scholarly journals Reducing the complexity of financial networks using network embeddings

2020 ◽  
Vol 10 (1) ◽  
Author(s):  
M. Boersma ◽  
A. Maliutin ◽  
S. Sourabh ◽  
L. A. Hoogduin ◽  
D. Kandhai
Keyword(s):  
Modern Technology ◽  
Financial Information ◽  
Data Driven ◽  
Financial Networks ◽  
Network Embedding ◽  
Classification Problems ◽  
Accounting Scandals ◽  
Financial Audit ◽  
Financial Expert ◽  
The Stability

Abstract Accounting scandals like Enron (2001) and Petrobas (2014) remind us that untrustworthy financial information has an adverse effect on the stability of the economy and can ultimately be a source of systemic risk. This financial information is derived from processes and their related monetary flows within a business. But as the flows are becoming larger and more complex, it becomes increasingly difficult to distill the primary processes for large amounts of transaction data. However, by extracting the primary processes we will be able to detect possible inconsistencies in the information efficiently. We use recent advances in network embedding techniques that have demonstrated promising results regarding node classification problems in domains like biology and sociology. We learned a useful continuous vector representation of the nodes in the network which can be used for the clustering task, such that the clusters represent the meaningful primary processes. The results show that we can extract the relevant primary processes which are similar to the created clusters by a financial expert. Moreover, we construct better predictive models using the flows from the extracted primary processes which can be used to detect inconsistencies. Our work will pave the way towards a more modern technology and data-driven financial audit discipline.

scholarly journals Data-Driven Stability Assessment of Multilayer Long Short-Term Memory Networks

2021 ◽  
Vol 11 (4) ◽  
pp. 1829
Author(s):  
Davide Grande ◽  
Catherine A. Harris ◽  
Giles Thomas ◽  
Enrico Anderlini
Keyword(s):  
Neural Network ◽  
Network Architecture ◽  
Short Term Memory ◽  
Moving Average ◽  
Machine Learning Algorithms ◽  
Physical Models ◽  
Data Driven ◽  
The Stability ◽  
And Control ◽  
Nonlinear Autoregressive

Recurrent Neural Networks (RNNs) are increasingly being used for model identification, forecasting and control. When identifying physical models with unknown mathematical knowledge of the system, Nonlinear AutoRegressive models with eXogenous inputs (NARX) or Nonlinear AutoRegressive Moving-Average models with eXogenous inputs (NARMAX) methods are typically used. In the context of data-driven control, machine learning algorithms are proven to have comparable performances to advanced control techniques, but lack the properties of the traditional stability theory. This paper illustrates a method to prove a posteriori the stability of a generic neural network, showing its application to the state-of-the-art RNN architecture. The presented method relies on identifying the poles associated with the network designed starting from the input/output data. Providing a framework to guarantee the stability of any neural network architecture combined with the generalisability properties and applicability to different fields can significantly broaden their use in dynamic systems modelling and control.

scholarly journals Audit of Non-financial Information

2020 ◽  
Vol 7 (4) ◽  
pp. 71-80
Author(s):  
R. G. Kaspina ◽  
N. O. Samoilova
Keyword(s):  
Research Problem ◽  
Practical Experience ◽  
Financial Information ◽  
Practical Significance ◽  
Practical Implementation ◽  
Problem Analysis ◽  
Nonfinancial Information ◽  
Current Trends ◽  
Financial Audit ◽  
Definition Of

The article is devoted to the practical implementation of auditing tasks in relation to non-financial information in Russia. The increased need to develop this area of auditing services is related to both the increased interest of users in the nonfinancial information in itself, and the need to improve its reliability. The methodological base of the research includes a set of scientific techniques and research methods such as theoretical analysis of the literature on the research problem, analysis of regulatory sources, a method of comparison, as well as the use of practical experience in providing auditing services in relation to non-financial information. The study of current trends in the publication and certification of nonfinancial statements in Russia and abroad, considers the main approaches to the definition of “non-financial audit” and the most widespread methodological approaches to its implementation, as well as reviews the practice of performing tasks to confirm non-financial information and identifies the main problems of their implementation. The theoretical and practical significance of the research is to justify the need to develop tools for providing auditing services in relation to non-financial information, as well as the proposed solutions to the identified problems of practical implementation of tasks.

