Predictive Judgments Research Articles

Russian Bancassurance Perspectives: From Path Dependence to Ecosystem

The aim of the study is to identify the future of Russian bancassurance in the “digital” world based on the formation of a reasonable opinion on its prospects within the framework of path dependence and the ecosystem approach. The relevance of the article is determined by the significance of bancassurance for the development of the insurance sector and the Russian financial market as a whole. The author uses methods such as analysis and synthesis, analogy, induction, descriptive analysis, matrix construction, clustering using graphs, and index method. The study is based on the works of domestic and foreign authors, data from the Bank of Russia on the state of the banking sector of the Russian Federation and key indicators of the insurers; reports of the rating agency “RA Expert” on bancassurance; data of Professional Analysis Systems of Markets and Companies Interfax. Based on the results of quantitative analysis, the author concludes that the key factor determining the development of Russian bancassurance within the framework of path dependence is the role of banks as recipients of cash flows. The author shows that the digital transformation of bancassurance is mainly associated with the digitalization of intermediary relations between the bank, individual client and insurance company. To quantify the level of such transformation, the author proposes indices of digitalization of bancassurance. The author shows that bancassurance can be successfully built into ecosystems due to its peculiarities. However, the conditions for the development of ecosystems in the Russian market can lead to the dissolution of bancassurance in ecosystems and the loss of its significance for the development of the Russian financial market. The presented conclusions are to be discussed taking into account the study of new issues in this problem area, including a study of the mergers and acquisitions market to analyse changes in the ownership structure of banks and insurance companies; a study of corporate bancassurance; broader analysis of quantitative values of bancassurance due to new data; analysis of ecosystem development in the Russian financial market in order to move from predictive judgments to a discussion of real situations.

What Makes Learners Overestimate Their Text Comprehension? The Impact of Learner Characteristics on Judgment Bias

It is frequently assumed that learner characteristics (e.g., reading skill, self-perceptions, optimism) account for overestimations of text comprehension, which threaten learning success. However, previous findings are heterogenous. To circumvent a key problem of previous research, we considered cognitive, metacognitive, motivational, and personality characteristics of learners (N = 255) simultaneously with regard to their impact on the judgment biases in prediction and postdiction judgments about factual and inference questions. The main results for the factual questions showed that men, lower reading skill, working memory capacity, and topic knowledge, yet higher self-perceptions of cognitive and metacognitive capacities yielded stronger overestimations for prediction judgments. For inference questions, a lower reading skill, higher self-perceptions of metacognitive capacities, and a higher self-efficacy were related to stronger overestimations for prediction and postdiction judgments. A higher openness was a risk factor for stronger overestimations when making predictions for the inference questions. The findings demonstrate that learner characteristics are a relevant source of judgment bias, which should be incorporated explicitly in theories of judgment accuracy. At the same time, fewer learner characteristics were actually relevant than previous research suggests. Moreover, which learner characteristics impact judgment bias also depends on task requirements, such as factual versus inference questions.

Research on a Decision Prediction Method Based on Causal Inference and a Multi-Expert FTOPJUDGE Mechanism

Legal judgement prediction (LJP) is a crucial part of legal AI, and its goal is to predict the outcome of a case based on the information in the description of criminal facts. This paper proposes a decision prediction method based on causal inference and a multi-expert FTOPJUDGE mechanism. First, a causal inference algorithm was adopted to process unstructured text. This process did not require very much manual intervention to better mine the information in the text. Then, a neural network dedicated to each task was set up, and a neural network that simultaneously served multiple tasks was also set up. Finally, the pre-trained language model Lawformer was used to provide knowledge for downstream tasks. By using the public data set CAIL2018 and comparing it with current mainstream decision prediction models, it was shown that the model significantly improved the performance of downstream tasks and achieved great improvements in multiple indicators. Through ablation experiments, the effectiveness and rationality of each module of the proposed model were verified. The method proposed in this study achieved reasonably good performance in legal judgment prediction, which provides a promising solution for legal judgment prediction.

A Computational Intelligence Model for Legal Prediction and Decision Support.

