scholarly journals Developing an Risk Signal Detection System Based on Opinion Mining for Financial Decision Support

2019 ◽  
Vol 11 (16) ◽  
pp. 4258 ◽  
Author(s):  
Byungun Yoon ◽  
Taeyeoun Roh ◽  
Hyejin Jang ◽  
Dooseob Yun
Keyword(s):  
Opinion Mining ◽  
Prediction Models ◽  
Detection System ◽  
Activity Score ◽  
Risk Level ◽  
Firm Risk ◽  
Integrated Monitoring ◽  
Firm Data ◽  
Credit Event ◽  
Firm Activity

Companies have long sought to detect financial risks and prevent crises in their business activities. Investors also have a great need to identify risks and utilize them for investment. Thus, several studies have attempted to detect financial risk. However, these studies had limitations in that various data were not exploited and diverse perspectives of the firm were not reflected. This can lead to wrong choices for investment. Thus, the purpose of this study was to propose risk signal prediction models based on firm data and opinion mining, reflecting both the perspectives of firms and investors. Furthermore, we developed a process to obtain real time firm related data and convenience visualization. To develop this process, a credit event was defined as an event that led to a critical risk of the firm. In the next step, the firm risk score was calculated for a firm having a possible credit event. This score was calculated by combining the firm activity score and opinion mining score. The firm activity score was calculated based on a financial statement and disclosure data indicator, while the opinion mining score was calculated based on a sentiment analysis of news and social data. As a result, the total firm risk grade was derived, and the risk level was proposed. These processes were developed into a system and illustrated by real firm data. The results of this study demonstrate that it is possible to derive risk signals through integrated monitoring indicators and provide useful information to users. This study can help users make decisions. It also provides users an opportunity to identify new investment momentums.

scholarly journals A Generic Model Of Predicting Probability Of Success-Distress Of An Organization: A Logistic Regression Analysis

2018 ◽  
Vol 34 (1) ◽  
pp. 169-182
Author(s):  
Shyam Bhandari ◽  
Anna J. Johnson-Syder
Keyword(s):  
Cash Flow ◽  
Prediction Models ◽  
Balance Sheet ◽  
Bankruptcy Prediction ◽  
Generic Model ◽  
Income Statement ◽  
Probability Of Success ◽  
Cash Flow Statement ◽  
Firm Data ◽  
Financial Issues

Many bankruptcy prediction models have been created over the years using a mix of variables derived mostly from accrual-based accounting statements and were industry specific. The primary issue with using a model comprised of accrual-based variables is that firm management can manipulate different components and make the balance sheet and income statement misleading (Wanuga 2006). Thus, firms appear financially healthy yet unable to meet the day-to-day cash flow needs of the firm; these financial issues are less likely to be hidden in the cash flow statement (Sharma 2001). In this study, we use a binary regression model with theoretically supported variables obtained from the cash flow statement to forecast firm success versus distress. Of particular interest, we examine firms representing 85 industries using firm data during and immediately following the greatest recession in United States history (Fieldhouse 2014; Lee 2014). The model is generic in the sense that it can be used to predict the probability of success-distress of any entity using the three major financial statements. We find that the overall model correctly classifies organizations 90.290 percent of the time.

Construction of Control Algorithm for an Autonomous Vehicle

2001 ◽  
Vol 13 (4) ◽  
pp. 387-394
Author(s):  
Hyung-Eun Im ◽  
◽  
Ichiro Kageyama ◽  
Yoshiyuki Nozaki
Keyword(s):  
Control Algorithm ◽  
Prediction Models ◽  
Autonomous Vehicle ◽  
Risk Level ◽  
Minimum Risk ◽  
Control Motion ◽  
Risk Elements ◽  
The Road ◽  
On The Road ◽  
Risk Potential

