings demonstrate the value of inter-firm relational structure as a complementary source of information for extending risk prioritization

q-fin.RM↗

arXiv2026

Multiscale Euclidean Network Trajectories: Second-Moment Geometry, Attribution, and Change Points

A central challenge in dynamic network analysis is to represent temporal evolution in a way that is both geometrically meaningful and statistically identifiable. One approach embeds a sequence of network snapshots as trajectories in a Euclidean space and relates these trajectories to node embeddings. In multilayer and unfolded spectral constructions, however, node embeddings and their underlying latent positions are identifiable only up to general linear transformations. Although this ambiguity preserves edge probabilities, it can distort geometry and invalidate distance based temporal comparisons at both the trajectory and node-levels. We develop Multiscale Euclidean Network Trajectories (MENT), a framework for multiscale temporal trajectories based on second-moment geometry. By imposing an isotropic normalization on the anchor latent positions, we reduce the relevant ambiguity to orthogonal transformations and prevent distortion of the second-moment geometry. In this canonical representation, we define a trace variation distance and mode-wise variation distances along orthogonal directions, and use multidimensional scaling to obtain low-dimensional trajectories of time points at both global and mode-wise levels. The resulting trajectories support interpretation and inference. They admit mode-wise decompositions, support attribution of global and mode-wise temporal changes to nodes, and enable change point detection through 1D trajectories. We prove consistency of the proposed unfolded spectral embedding and of the induced temporal trajectories. Experiments on two synthetic and two real dynamic networks illustrate stable and interpretable recovery of temporal structure and show strong performance against existing change point detection baselines.

stat.ML↗

arXiv2025

Aligning ESG Controversy Data with International Guidelines through Semi-Automatic Ontology Construction

The growing importance of environmental, social, and governance data in regulatory and investment contexts has increased the need for accurate, interpretable, and internationally aligned representations of non-financial risks, particularly those reported in unstructured news sources. However, aligning such controversy-related data with principle-based normative frameworks, such as the United Nations Global Compact or Sustainable Development Goals, presents significant challenges. These frameworks are typically expressed in abstract language, lack standardized taxonomies, and differ from the proprietary classification systems used by commercial data providers. In this paper, we present a semi-automatic method for constructing structured knowledge representations of environmental, social, and governance events reported in the news. Our approach uses lightweight ontology design, formal pattern modeling, and large language models to convert normative principles into reusable templates expressed in the Resource Description Framework. These templates are used to extract relevant information from news content and populate a structured knowledge graph that links reported incidents to specific framework principles. The result is a scalable and transparent framework for identifying and interpreting non-compliance with international sustainability guidelines.

cs.CL↗

arXiv2025

Capturing Legal Reasoning Paths from Facts to Law in Court Judgments using Knowledge Graphs

Court judgments reveal how legal rules have been interpreted and applied to facts, providing a foundation for understanding structured legal reasoning. However, existing automated approaches for capturing legal reasoning, including large language models, often fail to identify the relevant legal context, do not accurately trace how facts relate to legal norms, and may misrepresent the layered structure of judicial reasoning. These limitations hinder the ability to capture how courts apply the law to facts in practice. In this paper, we address these challenges by constructing a legal knowledge graph from 648 Japanese administrative court decisions. Our method extracts components of legal reasoning using prompt-based large language models, normalizes references to legal provisions, and links facts, norms, and legal applications through an ontology of legal inference. The resulting graph captures the full structure of legal reasoning as it appears in real court decisions, making implicit reasoning explicit and machine-readable. We evaluate our system using expert annotated data, and find that it achieves more accurate retrieval of relevant legal provisions from facts than large language model baselines and retrieval-augmented methods.

cs.CL↗

arXiv2025

Unfolded Laplacian Spectral Embedding: A Theoretically Grounded Approach to Dynamic Network Representation