scholarly journals Estimating eigenvalues of dynamical systems from time series with applications to predicting cardiac alternans

2012 ◽  
Vol 468 (2147) ◽  
pp. 3649-3666 ◽  
Author(s):  
Adam Petrie ◽  
Xiaopeng Zhao
Keyword(s):  
Dynamical System ◽  
Time Series ◽  
Data Driven ◽  
Standard Errors ◽  
Statistical Techniques ◽  
Likelihood Methods ◽  
Maximum Likelihood Methods ◽  
The Usa ◽  
Cardiac Alternans ◽  
The Stability

The stability of a dynamical system can be indicated by eigenvalues of its underlying mathematical model. However, eigenvalue analysis of a complicated system (e.g. the heart) may be extremely difficult because full models may be intractable or unavailable. We develop data-driven statistical techniques, which are independent of any underlying dynamical model, that use principal components and maximum-likelihood methods to estimate the dominant eigenvalues and their standard errors from the time series of one or a few measurable quantities, e.g. transmembrane voltages in cardiac experiments. The techniques are applied to predicting cardiac alternans that is characterized by an eigenvalue approaching −1. Cardiac alternans signals a vulnerability to ventricular fibrillation, the leading cause of death in the USA.

Stability Issues with Classifier Using Lukasiewicz Similarity and Modified Schweizer & Sklar Equations

2005 ◽  
Vol 9 (5) ◽  
pp. 514-525 ◽  
Author(s):  
Pasi Luukka ◽  
◽  
Jouni Sampo
Keyword(s):  
The Other ◽  
Classification Task ◽  
Classification Problems ◽  
Generalized Mean ◽  
The Stability ◽  
Stability Issues ◽  
Made In

In this article we have tested the stability of a classifier based on Lukasiewicz similarity in the generalized Lukasiewicz structure. We have also tested Schweizer & Sklar's implications with an extension to generalized mean to classification task. We will show that classification results are not so sensitive to p values with Schweizer & Sklar's measures, which indicates a generalized form of equations. In this article we have also tested the stability of these measures. Two different tests for stability were made: In one test the stability was checked with respect to weight parameters and the other test was carried out for idealvectors. The tests were done with five different classification problems.

scholarly journals A common model for the breathlessness experience across cardiorespiratory disease

2021 ◽  
pp. 00818-2020
Author(s):  
Sarah L. Finnegan ◽  
Kyle T.S. Pattinson ◽  
Josefin Sundh ◽  
Magnus Sköld ◽  
Christer Janson ◽  
...  
Keyword(s):  
Body Burden ◽  
Disease Diagnosis ◽  
Adverse Outcomes ◽  
Data Driven ◽  
Compact Set ◽  
Factor Scores ◽  
Model Stability ◽  
Patient Groups ◽  
The Stability

IntroductionChronic breathlessness occurs across many different conditions, often independently of disease severity. Yet, despite being strongly linked to adverse outcomes, the consideration of chronic breathlessness as a stand-alone therapeutic target remains limited. Here we use data-driven techniques to identify and confirm the stability of underlying features (factors) driving breathlessness across different cardiorespiratory diseases.MethodsStudy of questionnaire data on 182 participants with main diagnoses of asthma (21.4%), COPD (24.7%), heart failure (19.2%), idiopathic pulmonary fibrosis (18.7%), other interstitial lung disease (5.5%), and “other diagnoses” (8.8%) were entered into an exploratory factor analysis (EFA). Participants were stratified based on their EFA factor scores. We then examined model stability using six-month follow-up data and established the most compact set of measures describing the breathlessness experience.ResultsIn this dataset, we have identified four stable factors that underlie the experience of breathlessness. These factors were assigned the following descriptive labels: 1) body burden, 2) affect/mood, 3) breathing burden and 4) anger/frustration. Stratifying patients by their scores across the four factors revealed two groups corresponding to high and low burden. These two groups were not related to the primary disease diagnosis and remained stable after six months.DiscussionIn this work we identified and confirmed the stability of underlying features of breathlessness. Previous work in this domain has been largely limited to single-diagnosis patient groups without subsequent re-testing of model stability. This work provides further evidence supporting disease independent approaches to assess breathlessness.

