Document Type
Theses, Masters
Master Thesis
Master thesis
Rights
Available under a Creative Commons Attribution Non-Commercial Share Alike 4.0 International Licence
Disciplines
5.2 ECONOMICS AND BUSINESS
Abstract
The main aim of this thesis is to document the process of developing Big Data analytical applications and their integration with financial statement datasets. These datasets are publicly available on the U.S. SEC (Security and Exchange Commission) website which contains the annual and quarterly reports of approximately 8000 companies. Through its Electronic Data Gathering, Analysis and Retrieval (EDGAR) system, the SEC receives several terabytes of data in the mandatory filings from its registrants. This vast amount of data can potentially provide a valuable resource for those parties (such as investors, analysts, regulators and researchers) who are interested in assessing the financial performance and position of companies. Traditionally, the quarterly and annual reports were submitted in standard PDF, HTML and Text files. The data from these files could be manually extracted and analysed, but this process (still used by some analysts and researchers) is costly and time-consuming.
In 2009, the SEC mandated all listed companies to use a digital reporting format known as XBRL (eXtensible Business Reporting Language). The intention of this was to improve financial reporting in terms of transparency and efficiency. In order to take advantage of structured data contained in the XBRL format, a variety of methods such as novel extraction algorithms and data mining techniques have been developed. However, several limitations and issues have emerged. These include a lack of automated connectivity between the EDGAR web interface and the terms used in structured taxonomies, and the inability to provide access to multiple files in a single query.
Given the challenging and complex nature of these issues, this research project used the financial statement datasets available on the SEC website to extract relevant financial information from the company’s annual reports. The novel aspect of this research is providing big data analytical applications using cloud technologies that can efficiently perform datasets integration and transformation into a format suitable for further analysis. The result of this is that the extracted financial data can be analysed to assess the performance of companies, and this facilitates the critical examination of widely used credit assessment models such as the Altman Z’-Score.
DOI
https://doi.org/10.21427/KJ3E-FE83
Recommended Citation
Sadula, S. (2023). Integrating Big Data Analytics with U.S. SEC Financial Statement Datasets and the Critical Examination of the Altman Z’-Score Model. Technological University Dublin. DOI: 10.21427/KJ3E-FE83
Document Type
Master thesis
Publication Details
Submitted for the award of Master of Philosophy, School of Business and Humanities, Tallaght Campus, Technological University Dublin, January 2023.