Abstract
The field of data analytics has become a significant catalyst for change in government operations, presenting unique possibilities for enhancing governance efficiency. The availability of vast amounts of data accessible to individuals responsible for making decisions presents an opportunity for extracting valuable insights. However, effectively harnessing this potential requires the utilisation of advanced methodologies. Data analytics has the potential to greatly benefit procurement, which is a crucial aspect of government operations. By utilising data analytics, procurement can improve its efficiency, mitigate disputes, prevent instances of fraud and corruption, enhance transparency and accountability, and reduce both time and cost burdens. The significance of effective procurement management is underscored by Malaysia's budget allocation of RM388.1 billion for the year 2023. Insufficient monitoring of procurement procedures can give rise to fraudulent activities, corrupt practises, and suboptimal tenderer choices, thereby causing significant financial losses to government funds. A misdemeanor arrest of the government procurement cartel coalition in 2021, which involved a monopoly of 345 tenders in government ministries and agencies across the nation and a project value of RM3.8 billion is one illustration of the insufficient monitoring of the fraudulent cartel and coalition activities in government procurement process. In order to tackle these issues, this study introduces a novel framework that employs a machine learning model specifically developed to assist evaluation committees and tender board in detecting fraudulent company in the tenders and quotations. The framework demonstrates the capability to predict tenderers who possess a likelihood of engaging in fraudulent activities and forming cartel coalition with other tenderers. Comprehensive information pertaining to tenderers can be discerned, hence bolstering the evidentiary support for the presence of fraudulent alliances and cartels among tenderers. This framework additionally offers visual analytics that facilitates the awareness of committee members and tender boards regarding the potential danger of fraudulent activities by tenderers during the procurement process. The framework described in this study utilises historical and current datasets derived from Malaysia's eProcurement system that is known as ePerolehan that was exist since 1999. This framework effectively extracts patterns, identifies trends, and generates forecasts pertaining to fraudulent coalition and cartel activities among tenderers. To date, there is an absence of technologies available for the detection of fraudulent coalitions and cartels in the procurement process. By implementing this framework, it has the potential to mitigate financial losses and corrupt practises, hence fostering economic growth and enhancing transparency within a nation.
Metadata
Item Type: | Book Section |
---|---|
Creators: | Creators Email / ID Num. Mohd, Saifuddin saifuddin.mohd@gmail.com Ijab, Mohamad Taha taha@ukm.edu.my |
Contributors: | Contribution Name Email / ID Num. Patron Md Badarudin, Ismadi UNSPECIFIED Advisor Jasmis, Jamaluddin UNSPECIFIED Advisor Jono, Mohd Hajar Hasrol UNSPECIFIED Team Member Suhaimi, Nur Suhailayani UNSPECIFIED Team Member Mat Zain, Nurul Hidayah UNSPECIFIED Team Member Abdullah Sani, Anis Shobirin UNSPECIFIED Team Member Halim, Faiqah Hafidzah UNSPECIFIED Team Member Abd Kadir, Siti Aisyah UNSPECIFIED Team Member Jalil, Ummu Mardhiah UNSPECIFIED |
Subjects: | T Technology > T Technology (General) > Integer programming |
Divisions: | Universiti Teknologi MARA, Melaka > Jasin Campus > Faculty of Computer and Mathematical Sciences |
Event Title: | International Jasin Multimedia & Computer Science Invention and Innovation Exhibition (i-JaMCSIIX 2023) |
Event Dates: | 8th November 2023 |
Page Range: | pp. 106-109 |
Keywords: | Procurement; Cartel; Fraudulent; Coalition; Machine learning; Analytics |
Date: | 2023 |
URI: | https://ir.uitm.edu.my/id/eprint/94365 |