e-space
Manchester Metropolitan University's Research Repository

The detection of fraud activities on the stock market through forward analysis methodology of financial discussion boards

Lee, Pei and Owda, M and Crockett, K (2018) The detection of fraud activities on the stock market through forward analysis methodology of financial discussion boards. In: Future of Information and Communication Conference (FICC) 2018, 05 April 2018 - 06 April 2018, Singapore.

[img]
Preview

Download (571kB) | Preview

Abstract

Financial discussion boards (FDBs) have been widely used for a variety of financial knowledge exchange activities through the posting of comments on the FDBs. Popular public FDBs are prone to be used as a medium to spread false financial information due to having a larger group of audiences. Although online forums, in general, are usually integrated with anti-spam tools such as Akismet, moderation of posted contents heavily relies on human moderators. Unfortunately, popular FDBs attract many comments per day which realistically prevents human moderators from continuously monitoring and moderating possibly fraudulent contents. Such manual moderation can be extremely time-consuming. Moreover, due to the absence of useful tools, no relevant authorities are actively monitoring and handling potential financial crimes on FDBs. This paper presents a novel forward analysis methodology implemented in an Information Extraction (IE) prototype system named FDBs Miner (FDBM). This methodology aims to detect potentially illegal comments on FDBs while integrating share prices in the detection process as this helps to categorise the potentially illegal comments into different risk levels for investigation priority. The IE prototype system will first extract the public comments and per minute share prices from FDBs for the selected listed companies on London Stock Exchange (LSE). In the forward analysis process, the comments are flagged using a predefined Pump and Dump financial crime related keyword template. By only flagging the comments against the keyword template yields an average of 9.82% potentially illegal comments. It is unrealistic and unaffordable for human moderators to read these comments on a daily basis in long run. Hence, by integrating the share prices’ hikes and falls to categorise the flagged comments based on risk levels, it saves time and allows relevant authorities to prioritise and investigate into the higher risk flagged comments as it can potentially indicate real Pump and Dump crimes on FDBs.

Impact and Reach

Statistics

Downloads
Activity Overview
2Downloads
58Hits

Additional statistics for this dataset are available via IRStats2.

Altmetric

Actions (login required)

Edit Item Edit Item