In this study, a control algorithm of an autonomous vehicle is proposed on the basis of risk level to simulate control motion of a real driver. The normal traffic situation can be expressed by risk level. The risk level is affected by several risk elements: roadside edges, curves, the other vehicles, obstacles, and so on. Each risk element is represented by an exponential function. The risk elements make risk potential field on the road. It is assumed that the desirable course to follow is determined as the point of minimum risk potential in the cross section of the road. Tree prediction models are examined to predict the future position of vehicle. The change of preview time is considered on the curved road. A lateral and longitudinal control algorithm with the prediction model proposed in this study shows similar control motion to that of a real driver.

scholarly journals Research on the prediction model of elderly fall

2021 ◽  
Vol 336 ◽  
pp. 07019
Author(s):  
Shaohua Guo ◽  
Yinggang Xie ◽  
Yuxin Li
Keyword(s):  
Prediction Model ◽  
Prediction Models ◽  
Detection System ◽  
Research Work ◽  
Fall Detection ◽  
The Elderly ◽  
Wearable Device ◽  
Fall Prediction ◽  
Collection Data ◽  
Coordination Ability

As the world’s aging process accelerates, the issue of elderly safety is about to become a serious social problem. The elderly are prone to falls due to physiological reasons such as decreased physical function, weakened balance and coordination ability, and poor vision. The study of fall prediction models can predict the impending fall behavior in time before the fall, and have enough time to remind the elderly to adjust or take corresponding protective measures. Reduce the damage caused by falls to the human body, reduce the medical expenses caused by falls, and enhance the confidence of the elderly to live independently. This article gives a detailed overview of the research on the wearable device-based fall prediction system, and introduces the entire process of falling. According to the work flow of the wearable device fall detection system, it includes data collection, data preprocessing, feature extraction, and discrimination algorithms. Several aspects of the current research work are introduced, and the existing research results are classified, compared and statistically analyzed to provide meaningful reference and reference for subsequent research work. Finally, a fall prediction model based on an improved ConvLSTM is proposed.

scholarly journals 1255. External Validation and Systematic Quantification of the Predictive Performance of Carbapenem Resistant Enterobacterales Risk Prediction Models in Hospitalized Patients

2021 ◽  
Vol 8 (Supplement_1) ◽  
pp. S716-S717
Author(s):  
Andras Farkas ◽  
Arsheena Yassin ◽  
Hendrik Sy ◽  
Kristy Huang ◽  
Iana Stein ◽  
...  
Keyword(s):  
Risk Prediction ◽  
Prediction Models ◽  
False Negative ◽  
False Negative Rate ◽  
Model Performance ◽  
Hospitalized Patients ◽  
Risk Level ◽  
Timely Initiation ◽  
Risk Prediction Models ◽  
Carbapenem Resistant

Abstract Background Accurately predicting the presence of a carbapenem resistant enterobacterales (CRE) in hospitalized patients presents itself as an opportunity that would support timely initiation of CRE active agents. The aim of this study is to determine how reliably the existing risk prediction models identify patients likely to require empiric anti-CRE treatment, preliminary results of which are presented herein. Methods A systematic search identified all existing CRE prediction models for validation in our patient population. Medical records of hospitalized patients within the Mount Sinai Health System in New York were subsequently reviewed. Data was gathered on model predictors, baseline demographics, clinical information, microbiology results, antibiotic utilization history and index infection. Besides calculating the AUROC, the main outcome of our study was to establish optimal prediction score cutoffs and false positive rates (FPR) where corresponding model performance maintains a false negative rate (FNR) of < 10%, < 20% and < 30%, respectively. Results 12 models were retained for validation. We identified 106 patients, 41 of which were treated for a CRE infection. Previous admission, organ transplantation, CKD, infection type, and carbapenem use were baseline variables that significantly differed between the groups treated for a CRE or non-CRE related infection (Table 1). The models ability to discriminate varied as evidenced by the AUROC range of 0.5 to 0.77 (Figure 1), suggesting the Seligmen et al. model as the overall best. When evaluated at the pre-specified FNR intervals of < 10%, < 20% and < 30%, the model by Lodise et al., Seligman et al., and Vazquez-Guillamet et al. produced the best FPR, respectively (Table 2). Table 1. Baseline characchteristics Table 2. Model Performance Figure 1. AUROCs Conclusion Discriminative ability of the risk prediction models showed varying performance. The model by Lodise et al. appears to be most useful when a low risk level is deemed acceptable for failure rate, while at a moderate to high risk of missing a CRE case (20% and 30% FNR), the methods by Seligman and Vazquez-Guillamet et al. are most desirable as they minimize the chance of over-treatment. Additional work to increase sample size and to evaluate the models inter-rater reliability is currently on going. Disclosures All Authors: No reported disclosures

