Document Details
|
Document Type |
: |
Thesis |
|
Document Title |
: |
The Role of Data Mining Tools in Extracting Knowledge from Big Data in Saudi Banking Sector دور أدوات التنقيب في استخراج المعارف من البيانات البنكية الضخمة في القطاع المصرفي السعودي |
|
Subject |
: |
Faculty of Arts and Humanities |
|
Document Language |
: |
Arabic |
|
Abstract |
: |
In light of the implementation of Vision 2030 in the Kingdom of Saudi Arabia, business environment, especially the financial sector, is witnessing major transformations changing customer and employee expectations. Banks became aware of the importance of technology and gave priority to technical investments to support their interests and reach their goals. On the other hand, data is considered one of the most valuable assets for any organization, especially if the organization is able to reveal the hidden value in the primary data in the organization’s databases through the use of data mining tools, as data mining allows extracting knowledge from historical and hidden data in the form of patterns and correlations in rules and predict the outcome of future situations. Data mining also helps improve business decisions, increase customer value, communicate, and improve customer satisfaction. Leading banks use data mining tools for customer segmentation and profitability, credit scoring and approval, default prediction, marketing, fraudulent transaction detection and so on. There are many data mining tools out there that work equally well but some are more valuable than others. Banks and financial institutions suffer from many illegal operations related to fraud and piracy. Accordingly, it was necessary to find a way to detect such difficulties, in addition to knowing the behavior of borrowers and defaulters, which facilitates decision-making. This thesis aims to examine data mining tools and stand on their role in extracting knowledge, in addition to nominating the optimal and most effective data mining tool for extracting knowledge from big data, which contributes to detecting credit risks in Saudi banks. This research presents an analytical study of eight data mining tools, which include eight techniques such as clustering, summarization, correlation rules/ analysis, sequence discovery, classification, prediction, regression, and time series analysis. This thesis used the following research approaches: documentary-theoretical approach, comparative approach, and experimental approach. Several results were reached, the most important of which is that the decision tree technique is the best technique used to reach accurate results in banking data mining applications. RapidMiner also ranks first among these tools in evaluating performance and functionality standards, ease of use and technical support for its users. And by using the mentioned tools, especially RapidMiner, the risk ratio may decrease by high degrees, as RapidMiner reduces the time it takes to detect risk patterns in credit applications. This raises the percentage of caution among banks and improves financial performance and the relationship with customers, which benefit the society as a whole with the ease of providing loans and enabling banks to helping individuals and communities. |
|
Supervisor |
: |
Dr. Ibrahim Mahmoud Al-Omari |
|
Thesis Type |
: |
Doctorate Thesis |
|
Publishing Year |
: |
1444 AH
2023 AD |
|
Added Date |
: |
Sunday, July 2, 2023 |
|
Researchers
| هوازن عوض مطير | Hawazen, Mutair Awad | Researcher | Doctorate | |
|
Back To Researches Page
|