A comparative analysis of machine learning approaches in sukuk price estimation across global regions
Sukuk, also known as Islamic bonds, constitute a significant aspect of Islamic finance, offering Shariah-compliant investment opportunities. Motivated by the increasing prominence of Sukuk in global financial markets and their potential for economic development, this study aims to investigate the...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Social Science Research Network (SSRN)
2024
|
| Subjects: | |
| Online Access: | http://irep.iium.edu.my/116838/1/2024%20SSRN%20Islam%20A%20Comparative.pdf http://irep.iium.edu.my/116838/ https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4945306 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Sukuk, also known as Islamic bonds, constitute a significant aspect of Islamic finance, offering
Shariah-compliant investment opportunities. Motivated by the increasing prominence of Sukuk in
global financial markets and their potential for economic development, this study aims to
investigate the effectiveness of machine learning neural networks in Sukuk price estimation. The
objective is to evaluate the accuracy and efficiency of various machine learning techniques across
diverse global regions with significant interest in Sukuk investment, as determined by the size of
the Muslim population. The methodology for literature selection involves a systematic search of
academic databases and scholarly repositories, focusing on recent publications within the last five
years. Search terms include keywords related to Sukuk and machine learning. Selected papers are
screened based on titles and abstracts to ensure relevance to the research topic, prioritizing those
that explicitly discuss both Sukuk and machine learning. In addition, articles are evaluated for
outcome-based research, particularly those that offer conclusions about the precision and
effectiveness of Sukuk pricing or machine learning-based forecasting. The findings suggest that
artificial neural networks perform better than traditional statistical methods in Sukuk price
estimation. However, restrictions including short dataset sizes, the omission of Sukuk backed by
assets, and overly basic rating categories indicate areas that warrant additional investigation. Future
studies could explore comparative analyses of different machine learning algorithms, refine models
for dynamic market conditions, and incorporate real-time data integration to enhance Sukuk price
forecasting accuracy. Considering these drawbacks, the results highlight how machine learning
might enhance the effectiveness and precision of Sukuk pricing. |
|---|