Search

Data integration, which aims to solve problems and create new services by combining datasets, has attracted considerable attention. The discovery of similar datasets that can be combined is critical. In the literature on similar dataset discovery, it is important to select an appropriate discovery method for each information need, such as the domain. However, conventional studies have evaluated discovery methods in different ways, such as domains, test datasets, and evaluation metrics. This factor prevents the appropriate method selection for each situation. Furthermore, the specific effects of the combination of different methods are not well known despite conventional studies arguing the importance of the combination. This study attempts to understand (1) the similarity indicators that should be employed for each domain and (2) the effects of a combination of different indicators on performance. We evaluated 16 inter-dataset clustering models based on different metadata-based similarity indicators, using unified evaluation metrics and datasets for 15 domains. Our results (1) suggest that similarity indicators should be used for each domain and (2) demonstrate that most of the combinations of different methods can improve clustering performance.

In the evolving business landscape, the scope of risk factors is extremely wide, making it impossible for all business-related risks to be captured within publicly available financial disclosures. Previous studies have predominantly focused on understanding causal relationships and risk chains based on the risks that are explicitly documented. Thus, risks that are not explicitly listed are often overlooked. The aim of this study was to analyze risk chains and extract implicit information from disclosed documents. We focused on edge classification and suggested suitable labels for the edges of a risk chain graph. Furthermore, we proposed an edge-type classification in heterogeneous graphs using Graph Neural Networks (GNN). This was accomplished by defining six risks and constructing risk-chain graphs. The outcomes demonstrated the edge-type classification proved to be an effective approach compared with existing method. This method holds the potential to aid investors in enhancing their profits and making more informed decisions.

With the drastically changing business environment, it is difficult even for experts to properly extract and classify risk statements from securities reports, which contain large volumes and unstructured information. Several methods have been proposed, but the existing methods face difficulty in dealing with flexible risk expressions. This study presents an open-domain risk-analysis framework that combine the strengths of both humans and machines. They include defining appropriate business risks and constructing supervised data based on those definitions. Risks were then extracted and classified from the securities reports of a representative group of Japanese companies. We confirmed the limitations of pattern matching, and the usefulness of contextual analysis methods. We also confirmed the importance of constructing supervised data based on appropriate guidelines of data classification. This study presents a framework that quickly and effectively derives the risk structure of a given industry or company from vast and unstructured information.

This article proposes a methodology to forecast the movements of analysts' estimated net income and stock prices using analyst profiles. Our methodology is based on applying natural language processing and neural networks in the context of analyst reports. First, we apply the proposed method to extract opinion sentences from the analyst report while classifying the remaining parts as non-opinion sentences. Then, we employ the proposed method to forecast the movements of analysts' estimated net income and stock price by inputting the opinion and non-opinion sentences into separate neural networks. In addition to analyst reports, we input analyst profiles to the networks. As analyst profiles, we used the name of an analyst, the securities company to which the analyst belongs, the sector which the analyst covers, and the analyst ranking. Consequently, we obtain an indication that the analyst profile effectively improves the model forecasts. However, classifying analyst reports into opinion and non-opinion sentences is insignificant for the forecasts.

This study demonstrates whether analysts' sentiments toward individual stocks are useful for stock investment strategies. This is achieved by using natural language processing to create a polarity index from textual information in analyst reports. In this study, we performed time series forecasting for the created polarity index using deep learning, and clustered the forecasted values by volatility using a regime switching model. In addition, we constructed a portfolio from stock data and rebalanced it at each change point of the regime. Consequently, the investment strategy proposed in this study outperforms the benchmark portfolio in terms of returns. This suggests that the polarity index is useful for constructing stock investment strategies.

Abstract Although deep neural networks are excellent for text sentiment analysis, their applications in real-world practice are occasionally limited owing to their black-box property. In this study, we propose a novel neural network model called contextual sentiment neural network (CSNN) model that can explain the process of its sentiment analysis prediction in a way that humans find natural and agreeable and can catch up the summary of the contents. The CSNN has the following interpretable layers: the word-level original sentiment layer, word-level sentiment shift layer, word-level global importance layer, word-level contextual sentiment layer, and concept-level contextual sentiment layer. Because of these layers, this network can explain the process of its document-level sentiment analysis results in a human-like way using these layers. Realizing the interpretability of each layer in the CSNN is a crucial problem in the development of this CSNN because the general back-propagation method cannot realize such interpretability. To realize this interpretability, we propose a novel learning strategy called initialization propagation (IP) learning. Using real textual datasets, we experimentally demonstrate that the proposed IP learning is effective for improving the interpretability of each layer in CSNN. We then experimentally demonstrate that the CSNN has both the high predictability and high explanation ability.

This paper proposes and analyzes a methodology of forecasting movements of the analysts’ net income estimates and those of stock prices. We achieve this by applying natural language processing and neural networks in the context of analyst reports. In the pre-experiment, we applied our method to extract opinion sentences from the analyst report while classifying the remaining parts as non-opinion sentences. Then, we performed two additional experiments. First, we employed our proposed method for forecasting the movements of analysts’ net income estimates by inputting the opinion and non-opinion sentences into separate neural networks. Besides the reports, we inputted the trend of the net income estimate to the networks. Second, we employed our proposed method for forecasting the movements of stock prices. Consequently, we found differences between security firms, which depend on whether analysts’ net income estimates tend to be forecasted by opinions or facts in the context of analyst reports. Furthermore, the trend of the net income estimate was found to be effective for the forecast as well as an analyst report. However, in experiments of forecasting movements of stock prices, the difference between opinion sentences and non-opinion sentences was not effective.

We propose an extended scheme for selecting related stocks for themed mutual funds. This scheme was designed to support fund managers who are building themed mutual funds. In our preliminary experiments, building a themed mutual fund was found to be quite difficult. Our scheme is a type of natural language processing method and based on words extracted according to their similarity to a theme using word2vec and our unique similarity based on co-occurrence in company information. We used data including investor relations and official websites as company information data. We also conducted several other experiments, including hyperparameter tuning, in our scheme. The scheme achieved a 172% higher F1 score and 21% higher accuracy than a standard method. Our research also showed the possibility that official websites are not necessary for our scheme, contrary to our preliminary experiments for assessing data collaboration.