scholarly journals Booster in High Dimensional Data Classification using CNN and Decision Tree Algorithm

2019 ◽  
Vol 8 (2S5) ◽  
pp. 148-152
Keyword(s):  
Decision Tree ◽  
High Dimensional Data ◽  
High Dimensional ◽  
Decision Tree Algorithm ◽  
Classification Problems ◽  
Medical Field ◽  
Sensitive Data ◽  
Tree Algorithm ◽  
Evaluation Measure ◽  
The Stability

Classification problems in high dimensional data with small number of observations are becoming more common especially in microarray data. The performance in terms of accuracy is essential while handling sensitive data particularly in medical field. For this the stability of the selected features must be evaluated. Therefore, this paper proposes a new evaluation measure that incorporates the stability of the selected feature subsets and accuracy of the prediction. Booster in feature selection algorithm helps to achieve the same. The proposed work resolves both structured and unstructured data using convolution neural network based multimodal disease prediction and decision tree algorithm respectively. The algorithm is tested on heart disease dataset retrieved from UCI repository and the analysis shows the improved prediction accuracy.

scholarly journals Data-driven Covariate Selection for Confounding Adjustment by Focusing on the Stability of the Effect Estimator

2021 ◽  
Author(s):  
Wen Wei Loh ◽  
Dongning Ren
Keyword(s):  
Causal Effect ◽  
Data Driven ◽  
Selection Strategy ◽  
Effect Estimate ◽  
Covariate Selection ◽  
Common Causes ◽  
Stable Estimation ◽  
Real World Datasets ◽  
The Stability ◽  
Confounding Adjustment

Valid inference of cause-and-effect relations in observational studies necessitates adjusting for common causes of the focal predictor (i.e., treatment) and the outcome. When such common causes, henceforth termed confounders, remain unadjusted for, they generate spurious correlations that lead to biased causal effect estimates. But routine adjustment for all available covariates, when only a subset are truly confounders, is known to yield potentially inefficient and unstable estimators. In this article, we introduce a data-driven confounder selection strategy that focuses on stable estimation of the treatment effect. The approach exploits the causal knowledge that after adjusting for confounders to eliminate all confounding biases, adding any remaining non-confounding covariates associated with only treatment or outcome, but not both, should not systematically change the effect estimator. The strategy proceeds in two steps. First, we prioritize covariates for adjustment by probing how strongly each covariate is associated with treatment and outcome. Next, we gauge the stability of the effect estimator by evaluating its trajectory adjusting for different covariate subsets. The smallest subset that yields a stable effect estimate is then selected. Thus, the strategy offers direct insight into the (in)sensitivity of the effect estimator to the chosen covariates for adjustment. The ability to correctly select confounders and yield valid causal inference following data-driven covariate selection is evaluated empirically using extensive simulation studies. Furthermore, we compare the proposed method empirically with routine variable selection methods. Finally, we demonstrate the procedure using two publicly available real-world datasets.

scholarly journals Pengaruh Penalaran Moral dan Sensitivitas Etika Terhadap Persepsi Etis dengan Gender Sebagai Variabel Moderasi

2019 ◽  
Vol 17 (1) ◽  
pp. 64
Author(s):  
Theresia Joycelin Jasmine ◽  
Clara Susilawati
Keyword(s):  
Regression Analysis ◽  
Moral Reasoning ◽  
Financial Information ◽  
Accounting Students ◽  
Ethical Sensitivity ◽  
Ethical Perceptions ◽  
Accounting Profession ◽  
Accounting Scandals ◽  
Simple Regression Analysis ◽  
The Relationship

