To Detect Irregular Trade Behaviors In Stock Market By Using Graph Based Ranking Methods

TL;DR

This paper introduces graph Laplacian based semi-supervised ranking methods to detect illegal and irregular trade behaviors in the stock market, demonstrating superior performance over other graph-based methods.

Contribution

The paper proposes a novel application of three graph Laplacian based semi-supervised ranking methods for detecting irregular stock market trades.

Findings

Un-normalized and symmetric normalized graph Laplacian methods outperform random walk Laplacian.

Semi-supervised ranking effectively detects illegal trade behaviors.

Experimental results validate the effectiveness of the proposed methods.

Abstract

To detect the irregular trade behaviors in the stock market is the important problem in machine learning field. These irregular trade behaviors are obviously illegal. To detect these irregular trade behaviors in the stock market, data scientists normally employ the supervised learning techniques. In this paper, we employ the three graph Laplacian based semi-supervised ranking methods to solve the irregular trade behavior detection problem. Experimental results show that that the un-normalized and symmetric normalized graph Laplacian based semi-supervised ranking methods outperform the random walk Laplacian based semi-supervised ranking method.