Predicting Imminent Crash Risk with Simulated Traffic from Distant Sensors

2018 ◽  
Vol 2672 (38) ◽  
pp. 12-21
Author(s):  
Zhi Chen ◽  
Xiao Qin ◽  
Renxin Zhong ◽  
Pan Liu ◽  
Yang Cheng
Keyword(s):  
Real Time ◽  
Prediction Models ◽  
Detection System ◽  
Data Retrieval ◽  
Transmission Model ◽  
Traffic Data ◽  
Crash Prediction ◽  
Station Data ◽  
Virtual Station ◽  
Crash Prediction Models

The aim of this research was to investigate the performance of simulated traffic data for real-time crash prediction when loop detector stations are distant from the actual crash location. Nearly all contemporary real-time crash prediction models use traffic data from physical detector stations; however, the distance between a crash location and its nearest detector station can vary considerably from site to site, creating inconsistency in detector data retrieval and subsequent crash prediction. Moreover, large distances between crash locations and detector stations imply that traffic data from these stations may not truly reflect crash-prone conditions. Crash and noncrash events were identified for a freeway section on I-94 EB in Wisconsin. The cell transmission model (CTM), a macroscopic simulation model, was applied in this study to instrument segments with virtual detector stations when physical stations were not available near the crash location. Traffic data produced from the virtual stations were used to develop crash prediction models. A comparison revealed that the predictive accuracy of models developed with virtual station data was comparable to those developed with physical station data. The finding demonstrates that simulated traffic data are a viable option for real-time crash prediction given distant detector stations. The proposed approach can be used in the real-time crash detection system or in a connected vehicle environment with different settings.

scholarly journals Corporate ownership structure and risk-taking: evidence from Japan

2017 ◽  
Vol 6 (4) ◽  
pp. 39-52 ◽  
Author(s):  
SunEae Chun ◽  
MinHwan Lee
Keyword(s):  
Financial Institutions ◽  
Ownership Structure ◽  
Risk Taking ◽  
Pension Funds ◽  
Insurance Companies ◽  
Risk Level ◽  
Managerial Ownership ◽  
Firm Risk ◽  
Concentrated Ownership ◽  
Corporate Risk

We examine the relationship between ownership structure and corporate risk-taking in Japan over the sample periods of 2000 2010. Reflecting the ongoing changes in the ownership structure in Japan, we incorporate the various kinds of insider and outsider ownership in the analysis. Ownership such as concentrated ownership, ownership by closely related parties, financial institutions comprising banks and insurance companies and managers are categorized into inside ownership, while ownership by foreigners or financial institution such as investment trusts or pension funds are categorized into outside ownership. The ownership structure is found to have a different impact on the firm’s risk-taking behavior. The study shows that concentrated ownership or ownership by closely related parties affect the firm risks in a convex manner and encourages the firm management to take more risk when the firms have growth opportunities. On the other hand, ownership by financial institutions such as bank and insurance companies, does not seem to affect the firm risk level. This implies that the financial institutions fail to play their role of a shareholder monitor. When managerial ownership is allowed, it is found that Japanese managers’ incentives are aligned with those of shareholders. Contrary to the conventional entrenchment hypothesis, however, managers seem to take more risk as the share of managerial ownership increases. Foreign investors are found to enhance corporate risk-taking in a monotonic manner and do not bias corporate investment in a conservative direction in pursuit of their short-term gains. Domestic institutions such as investment trusts or pension funds are found to neither affect the firm risk level nor enhance the firm value.