Dynamic relational data arise in many machine learning applications, yet their evolving structure poses challenges for learning representations that remain consistent and interpretable over time. A common approach is to learn time varying node embeddings, whose usefulness depends on well defined stability properties across nodes and across time. We introduce Unfolded Laplacian Spectral Embedding (ULSE), a principled extension of unfolded adjacency spectral embedding to normalized Laplacian operators, a setting where stability guarantees have remained out of reach. We prove that ULSE satisfies both cross-sectional and longitudinal stability under a dynamic stochastic block model. Moreover, the Laplacian formulation yields a dynamic Cheeger-type inequality linking the spectrum of the unfolded normalized Laplacian to worst case conductance over time, providing structural insight into the embeddings. Empirical results on synthetic and real world dynamic networks validate the theory.

stat.ML↗

arXiv2024

Leveraging Large Language Models for Institutional Portfolio Management: Persona-Based Ensembles

Large language models (LLMs) have demonstrated promising performance in various financial applications, though their potential in complex investment strategies remains underexplored. To address this gap, we investigate how LLMs can predict price movements in stock and bond portfolios using economic indicators, enabling portfolio adjustments akin to those employed by institutional investors. Additionally, we explore the impact of incorporating different personas within LLMs, using an ensemble approach to leverage their diverse predictions. Our findings show that LLM-based strategies, especially when combined with the mode ensemble, outperform the buy-and-hold strategy in terms of Sharpe ratio during periods of rising consumer price index (CPI). However, traditional strategies are more effective during declining CPI trends or sharp market downturns. These results suggest that while LLMs can enhance portfolio management, they may require complementary strategies to optimize performance across varying market conditions.

cs.CE↗

arXiv2024

Hierarchical Narrative Analysis: Unraveling Perceptions of Generative AI

Written texts reflect an author's perspective, making the thorough analysis of literature a key research method in fields such as the humanities and social sciences. However, conventional text mining techniques like sentiment analysis and topic modeling are limited in their ability to capture the hierarchical narrative structures that reveal deeper argumentative patterns. To address this gap, we propose a method that leverages large language models (LLMs) to extract and organize these structures into a hierarchical framework. We validate this approach by analyzing public opinions on generative AI collected by Japan's Agency for Cultural Affairs, comparing the narratives of supporters and critics. Our analysis provides clearer visualization of the factors influencing divergent opinions on generative AI, offering deeper insights into the structures of agreement and disagreement.

cs.CL↗

arXiv2024

Hypergraph Change Point Detection using Adapted Cardinality-Based Gadgets: Applications in Dynamic Legal Structures

Hypergraphs provide a robust framework for modeling complex systems with higher-order interactions. However, analyzing them in dynamic settings presents significant computational challenges. To address this, we introduce a novel method that adapts the cardinality-based gadget to convert hypergraphs into strongly connected weighted directed graphs, complemented by a symmetrized combinatorial Laplacian. We demonstrate that the harmonic mean of the conductance and edge expansion of the original hypergraph can be upper-bounded by the conductance of the transformed directed graph, effectively preserving crucial cut information. Additionally, we analyze how the resulting Laplacian relates to that derived from the star expansion. Our approach was validated through change point detection experiments on both synthetic and real datasets, showing superior performance over clique and star expansions in maintaining spectral information in dynamic settings. Finally, we applied our method to analyze a dynamic legal hypergraph constructed from extensive United States court opinion data.

cs.SI↗

arXiv2024

Dynamic Link and Flow Prediction in Bank Transfer Networks

The prediction of both the existence and weight of network links at future time points is essential as complex networks evolve over time. Traditional methods, such as vector autoregression and factor models, have been applied to small, dense networks, but become computationally impractical for large-scale, sparse, and complex networks. Some machine learning models address dynamic link prediction, but few address the simultaneous prediction of both link presence and weight. Therefore, we introduce a novel model that dynamically predicts link presence and weight by dividing the task into two sub-tasks: predicting remittance ratios and forecasting the total remittance volume. We use a self-attention mechanism that combines temporal-topological neighborhood features to predict remittance ratios and use a separate model to forecast the total remittance volume. We achieve the final prediction by multiplying the outputs of these models. We validated our approach using two real-world datasets: a cryptocurrency network and bank transfer network.