Accounting profession is required to provide true financial information and give confidence to users of financial information. However, many accounting scandals eroded people trust in the accounting profession. Therefore, it is important for prospective accountants to have understanding and knowledge in regard with ethical and moral values. This study examine moderating effect of gender on the the relationship between moral reasoning and ethical perceptions and between ethical sensitivity and ethical perceptions. If accounting students have higher moral reasoning dan ethical sensitivity, the ethical perceptions of accounting students are also predicted to be higher. This study examines moral reasoning and ethical sensitivity to ethical perceptions of accounting students with gender as a moderating variabel using a sample of students from 13 universities in Semarang. This study uses simple regression analysis and moderating regression analysis (MRA). Results show gender effect the relationship between moral reasoning and ethical perceptions, but hass no effect on relationship between ethical sensitivity and ethical perceptions of accounting students. Abstrak Profesi akuntansi dituntut memberikan informasi keuangan yang benar dan memiliki etika sehingga memberikan kepercayaan kepada pengguna informasi keuangan. Namun, banyaknya skandal akuntansi menurunkan kepercayaan terhadap profesi akuntansi. Oleh karena itu, penting bagi calon akuntan memiliki pemahaman dan pengetahuan berperilaku berdasarkan nilai etis dan moral. Penelitian ini menguji efek moderasi gender terhadap hubungan antara penalaran moral dan persepsi etis dan hubungan antara sensitivitas etika dan persepsi etis mahasiswa akuntansi. Jika mahasiswa akuntansi memiliki penalaran moral dan sensitivitas etika yang tinggi maka persepsi etis mahasiswa akuntansi tersebut juga tinggi. Penelitian ini menggunakan sampel mahasiswa dari 13 Universitas di Semarang. Penelitian ini menggunakan analisis regresi sederhana dan moderating regression analysis (MRA). Hasil penelitian menunjukkan bahwa gender mempengaruhi hubungan antara penalaran moral dan sensitivitas etis tetapi tidak mempengaruhi hubungan antara penalaran moral dan persepsi etis mahasiswa akuntansi.

scholarly journals A New Data-Driven Control System for MEMSs Gyroscopes: Dynamics Estimation by Type-3 Fuzzy Systems

Micromachines ◽  
2021 ◽  
Vol 12 (11) ◽  
pp. 1390
Author(s):  
Khalid A. Alattas ◽  
Ardashir Mohammadzadeh ◽  
Saleh Mobayen ◽  
Ayman A. Aly ◽  
Bassem F. Felemban ◽  
...  
Keyword(s):  
Fuzzy System ◽  
Measurement Errors ◽  
Fuzzy Systems ◽  
Data Driven ◽  
Output Data ◽  
Data Set ◽  
Control Scheme ◽  
Mems Gyroscopes ◽  
The Stability ◽  
Type 3

In this study, a novel data-driven control scheme is presented for MEMS gyroscopes (MEMS-Gs). The uncertainties are tackled by suggested type-3 fuzzy system with non-singleton fuzzification (NT3FS). Besides the dynamics uncertainties, the suggested NT3FS can also handle the input measurement errors. The rules of NT3FS are online tuned to better compensate the disturbances. By the input-output data set a data-driven scheme is designed, and a new LMI set is presented to ensure the stability. By several simulations and comparisons the superiority of the introduced control scheme is demonstrated.

The State of Segment Reporting by US Public Entities: 1976-2017

2020 ◽  
Author(s):  
Christine A. Botosan ◽  
Adrienna Huffman ◽  
Mary Harris Stanford
Keyword(s):  
Accounting Standards ◽  
Financial Accounting ◽  
Data Driven ◽  
Financial Accounting Standards Board ◽  
Segment Reporting ◽  
Depth Data ◽  
Sfas 131 ◽  
The Stability ◽  
Segment Disclosures ◽  
Over Time

This paper offers an in-depth data driven overview of the history and status as of 2017 of segment reporting by public entities trading in U.S. capital markets. Our analysis focuses on the perceived issues identified in the Financial Accounting Standards Board (FASB) 2016 Invitation to Comment on FASB's Agenda - the extent of disaggregation into reportable segments, the stability of segmentation over time, the line-items disclosed, and the reconciliation of segment to consolidated totals. We document the trends in and status of segment reporting as of 2017 as another round of efforts to improve segment reporting proceeds. The paper concludes with a discussion of several unanswered questions suggested by the data. Keywords: Segment disclosures, SFAS 131, SFAS 14, ASC 280.

Sign in / Sign up

Export Citation Format

Share Document