scholarly journals IoT-Inspired Framework of Intruder Detection for Smart Home Security Systems

Electronics ◽  
2020 ◽  
Vol 9 (9) ◽  
pp. 1361
Author(s):  
Tariq Ahamed Ahanger ◽  
Usman Tariq ◽  
Atef Ibrahim ◽  
Imdad Ullah ◽  
Yassine Bouteraa
Keyword(s):  
Real Time ◽  
Smart Home ◽  
Prediction Models ◽  
Fuzzy Inference ◽  
Detection System ◽  
Fog Computing ◽  
Foot Pressure ◽  
Inference System ◽  
Predictive Learning ◽  
Home Based

The proliferation of IoT devices has led to the development of smart appliances, gadgets, and instruments to realize a significant vision of a smart home. Conspicuously, this paper presents an intelligent framework of a foot-mat-based intruder-monitoring and detection system for a home-based security system. The presented approach incorporates fog computing technology for analysis of foot pressure, size, and movement in real time to detect personnel identity. The task of prediction is realized by the predictive learning-based Adaptive Neuro-Fuzzy Inference System (ANFIS) through which the proposed model can estimate the possibility of an intruder. In addition to this, the presented approach is designed to generate a warning and emergency alert signals for real-time indications. The presented framework is validated in a smart home scenario database, obtained from an online repository comprising 49,695 datasets. Enhanced performance was registered for the proposed framework in comparison to different state-of-the-art prediction models. In particular, the presented model outperformed other models by obtaining efficient values of temporal delay, statistical performance, reliability, and stability.

Multiple Imputation by Chained Equations–K-Nearest Neighbors and Deep Neural Network Architecture for Kidney Disease Prediction

2021 ◽  
Author(s):  
M. Dhilsath Fathima ◽  
R. Hariharan ◽  
S. P. Raja
Keyword(s):  
Neural Network ◽  
Kidney Disease ◽  
Multiple Imputation ◽  
Deep Neural Network ◽  
Missing Values ◽  
Prediction Models ◽  
Model Performance ◽  
Nearest Neighbors ◽  
Risk Level ◽  
Clinical Dataset

Chronic kidney disease (CKD) is a health concern that affects people all over the world. Kidney dysfunction or impaired kidney functions are the causes of CKD. The machine learning-based prediction models are used to determine the risk level of CKD and assist healthcare practitioners in delaying and preventing the disease’s progression. The researchers proposed many prediction models for determining the CKD risk level. Although these models performed well, their precision is limited since they do not handle missing values in the clinical dataset adequately. The missing values of a clinical dataset can degrade the training outcomes that leads to false predictions. Thus, imputing missing values increases the prediction model performance. This proposed work developed a novel imputation technique by combining Multiple Imputation by Chained Equations and [Formula: see text]-Nearest Neighbors (MICE–KNN) for imputing the missing values. The experimental results show that MICE–KNN accurately predicts the missing values, and the Deep Neural Network (DNN) improves the prediction performance of the CKD model. Various metrics like mean absolute error, accuracy, specificity, Matthews correlation coefficient, the area under the curve, [Formula: see text]-score, sensitivity, and precision have been used to evaluate the proposed CKD model performance. The performance analysis exhibits that MICE–KNN with deep learning outperforms other classifiers. According to our experimental study, the MICE–KNN imputation algorithm with DNN is more appropriate for predicting the kidney disease.