econ.GN↗

arXiv2023

Gaussian Hierarchical Latent Dirichlet Allocation: Bringing Polysemy Back

Topic models are widely used to discover the latent representation of a set of documents. The two canonical models are latent Dirichlet allocation, and Gaussian latent Dirichlet allocation, where the former uses multinomial distributions over words, and the latter uses multivariate Gaussian distributions over pre-trained word embedding vectors as the latent topic representations, respectively. Compared with latent Dirichlet allocation, Gaussian latent Dirichlet allocation is limited in the sense that it does not capture the polysemy of a word such as ``bank.'' In this paper, we show that Gaussian latent Dirichlet allocation could recover the ability to capture polysemy by introducing a hierarchical structure in the set of topics that the model can use to represent a given document. Our Gaussian hierarchical latent Dirichlet allocation significantly improves polysemy detection compared with Gaussian-based models and provides more parsimonious topic representations compared with hierarchical latent Dirichlet allocation. Our extensive quantitative experiments show that our model also achieves better topic coherence and held-out document predictive accuracy over a wide range of corpus and word embedding vectors.

stat.ML↗

arXiv2020

Nondiagonal Mixture of Dirichlet Network Distributions for Analyzing a Stock Ownership Network

Block modeling is widely used in studies on complex networks. The cornerstone model is the stochastic block model (SBM), widely used over the past decades. However, the SBM is limited in analyzing complex networks as the model is, in essence, a random graph model that cannot reproduce the basic properties of many complex networks, such as sparsity and heavy-tailed degree distribution. In this paper, we provide an edge exchangeable block model that incorporates such basic features and simultaneously infers the latent block structure of a given complex network. Our model is a Bayesian nonparametric model that flexibly estimates the number of blocks and takes into account the possibility of unseen nodes. Using one synthetic dataset and one real-world stock ownership dataset, we show that our model outperforms state-of-the-art SBMs for held-out link prediction tasks.

cs.SI↗

arXiv2020

Identifying the Hierarchical Influence Structure Behind Smart Sanctions Using Network Analysis

Smart sanctions are an increasingly popular tool in foreign policy. Countries and international institutions worldwide issue such lists to sanction targeted entities through financial asset freezing, embargoes, and travel restrictions. The relationships between the issuer and the targeted entities in such lists reflect what kind of entities the issuer intends to be against. Thus, analyzing the similarities of sets of targeted entities created by several issuers might pave the way toward understanding the foreign political power structure that influences institutions to take similar actions. In the current paper, by analyzing the smart sanctions lists issued by major countries and international institutions worldwide (a total of 73 countries, 12 international organizations, and 1,700 lists), we identify the hierarchical structure of influence among these institutions that encourages them to take such actions. The Helmholtz--Hodge decomposition is a method that decomposes network flow into a hierarchical gradient component and a loop component and is especially suited for this task. Hence, by performing a Helmholtz--Hodge decomposition of the influence network of these institutions, as constructed from the smart sanctions lists they have issued, we show that meaningful insights about the hierarchical influence structure behind smart sanctions can be obtained.

cs.SI↗

arXiv2019

Prediction of ESG Compliance using a Heterogeneous Information Network

Negative screening is one method to avoid interactions with inappropriate entities. For example, financial institutions keep investment exclusion lists of inappropriate firms that have environmental, social, and government (ESG) problems. They create their investment exclusion lists by gathering information from various news sources to keep their portfolios profitable as well as green. International organizations also maintain smart sanctions lists that are used to prohibit trade with entities that are involved in illegal activities. In the present paper, we focus on the prediction of investment exclusion lists in the finance domain. We construct a vast heterogeneous information network that covers the necessary information surrounding each firm, which is assembled using seven professionally curated datasets and two open datasets, which results in approximately 50 million nodes and 400 million edges in total. Exploiting these vast datasets and motivated by how professional investigators and journalists undertake their daily investigations, we propose a model that can learn to predict firms that are more likely to be added to an investment exclusion list in the near future. Our approach is tested using the negative news investment exclusion list data of more than 35,000 firms worldwide from January 2012 to May 2018. Comparing with the state-of-the-art methods with and without using the network, we show that the predictive accuracy is substantially improved when using the vast information stored in the heterogeneous information network. This work suggests new ways to consolidate the diffuse information contained in big data to monitor dominant firms on a global scale for better risk management and more socially responsible investment.

