Applying Deep Learning to Audit Procedures: An Illustrative Framework

2019 ◽  
Vol 33 (3) ◽  
pp. 89-109 ◽  
Author(s):  
Ting (Sophia) Sun
Keyword(s):  
Decision Making ◽  
Deep Learning ◽  
Data Warehouse ◽  
Visual Recognition ◽  
Prediction Models ◽  
Historical Data ◽  
Structured Data ◽  
Text Understanding ◽  
Audit Data ◽  
Learning Functions

SYNOPSIS This paper aims to promote the application of deep learning to audit procedures by illustrating how the capabilities of deep learning for text understanding, speech recognition, visual recognition, and structured data analysis fit into the audit environment. Based on these four capabilities, deep learning serves two major functions in supporting audit decision making: information identification and judgment support. The paper proposes a framework for applying these two deep learning functions to a variety of audit procedures in different audit phases. An audit data warehouse of historical data can be used to construct prediction models, providing suggested actions for various audit procedures. The data warehouse will be updated and enriched with new data instances through the application of deep learning and a human auditor's corrections. Finally, the paper discusses the challenges faced by the accounting profession, regulators, and educators when it comes to applying deep learning.

Physical Data Warehousing Design

2011 ◽  
pp. 906-911 ◽  
Author(s):  
Ladjel Bellatreche ◽  
Mukesh Mohania
Keyword(s):  
Decision Making ◽  
Data Warehouse ◽  
Historical Data ◽  
Data Warehousing ◽  
Management Decision ◽  
Materialized Views ◽  
Performance Goal ◽  
Interactive Nature ◽  
Management Decision Making ◽  
Using Data

Recently, organizations have increasingly emphasized applications in which current and historical data are analyzed and explored comprehensively, identifying useful trends and creating summaries of the data in order to support high-level decision making. Every organization keeps accumulating data from different functional units, so that they can be analyzed (after integration), and important decisions can be made from the analytical results. Conceptually, a data warehouse is extremely simple. As popularized by Inmon (1992), it is a “subject-oriented, integrated, time-invariant, non-updatable collection of data used to support management decision-making processes and business intelligence”. A data warehouse is a repository into which are placed all data relevant to the management of an organization and from which emerge the information and knowledge needed to effectively manage the organization. This management can be done using data-mining techniques, comparisons of historical data, and trend analysis. For such analysis, it is vital that (1) data should be accurate, complete, consistent, well defined, and time-stamped for informational purposes; and (2) data should follow business rules and satisfy integrity constraints. Designing a data warehouse is a lengthy, time-consuming, and iterative process. Due to the interactive nature of a data warehouse application, having fast query response time is a critical performance goal. Therefore, the physical design of a warehouse gets the lion’s part of research done in the data warehousing area. Several techniques have been developed to meet the performance requirement of such an application, including materialized views, indexing techniques, partitioning and parallel processing, and so forth. Next, we briefly outline the architecture of a data warehousing system.

scholarly journals Warehouse Data System Analysis PT. Kanaan Global Indonesia

2020 ◽  
Vol 1 (3) ◽  
pp. 70-73
Author(s):  
Tino Feri Efendi ◽  
Mutiya Krisanty
Keyword(s):  
Decision Making ◽  
Data Warehouse ◽  
Inventory Control ◽  
Research Method ◽  
System Analysis ◽  
Historical Data ◽  
Decision Making Process ◽  
Literature Study ◽  
Precise Information ◽  
Operational Systems

Data Warehouse is a computer system for archiving and analyzing historical data of an organization. An organization copies information from its operational systems to a warehouse. The purpose of this research is to help provide information in supporting the decision-making process in the field of sales, purchasing and material inventory control at PT Kanaan Global Indonesia. PT Kanaan Global Indonesia previously presented the data warehouse manually. By designing a data warehouse system, company leaders can be more assisted in making decisions that are faster and more precise. The research method used includes analysis of observations, interviews, documentation and literature study. The result of this research is the availability of a data warehouse that can produce fast and precise information, thus helping the company in making decisions.Keywords— Data, Information, Warehouse

scholarly journals Combining structured and unstructured data for predictive models: a deep learning approach