A Change Point Detection Approach for Intelligent Real-Time Identification of Lost Circulation Events During Drilling Operations

2021 ◽  
Author(s):  
Francesco Cannarile ◽  
Stefano Montoli ◽  
Giuseppe Giliberto ◽  
Mauro Suardi ◽  
Benedetta Di Bari ◽  
...  
Keyword(s):  
Change Point ◽  
Structural Changes ◽  
Prediction Models ◽  
Detection System ◽  
Drilling Fluid ◽  
Change Point Detection ◽  
Lost Circulation ◽  
Drilling Operations ◽  
Point Detection ◽  
Mud Flow

Abstract Lost circulation is a challenging aspect during drilling operations as uncontrolled flow of wellbore fluids into formation can expose rig personnel and environment to risks. Further, the time required to regain the circulation of drilling fluid typically results in unplanned Non-Productive Time (NPT) causing undesired amplified drilling cost. Thus, it is of primary importance to support drilling supervisors with accurate and effective detection tools for safe and economic drilling operations. In this framework, a novel lost circulation intelligent detection system is proposed which relies on the simultaneous identification of decreasing trends in the paddle mud flow-out and standpipe pressure signals, at constant mud flow-in rate. First, mud flow-out and standpipe pressure signals underlie cubic-spline-based smoothing step to remove background noise caused by the measurement instrument and the intrinsic variability of the drilling environment. To identify structural changes in the considered signals, a nonparametric kernel-based change point detection algorithm is employed. Finally, an alarm is raised if flow-out and standpipe pressure decreasing trends have been detected and their negative variations are below prefixed threshold values. The proposed intelligent lost circulation detection system has been verified with respect to historical field data recorded from several Eni wells located in different countries. Results show that the proposed system satisfactorily and reliably detects both partial and total lost circulation events. Further, its integration with already existing Eni NPT prediction models has led to a significant improvement in terms of events correctly triggered.

scholarly journals Plasma Amyloid-β Oligomerization Tendency Predicts Amyloid PET Positivity

2020 ◽  
Author(s):  
Jung-Min Pyun ◽  
Ji Sun Ryu ◽  
Ryan Lee ◽  
KyuHawn Shim ◽  
Young Chul Youn ◽  
...  
Keyword(s):  
High Performance ◽  
Prediction Models ◽  
Mmse Score ◽  
Detection System ◽  
Amyloid Β ◽  
Visual Assessment ◽  
Research Field ◽  
Amyloid Pet ◽  
Apoe Ε4 ◽  
Auc Value

Abstract Background: Among other emerging amyloid-targeting blood-based biomarkers, Multimer Detection System-Oligomeric Amyloid-β (MDS-OAβ) measures dynamic changes in concentration of oligomeric amyloid-β (OAβ), which is considered the main pathogenic culprit of Alzheimer’s disease (AD), in plasma after spiking with synthetic amyloid-β (Aβ). We aimed to investigate predictability of MDS-OAβ on amyloid Positron Emission Tomography (PET) positivity.Methods: A total of 96 subjects who visited Seoul National University Bundang Hospital for medical check-up complaining of cognitive decline and had undergone extensive medical assessment were recruited. Amyloid statuses were dichotomized into positive or negative based on visual assessment of amyloid PET. Plasma OAβ concentration was measured by MDS-OAβ. In the previous validation study, 0.78ng/ml was established as the cut-off value and the plasma OAβ concentration higher than or equal to the cut-off value was defined MDS-OAβ positive.Results: MDS-OAβ positivity could discriminate amyloid PET positivity with the AUC value of 0.855 (95% CI 0.776–0.933). Adding MDS-OAβ positivity to prediction models including age, MMSE score, and APOE ε4 status improved the performance up to the AUC value of 0.926 (95% CI 0.871–0.980).Conclusions: The Aβ oligomerization tendency in plasma could predict amyloid PET positivity with high performance, and when it is combined with age, MMSE score, and APOE ε4 status, the predictability was improved substantially. This suggests the potential of MDS-OAβ as a useful initial stage test in clinical and research field of AD.

Sign in / Sign up

Export Citation Format

Share Document