Legal judgment prediction (LJP) and decision support aim to enable machines to predict the verdict of legal cases after reading the description of facts, which is an application of artificial intelligence in the legal field. This paper proposes a legal judgment prediction model based on process supervision for the sequential dependence of each subtask in the legal judgment prediction task. Experimental results verify the effectiveness of the model framework and process monitoring mechanism adopted in this model. First, the convolutional neural network (CNN) algorithm was used to extract text features, and the principal component analysis (PCA) algorithm was used to reduce the dimension of data features. Next, the prediction model based on process supervision is proposed for the first time. When modeling the dependency relationship between sequential sub-data sets, process supervision is introduced to ensure the accuracy of the obtained dependency information, and genetic algorithm (GA) is introduced to optimize the parameters so as to improve the final prediction performance. Compared to our benchmark method, our algorithm achieved the best results on four different legal open data sets (CAIL2018_Small, CAIL2018_Large, CAIL2019_Small, and CAIL2019_Large). The realization of automatic prediction of legal judgment can not only assist judges, lawyers, and other professionals to make more efficient legal judgment but also provide legal aid for people who lack legal expertise.

An Optimization Analysis Model of Tourism Specialized Villages Based on Neural Network and System Dynamics

With the rapid development of tourism, professional tourism villages emerge one after another, which has become the focus of the tourism industry. At present, there are some problems in tourism professional villages, such as imperfect management and inaccurate prediction of future development, which affect the rational allocation of tourism resources. In order to improve the distribution of tourism resources and better predict the development of tourism professional villages, it is necessary to make comprehensive judgment and analysis, especially the analysis of indicators such as the prediction and development judgment of tourism professional villages. This paper discusses the optimization analysis of the agglomeration of tourism specialized villages by backpropagation (BP) neural network and system dynamics model, analyzes the system structure of the agglomeration factors of tourism specialized villages, and promotes the intelligent integration of the agglomeration factors. The development of clusters of professional villages promotes data integration among resources, economy, society, and other elements and presents the characteristics of big data. As the level of concentration of professional villages increases, the complexity of the associated factors also increases, which increases the difficulty and effectiveness of tourism analysis. In view of this situation, taking mountain tourism as the research object, this paper proposes an improved system dynamics model based on BP, extracts features from cross factor (resource, economic, and social) data, and optimizes the relationship between professional village agglomeration and various factors. The MATLAB simulation results show that based on the improved system dynamics analysis, the simplification rate of (resources, economy, and society) data can be controlled at more than 24%, the degree of agglomeration is more than 95%, and the construction time of the relationship map of related factors is less than 40 s. Therefore, the analysis method proposed in this paper is suitable for the calculation of the agglomeration of tourism professional villages in the mountain area and can meet the needs of the development of tourism professional villages in the mountain area.

Mulan: A Multiple Residual Article-Wise Attention Network for Legal Judgment Prediction

Legal judgment prediction (LJP) is used to predict judgment results based on the description of individual legal cases. In order to be more suitable for actual application scenarios in which the case has cited multiple articles and has multiple charges, we formulate legal judgment prediction as a multiple label learning problem and present a deep learning model that can effectively encode the content of each legal case via a multi-residual convolution neural network and the semantics of law articles via an article encoder. An article-wise attention mechanism is proposed to fuse the two types of encoded information. Experimental results derived on the CAIL2018 datasets show that our model provides a significant performance improvement over the existing neural models in predicting relevant law articles and charges.

Why Is Murat's Achievement So Low? Causal Attributions and Implicit Attitudes Toward Ethnic Minority Students Predict Preservice Teachers' Judgments About Achievement.

In many educational systems, ethnic minority students score lower in their academic achievement, and consequently, teachers develop low expectations regarding this student group. Relatedly, teachers’ implicit attitudes, explicit expectations, and causal attributions also differ between ethnic minority and ethnic majority students—all in a disadvantageous way for ethnic minority students. However, what is not known so far, is how attitudes and causal attributions contribute together to teachers’ judgments. In the current study, we explored how implicit attitudes and causal attributions contribute to preservice teachers’ judgments of the low educational success of an ethnic minority student. Results showed that both implicit attitudes and causal attributions predicted language proficiency and intelligence judgments. Negative implicit attitudes, assessed with the IRAP, and internal stable causal attributions led to lower judgments of language proficiency, whereas lower judgments of intelligence were predicted by positive implicit attitudes and higher judgments of intelligence by external stable attributions. Substantial differences in the prediction of judgments could be found between the IRAP and BIAT as measures of implicit attitudes.

