Please use this identifier to cite or link to this item: https://dl.ucsc.cmb.ac.lk/jspui/handle/123456789/3163
Title: Identifying Trading Manipulators
Authors: Withanage, A.R.P.
Issue Date: 29-Jun-2015
Abstract: Applying Fuzzy Logic to Identifying Trading Manipulators The main objective of the study is to provide a system that develops to identify the relationships between the entities involved in the securities markets by analyzing historical trade data. The stock markets are very sophisticated complex systems with high value market. Every second, millisecond, thousands of transactions occur in the stock finance made huge turnover. Stock markets dramatic movements and booms and unexpected falls, make all market surveillance tools based on traditional rules useless, and therefore does not provide the ability to identify the relationship between users of the monitoring system based on historical data. Due to the lack of tools to identify and vulnerabilities of these tools, financial fraud or malpractice may occur. For instance, in some countries, high-volume of the market may owned by a few individuals because of it. This research attempts to address this complexity in detecting abnormal trading behavior and its relationship with the subtractive clustering method of identification based fuzzy system. This study uses Mamdani Fuzzy Inference Modeling System to classify relations. The model examined in this study, from historical market data, some of the rules governing the market, and shows that the rules apply to a particular action can be generalized independent of the market, and can be measured and applies other regardless of time or specific industrial field to identify or recognize business models. The results of experimental tests of this study shows that the model can correctly identify the pattern of trade between the market entities with a threshold that indicates the strength of the interest in the market transactions.
URI: http://hdl.handle.net/123456789/3163
Appears in Collections:Master of Computer Science - 2015

Files in This Item:
File Description SizeFormat 
124406998.pdf.pdf
  Restricted Access
1.25 MBAdobe PDFView/Open Request a copy


Items in UCSC Digital Library are protected by copyright, with all rights reserved, unless otherwise indicated.