cs.SI↗

arXiv2019

Learning Topic Models by Neighborhood Aggregation

Topic models are frequently used in machine learning owing to their high interpretability and modular structure. However, extending a topic model to include a supervisory signal, to incorporate pre-trained word embedding vectors and to include a nonlinear output function is not an easy task because one has to resort to a highly intricate approximate inference procedure. The present paper shows that topic modeling with pre-trained word embedding vectors can be viewed as implementing a neighborhood aggregation algorithm where messages are passed through a network defined over words. From the network view of topic models, nodes correspond to words in a document and edges correspond to either a relationship describing co-occurring words in a document or a relationship describing the same word in the corpus. The network view allows us to extend the model to include supervisory signals, incorporate pre-trained word embedding vectors and include a nonlinear output function in a simple manner. In experiments, we show that our approach outperforms the state-of-the-art supervised Latent Dirichlet Allocation implementation in terms of held-out document classification tasks.

stat.ML↗

arXiv2016

Semi-supervised Graph Embedding Approach to Dynamic Link Prediction

We propose a simple discrete time semi-supervised graph embedding approach to link prediction in dynamic networks. The learned embedding reflects information from both the temporal and cross-sectional network structures, which is performed by defining the loss function as a weighted sum of the supervised loss from past dynamics and the unsupervised loss of predicting the neighborhood context in the current network. Our model is also capable of learning different embeddings for both formation and dissolution dynamics. These key aspects contributes to the predictive performance of our model and we provide experiments with three real--world dynamic networks showing that our method is comparable to state of the art methods in link formation prediction and outperforms state of the art baseline methods in link dissolution prediction.

stat.ML↗

arXiv2016

The gradual evolution of buyer--seller networks and their role in aggregate fluctuations

Buyer--seller relationships among firms can be regarded as a longitudinal network in which the connectivity pattern evolves as each firm receives productivity shocks. Based on a data set describing the evolution of buyer--seller links among 55,608 firms over a decade and structural equation modeling, we find some evidence that interfirm networks evolve reflecting a firm's local decisions to mitigate adverse effects from neighbor firms through interfirm linkage, while enjoying positive effects from them. As a result, link renewal tends to have a positive impact on the growth rates of firms. We also investigate the role of networks in aggregate fluctuations.

q-fin.GN↗

arXiv2016

A New Approach to Building the Interindustry Input--Output Table

We present a new approach to estimating the interdependence of industries in an economy by applying data science solutions. By exploiting interfirm buyer--seller network data, we show that the problem of estimating the interdependence of industries is similar to the problem of uncovering the latent block structure in network science literature. To estimate the underlying structure with greater accuracy, we propose an extension of the sparse block model that incorporates node textual information and an unbounded number of industries and interactions among them. The latter task is accomplished by extending the well-known Chinese restaurant process to two dimensions. Inference is based on collapsed Gibbs sampling, and the model is evaluated on both synthetic and real-world datasets. We show that the proposed model improves in predictive accuracy and successfully provides a satisfactory solution to the motivated problem. We also discuss issues that affect the future performance of this approach.

stat.ML↗

arXiv2013

High quality topic extraction from business news explains abnormal financial market volatility

Understanding the mutual relationships between information flows and social activity in society today is one of the cornerstones of the social sciences. In financial economics, the key issue in this regard is understanding and quantifying how news of all possible types (geopolitical, environmental, social, financial, economic, etc.) affect trading and the pricing of firms in organized stock markets. In this article, we seek to address this issue by performing an analysis of more than 24 million news records provided by Thompson Reuters and of their relationship with trading activity for 206 major stocks in the S&P US stock index. We show that the whole landscape of news that affect stock price movements can be automatically summarized via simple regularized regressions between trading activity and news information pieces decomposed, with the help of simple topic modeling techniques, into their "thematic" features. Using these methods, we are able to estimate and quantify the impacts of news on trading. We introduce network-based visualization techniques to represent the whole landscape of news information associated with a basket of stocks. The examination of the words that are representative of the topic distributions confirms that our method is able to extract the significant pieces of information influencing the stock market. Our results show that one of the most puzzling stylized fact in financial economies, namely that at certain times trading volumes appear to be "abnormally large," can be partially explained by the flow of news. In this sense, our results prove that there is no "excess trading," when restricting to times when news are genuinely novel and provide relevant financial information.

stat.ML↗