Brand Marketing Decision Support System Based on Computer Vision and Parallel Computing

With the rapid development of information technology, decision support systems that can assist business managers in making scientific decisions have become the focus of research. At present, there are not many related studies, but from the brand marketing level, there are not many studies combining smart technology. Based on computer vision technology and parallel computing algorithms, this paper launches an in-depth study of brand marketing decision support systems. First, use computer vision technology and Viola-Jones face detection framework to detect consumers’ faces, and use the classic convolutional neural network model AlexNet for gender judgment and age prediction to analyze consumer groups. Then, use parallel computing to optimize the genetic algorithm to improve the running speed of the algorithm. Design the brand marketing decision support system based on the above technology and algorithm, analyze the relevant data of the L brand, and divide the functional structure of the system into three parts: customer market analysis, performance evaluation, and demand forecasting. The ROC curve of the Viola-Jones face detection framework shows its superior performance. After 500 iterations of the AlexNet model, the verification set loss of the network is stable at 1.8, and the accuracy of the verification set is stable at 38%. Parallel genetic algorithms run 1.8 times faster than serial genetic algorithms at the lowest and 9 times faster at the highest. The minimum prediction error is 0.17%, and the maximum is 2%, which shows that the system can make accurate predictions based on previous years’ data. Computer vision is a technique that converts still image or video data into a decision or a new representation. All such transformations are done to accomplish a specific purpose. Therefore, a brand marketing decision support system based on computer vision and parallel computing can help managers make scientific decisions, save production costs, reduce inventory pressure, and enhance the brand’s competitive advantage.

ICDF: Intrusion collaborative detection framework based on confidence

Many machine-learning-based intrusion detection methods have been proposed, however there is a lack of collaboration among these methods. Faced with a cascade of malicious behaviors and various running environments, coupled with the endless emergence of new malicious activities, it is difficult for us to choose an algorithm manually that is suitable for all scenarios. In addition, usually the binary detection models are applied that only “normal” or “abnormal” decision is made, and it is difficult for us to know how much confidence we have in the prediction model. In this study, we propose an intrusion collaborative detection framework (ICDF), an ICDF that allows heterogeneous detection models to effectively work together which have complementary expertise. A multialgorithm model ensemble learning method with confidence interval is adopted. In this process, each algorithm model only makes prediction judgments on its own credible probability interval and refuses to predict outside the interval. The final result is generated by voting based on the confidence of multiple models. Ten detection algorithms were tested on three different data sets. Compared with different single algorithms, ICDF could achieve high precision and recall rate, and the best F1 scores.

User Experience of 5G Video Services in Indonesia: Predictions Based on a Structural Equation Model

The advent of 5G has created an expectation for the provision of a much better user experience (UX) for utilising video streaming services. However, apart from quality, there are many other factors believed to influence users’ experiences of video streaming services in the era of 5G. The question then arises: what will determine the UX of streaming video services in the 5G era? This study aimed to discover what factors would influence 5G UX by using a conceptual framework involving measures of users’ predictive judgements of 5G combined with users’ measurements of current 4G UX, considering that there is no specific standard for measuring UX. Our case study is Indonesia, the world’s fourth-largest market, so the predictions may later become a reference for the priorities of implementing 5G technology. Our conceptual framework utilised the structural equation model (SEM) approach, based on the primary data of a 254-respondent sample of the Indonesian market. The questionnaire assessed 10 factors of user experience, ranging from service attractiveness to economic-related aspects. The results imply that the current user’s experience of 4G has an effect with a significance value of 0.42 to their later experience when accessing 5G video services. It means that many users will continue to use 4G for video streaming and still need tangible evidence of 5G. Among the 10 factors, a satisfaction value of 0.72 in 4G technology and perspicuity of 0.81 in 5G are the highest correlations. These factors are the most influential for video service experience.

Legal Judgment Prediction via Heterogeneous Graphs and Knowledge of Law Articles

Legal judgment prediction (LJP) is a crucial task in legal intelligence to predict charges, law articles and terms of penalties based on case fact description texts. Although existing methods perform well, they still have many shortcomings. First, the existing methods have significant limitations in understanding long documents, especially those based on RNNs and BERT. Secondly, the existing methods are not good at solving the problem of similar charges and do not fully and effectively integrate the information of law articles. To address the above problems, we propose a novel LJP method. Firstly, we improve the model’s comprehension of the whole document based on a graph neural network approach. Then, we design a graph attention network-based law article distinction extractor to distinguish similar law articles. Finally, we design a graph fusion method to fuse heterogeneous graphs of text and external knowledge (law article group distinction information). The experiments show that the method could effectively improve LJP performance. The experimental metrics are superior to the existing state of the art.