2020 ◽  
Author(s):  
Dongdong Zhang ◽  
Changchang Yin ◽  
Jucheng Zeng ◽  
Xiaohui Yuan ◽  
Ping Zhang
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Medical Information ◽  
Prediction Models ◽  
Short Term Memory ◽  
Heterogeneous Data ◽  
Structured Data ◽  
Unstructured Data ◽  
Data Types ◽  
Clinical Notes

Background: The broad adoption of Electronic Health Records (EHRs) provides great opportunities to conduct health care research and solve various clinical problems in medicine. With recent advances and success, methods based on machine learning and deep learning have become increasingly popular in medical informatics. However, while many research studies utilize temporal structured data on predictive modeling, they typically neglect potentially valuable information in unstructured clinical notes. Integrating heterogeneous data types across EHRs through deep learning techniques may help improve the performance of prediction models. Methods: In this research, we proposed 2 general-purpose multi-modal neural network architectures to enhance patient representation learning by combining sequential unstructured notes with structured data. The proposed fusion models leverage document embeddings for the representation of long clinical note documents and either convolutional neural network or long short-term memory networks to model the sequential clinical notes and temporal signals, and one-hot encoding for static information representation. The concatenated representation is the final patient representation which is used to make predictions. Results: We evaluate the performance of proposed models on 3 risk prediction tasks (i.e., in-hospital mortality, 30-day hospital readmission, and long length of stay prediction) using derived data from the publicly available Medical Information Mart for Intensive Care III dataset. Our results show that by combining unstructured clinical notes with structured data, the proposed models outperform other models that utilize either unstructured notes or structured data only. Conclusions: The proposed fusion models learn better patient representation by combining structured and unstructured data. Integrating heterogeneous data types across EHRs helps improve the performance of prediction models and reduce errors.

Physical Data Warehousing Design

2011 ◽  
pp. 1546-1551
Author(s):  
Ladjel Bellatreche ◽  
Mukesh Mohania
Keyword(s):  
Decision Making ◽  
Data Warehouse ◽  
Historical Data ◽  
Data Warehousing ◽  
Management Decision ◽  
Materialized Views ◽  
Performance Goal ◽  
Interactive Nature ◽  
Management Decision Making ◽  
Using Data

Recently, organizations have increasingly emphasized applications in which current and historical data are analyzed and explored comprehensively, identifying useful trends and creating summaries of the data in order to support high-level decision making. Every organization keeps accumulating data from different functional units, so that they can be analyzed (after integration), and important decisions can be made from the analytical results. Conceptually, a data warehouse is extremely simple. As popularized by Inmon (1992), it is a “subject-oriented, integrated, time-invariant, nonupdatable collection of data used to support management decision-making processes and business intelligence”. A data warehouse is a repository into which are placed all data relevant to the management of an organization and from which emerge the information and knowledge needed to effectively manage the organization. This management can be done using data-mining techniques, comparisons of historical data, and trend analysis. For such analysis, it is vital that (1) data should be accurate, complete, consistent, well defined, and time-stamped for informational purposes; and (2) data should follow business rules and satisfy integrity constraints. Designing a data warehouse is a lengthy, time-consuming, and iterative process. Due to the interactive nature of a data warehouse application, having fast query response time is a critical performance goal. Therefore, the physical design of a warehouse gets the lion’s part of research done in the data warehousing area. Several techniques have been developed to meet the performance requirement of such an application, including materialized views, indexing techniques, partitioning and parallel processing, and so forth. Next, we briefly outline the architecture of a data warehousing system.

scholarly journals THE DEVELOPMENT OF THE APPLICATION OF A DATA WAREHOUSE AT PT JKL

2012 ◽  
Vol 6 (1) ◽  
pp. 8 ◽  
Author(s):  
Choirul Huda ◽  
Rita Puspita Sari ◽  
Muharram Hasein Haekal ◽  
Tri Agustaria
Keyword(s):  
Decision Making ◽  
Information Technology ◽  
Data Warehouse ◽  
Historical Data ◽  
Decision Making Process ◽  
Literature Study ◽  
Process Methodology ◽  
The Right ◽  
A Company ◽  
Analyze Data

