نشانه گذاری تحلیل نزدیک به « مرکز نظارت بازار اوراق قرضه تایلند» با استفاده از قوانین اتحادیه ای
|کد مقاله||سال انتشار||مقاله انگلیسی||ترجمه فارسی||تعداد کلمات|
|15214||2009||5 صفحه PDF||سفارش دهید||محاسبه نشده|
Publisher : Elsevier - Science Direct (الزویر - ساینس دایرکت)
Journal : Expert Systems with Applications, Volume 36, Issue 4, May 2009, Pages 8523–8527
This study investigates the opportunity of employing data mining techniques as a supplement to traditional techniques, such as economic modeling, to detect misconduct in the Thai Bond Market. In the study, association rules are used to detect “Mark the Close” conduct in the Thai Bond Market Association (ThaiBMA) surveillance system. The experiment was conducted on 54,334 trading transactions reported to the ThaiBMA in the year 2005. The result shows that association rules can be effectively used to provide a short list of traders who are likely to behave in such a way.
The Thai Bond Market has been established and growing since November 1994. As of 2006, the size of the Thai Bond Market was 4085.26 THB billion which was 52.29% and 80.44% of the Thai GDP and stock exchange market capital, respectively. The development of the Bond Market in Thailand has been one of the important items on the agenda for policymakers since the 1997 financial crisis. Recently established by the Security Exchange Commission of Thailand in September 2005, the Thai Bond Market Association (ThaiBMA) is a self-regulatory organization that is responsible for overseeing and monitoring the conduct of its members in order to ensure fairness and efficiency in debt securities trading. Its main role is to provide the fair and efficient operation of the Bond Market and to be an information centre for the Thai Bond Market. It also supports Bond Market development and sets the market conventions and standards for bond trading in Thailand. As part of being a self-regulatory organization, the ThaiBMA is responsible for performing market monitoring and surveillance to ensure that all trading activities comply with relevant laws and regulations, and acting as the front line in detecting any unfair trading practices. In order to perform this function efficiently, the ThaiBMA is implementing an automated surveillance system to help signal unusual trading in daily trade transactions so that the agency can conduct investigations which, in some cases, may lead to further reports and enforcement. The surveillance workflow is shown in Fig. 1. Full-size image (25 K) Fig. 1. Surveillance workflow of the ThaiBMA. Figure options As suggested in Fig. 1, trading transactions are monitored and analyzed in real time. If a trading transaction is “unusual” and warrants further investigation, it will be examined to see whether there has been a breach in the code of conduct. If so, the agency shall report the breach and notify the regulator to enforce the regulation. The other elements of the surveillance system include the timely disclosure of information as well as education and procedure reviews. This study focuses on employing data mining techniques in trading analysis which is shown as a dotted rectangle in Fig. 1.
نتیجه گیری انگلیسی
The study shows that association rules can be employed to detect Mark the Close conduct in the ThaiBMA surveillance system to supplement the traditional approach especially in behavioural aspects. However, in order to implement association rules in the surveillance system, the level of support has to be adjusted as appropriate. By setting a low support level, the technique tends to list a number of rules as a result because more rules will be qualified to be considered by the algorithm. On the other hand, by setting a high level of support, a small number of rules will be qualified to be considered by the algorithm and it will give fewer rules as a result.