A target anti‐occlusion method based on image processing and trajectory prediction in electro‐optical tracking system

In the electro-optical tracking system, due to the full occlusion of clouds or buildings, the traditional tracking algorithm fails to work effectively. In the authors’ study, a dual-channel anti-occlusion scheme based on image processing and trajectory prediction is proposed. On the one hand, the image-processing unit plays a significant role in evaluating the occlusion state of the target. An improved image occlusion judgement method based on Bhattacharyya coefficient occlusion judgement is proposed, and the ability to resist background interference and rapidity of the algorithm is enhanced. On the other hand, according to the different occlusion states, the dual operation modes of tracking and prediction are usually set. When the target is completely occluded, the prediction mode based on a robust predictive filtering method is investigated to predict the real-time trajectory of the target more accurately. Image occlusion judgement and trajectory prediction can solve the occlusion problems in tracking control. Otherwise, the feasibility and effectiveness of the proposed method are verified by experiments. The cover image is based on the Research Article A target anti-occlusion method based on image processing and trajectory prediction in electro-optical tracking system by Yao Mao et al., https://doi.org/10.1049/rsn2.12235.

Point, interval, and density forecasts: Differences in bias, judgment noise, and overall accuracy

AbstractThere are three main ways in which judgmental predictions are expressed: point forecasts; interval forecasts; probability density forecasts. Do these approaches differ solely in terms of their simplicity of elicitation and the detail they provide? We examined error in values of the central tendency extracted from these three types of forecast in a domain in which all of them are used: lay forecasts of inflation. A first experiment using a between‐participant design showed that the mean level of forecasts and the bias in them are unaffected by the type of forecast but that judgment noise (and, hence, overall error) is higher in point forecasts than in interval or density forecasts. A second experiment replicated the difference between point and interval forecasts in a within‐participant design (of the sort used in inflation surveys) and showed no effect of the order in which different types of forecast are made but revealed that people are more overconfident in interval than in point forecasts. A third experiment showed that volatility in past data increases bias in point but not interval forecasts, and that taking the average of two point forecasts made by an individual reduces judgment noise to the level found in interval forecasting.

Prediction of water source and water volume of underground reservoir in coal mine under multiple aquifers

Abstract The role of coal mine underground reservoirs (CMUR) in ‘guide storage and use’ greatly solves the problem of mine water waste. Replenishment and prediction of reservoir water sources provide an important support for the successful development of key technologies concerning CMUR. To study water replenishment for CMUR, the hydrogeological conditions of the Shendong mining area were investigated as an example. Based on the relationship between the development height of the ‘two belts’ of shallow coal seams and the relative occurrence of location of aquifers, the aquifers are generalized and classified according to occurrences location. Taking Bulianta coal mine as the research background, a discrete element fluid–solid coupling numerical simulation model is constructed to analyze the development characteristics of mining-induced fractures after coal seam mining, and the water replenishment channel of the CMUR is determined. On this basis, analysis is made on the change law of water pressure in the aquifer, aquifuge and coal seam roof under mining action. Taking hydraulic head pressure and water velocity as the judgment basis, prediction and evaluation are made on the water replenishment capacity of CMUR. The research results can provide references for coal mine safety production and mine water protection and utilization.

A full-process intelligent trial system for smart court

In constructing a smart court, to provide intelligent assistance for achieving more efficient, fair, and explainable trial proceedings, we propose a full-process intelligent trial system (FITS). In the proposed FITS, we introduce essential tasks for constructing a smart court, including information extraction, evidence classification, question generation, dialogue summarization, judgment prediction, and judgment document generation. Specifically, the preliminary work involves extracting elements from legal texts to assist the judge in identifying the gist of the case efficiently. With the extracted attributes, we can justify each piece of evidence’s validity by establishing its consistency across all evidence. During the trial process, we design an automatic questioning robot to assist the judge in presiding over the trial. It consists of a finite state machine representing procedural questioning and a deep learning model for generating factual questions by encoding the context of utterance in a court debate. Furthermore, FITS summarizes the controversy focuses that arise from a court debate in real time, constructed under a multi-task learning framework, and generates a summarized trial transcript in the dialogue inspectional summarization (DIS) module. To support the judge in making a decision, we adopt first-order logic to express legal knowledge and embed it in deep neural networks (DNNs) to predict judgments. Finally, we propose an attentional and counterfactual natural language generation (AC-NLG) to generate the court’s judgment.