One rapidly evolving technology today is information technology, which can help decision-making in an organization or a company. The data warehouse is one form of information technology that supports those needs, as one of the right solutions for companies in decision-making. The objective of this research is the development of a data warehouse at PT JKL in order to support executives in analyzing the organization and support the decision-making process. Methodology of this research is conducting interview with related units, literature study and document examination. This research also used the Nine Step Methodology developed by Kimball to design the data warehouse. The results obtained is an application that can summarize the data warehouse, integrating and presenting historical data in multidimensional. The conclusion from this research is the data warehouse can help companies to analyze data in a flexible, fast, and effective data access.Keywords: Data Warehouse; Inventory; Contract Approval; Inventory; Dashboard

scholarly journals Combining structured and unstructured data for predictive models: a deep learning approach

2020 ◽  
Vol 20 (1) ◽  
Author(s):  
Dongdong Zhang ◽  
Changchang Yin ◽  
Jucheng Zeng ◽  
Xiaohui Yuan ◽  
Ping Zhang
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Medical Information ◽  
Prediction Models ◽  
Short Term Memory ◽  
Heterogeneous Data ◽  
Structured Data ◽  
Unstructured Data ◽  
Data Types ◽  
Clinical Notes

Abstract Background The broad adoption of electronic health records (EHRs) provides great opportunities to conduct health care research and solve various clinical problems in medicine. With recent advances and success, methods based on machine learning and deep learning have become increasingly popular in medical informatics. However, while many research studies utilize temporal structured data on predictive modeling, they typically neglect potentially valuable information in unstructured clinical notes. Integrating heterogeneous data types across EHRs through deep learning techniques may help improve the performance of prediction models. Methods In this research, we proposed 2 general-purpose multi-modal neural network architectures to enhance patient representation learning by combining sequential unstructured notes with structured data. The proposed fusion models leverage document embeddings for the representation of long clinical note documents and either convolutional neural network or long short-term memory networks to model the sequential clinical notes and temporal signals, and one-hot encoding for static information representation. The concatenated representation is the final patient representation which is used to make predictions. Results We evaluate the performance of proposed models on 3 risk prediction tasks (i.e. in-hospital mortality, 30-day hospital readmission, and long length of stay prediction) using derived data from the publicly available Medical Information Mart for Intensive Care III dataset. Our results show that by combining unstructured clinical notes with structured data, the proposed models outperform other models that utilize either unstructured notes or structured data only. Conclusions The proposed fusion models learn better patient representation by combining structured and unstructured data. Integrating heterogeneous data types across EHRs helps improve the performance of prediction models and reduce errors.

scholarly journals Study and Performance Analysis of Different Techniques for Computing Data Cubes

2019 ◽  
pp. 33-42
Author(s):  
Aiasha Siddika
Keyword(s):  
Decision Making ◽  
Data Warehouse ◽  
Historical Data ◽  
Large Data ◽  
Online Analytical Processing ◽  
Huge Amount ◽  
Data Volume ◽  
Analytical Processing ◽  
And Performance ◽  
Problem Data

Data is an integrated form of observable and recordable facts in operational or transactional systems in the data warehouse. Usually, data warehouse stores aggregated and historical data in multi-dimensional schemas. Data only have value to end-users when it is formulated and represented as information. And Information is a composed collection of facts for decision making. Cube computation is the most efficient way for answering this decision making queries and retrieve information from data. Online Analytical Process (OLAP) used in this purpose of the cube computation. There are two types of OLAP: Relational Online Analytical Processing (ROLAP) and Multidimensional Online Analytical Processing (MOLAP).This research worked on ROLAP and MOLAP and then compare both methods to find out the computation times by the data volume. Generally, a large data warehouse produces an extensive output, and it takes a larger space with a huge amount of empty data cells. To solve this problem, data compression is inevitable. Therefore, Compressed Row Storage (CRS) is applied to reduce empty cell overhead.

A Historical Data based Ensemble System for Efficient Stock Price Prediction

2019 ◽  
Vol 12 ◽  
Author(s):  
Vijay Kumar Dwivedi ◽  
Manoj Madhava Gore
Keyword(s):  
Stock Price ◽  
Prediction Models ◽  
Historical Data ◽  
Stock Exchange ◽  
Primary Objective ◽  
Lasso Regression ◽  
Stock Price Prediction ◽  
Price Prediction ◽  
Consistent Manner ◽  
Selection Operator

Background: Stock price prediction is a challenging task. The social, economic, political, and various other factors cause frequent abrupt changes in the stock price. This article proposes a historical data-based ensemble system to predict the closing stock price with higher accuracy and consistency over the existing stock price prediction systems. Objective: The primary objective of this article is to predict the closing price of a stock for the next trading in more accurate and consistent manner over the existing methods employed for the stock price prediction. Method: The proposed system combines various machine learning-based prediction models employing least absolute shrinkage and selection operator (LASSO) regression regularization technique to enhance the accuracy of stock price prediction system as compared to any one of the base prediction models. Results: The analysis of results for all the eleven stocks (listed under Information Technology sector on the Bombay Stock Exchange, India) reveals that the proposed system performs best (on all defined metrics of the proposed system) for training datasets and test datasets comprising of all the stocks considered in the proposed system. Conclusion: The proposed ensemble model consistently predicts stock price with a high degree of accuracy over the existing methods used for the prediction.

scholarly journals Explaining deep neural networks for knowledge discovery in electrocardiogram analysis

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Steven A. Hicks ◽  
Jonas L. Isaksen ◽  
Vajira Thambawita ◽  
Jonas Ghouse ◽  
Gustav Ahlberg ◽  
...  
Keyword(s):  
Decision Making ◽  
Deep Learning ◽  
Deep Neural Networks ◽  
Clinical Decision Making ◽  
Medical Knowledge ◽  
Clinical Decision ◽  
Medical Data ◽  
Medical Doctors ◽  
Medical Tests ◽  
Deep Learning Model

AbstractDeep learning-based tools may annotate and interpret medical data more quickly, consistently, and accurately than medical doctors. However, as medical doctors are ultimately responsible for clinical decision-making, any deep learning-based prediction should be accompanied by an explanation that a human can understand. We present an approach called electrocardiogram gradient class activation map (ECGradCAM), which is used to generate attention maps and explain the reasoning behind deep learning-based decision-making in ECG analysis. Attention maps may be used in the clinic to aid diagnosis, discover new medical knowledge, and identify novel features and characteristics of medical tests. In this paper, we showcase how ECGradCAM attention maps can unmask how a novel deep learning model measures both amplitudes and intervals in 12-lead electrocardiograms, and we show an example of how attention maps may be used to develop novel ECG features.

scholarly journals Exploiting Data Analytics and Deep Learning Systems to Support Pavement Maintenance Decisions

2021 ◽  
Vol 11 (6) ◽  
pp. 2458
Author(s):  
Ronald Roberts ◽  
Laura Inzerillo ◽  
Gaetano Di Mino
Keyword(s):  
Deep Learning ◽  
Management Practices ◽  
Prediction Models ◽  
Road Networks ◽  
Pavement Management ◽  
Efficient Operation ◽  
Pavement Maintenance ◽  
Goods And Services ◽  
Maintenance Decisions ◽  
Computational Systems

Road networks are critical infrastructures within any region and it is imperative to maintain their conditions for safe and effective movement of goods and services. Road Management, therefore, plays a key role to ensure consistent efficient operation. However, significant resources are required to perform necessary maintenance activities to achieve and maintain high levels of service. Pavement maintenance can typically be very expensive and decisions are needed concerning planning and prioritizing interventions. Data are key towards enabling adequate maintenance planning but in many instances, there is limited available information especially in small or under-resourced urban road authorities. This study develops a roadmap to help these authorities by using flexible data analysis and deep learning computational systems to highlight important factors within road networks, which are used to construct models that can help predict future intervention timelines. A case study in Palermo, Italy was successfully developed to demonstrate how the techniques could be applied to perform appropriate feature selection and prediction models based on limited data sources. The workflow provides a pathway towards more effective pavement maintenance management practices using techniques that can be readily adapted based on different environments. This takes another step towards automating these practices within the pavement management system.

Sign in / Sign up

Export Citation Format

Share Document