Context Matters: Recovering Human Semantic Structure from Machine Learning Analysis of Large-Scale Text Corpora.

Applying machine learning algorithms to automatically infer relationships between concepts from large‐scale collections of documents presents a unique opportunity to investigate at scale how human semantic knowledge is organized, how people use it to make fundamental judgments (“How similar are cats and bears?”), and how these judgments depend on the features that describe concepts (e.g., size, furriness). However, efforts to date have exhibited a substantial discrepancy between algorithm predictions and human empirical judgments. Here, we introduce a novel approach to generating embeddings for this purpose motivated by the idea that semantic context plays a critical role in human judgment. We leverage this idea by constraining the topic or domain from which documents used for generating embeddings are drawn (e.g., referring to the natural world vs. transportation apparatus). Specifically, we trained state‐of‐the‐art machine learning algorithms using contextually‐constrained text corpora (domain‐specific subsets of Wikipedia articles, 50+ million words each) and showed that this procedure greatly improved predictions of empirical similarity judgments and feature ratings of contextually relevant concepts. Furthermore, we describe a novel, computationally tractable method for improving predictions of contextually‐unconstrained embedding models based on dimensionality reduction of their internal representation to a small number of contextually relevant semantic features. By improving the correspondence between predictions derived automatically by machine learning methods using vast amounts of data and more limited, but direct empirical measurements of human judgments, our approach may help leverage the availability of online corpora to better understand the structure of human semantic representations and how people make judgments based on those.

Sequential Multi-Task Learning with Task Dependency for Appeal Judgment Prediction

Sequential Multi-Task Learning with Task Dependency for Appeal Judgment Prediction

Recent advances in legal judgment prediction

Recent advances in legal judgment prediction

Legal Judgment Elements Extraction Approach with Law Article-aware Mechanism

Legal judgment elements extraction (LJEE) aims to identify the different judgment features from the fact description in legal documents automatically, which helps to improve the accuracy and interpretability of the judgment results. In real court rulings, judges usually need to scan both the fact descriptions and the law articles repeatedly to find out the relevant information, and it is hard to acquire the key judgment features quickly, so legal judgment elements extraction is a crucial and challenging task for legal judgment prediction. However, most existing methods follow the text classification framework, which fails to model the attentive relations of the law articles and the legal judgment elements. To address this issue, we simulate the working process of human judges, and propose a legal judgment elements extraction method with a law article-aware mechanism, which captures the complex semantic correlations of the law article and the legal judgment elements. Experimental results show that our proposed method achieves significant improvements than other state-of-the-art baselines on the element recognition task dataset. Compared with the BERT-CNN model, the proposed “All labels Law Articles Embedding Model (ALEM)” improves the accuracy, recall, and F1 value by 0.5, 1.4 and 1.0, respectively.

MVE-FLK: A multi-task legal judgment prediction via multi-view encoder fusing legal keywords

Legal Judgment Prediction (LJP) aims to predict the judgment result based on the fact description of a criminal case, and is gradually becoming a hot research topic in the legal realm. Generally, a classic LJP contains three subtasks, i.e., applicable law article prediction, charge prediction, and term of penalty prediction. In real-world scenarios, both charge prediction and applicable law article prediction are actually the tasks of multi-class classification with multi-label learning. However, most existing studies model them as the problems of multi-class classification with single-label learning. Besides, they only consider the context of the fact description, and ignore the exploitation of effective keywords that are widely existed in abundant law articles. To fill the above gaps, we propose a novel multi-task legal judgment prediction framework via multi-view encoder fusing legal keywords, named MVE-FLK, to jointly model multiple subtasks in LJP. Specifically, the multi-view encoder is the core module of MVE-FLK, in this module, we devise a word and sentence encoder (WSE) with an attention mechanism to fuse legal keywords. And then, we develop a multi-view attention network to combine WSE with classic Transformer and DAN (Deep Averaging Network) for encoding the case from multiple views. After that, we propose a multi-task prediction module by developing a novel keywords fusing approach to enhance the performance of multi-task prediction. In addition, we devise a unique prediction principle for each subtask at a fine-grained level, which effectively improves the performance of subtasks. The experimental results on two real-life legal datasets show that our model yields significant prediction performance advantages over six competitive methods.