A link mining algorithm for earnings forecast and trading

Abstract

The objective of this paper is to present and discuss a link mining algorithm called CorpInterlock and its application to the financial domain. This algorithm selects the largest strongly connected component of a social network and ranks its vertices using several indicators of distance and centrality. These indicators are merged with other relevant indicators in order to forecast new variables using a boosting algorithm. We applied the algorithm CorpInterlock to integrate the metrics of an extended corporate interlock (social network of directors and financial analysts) with corporate fundamental variables and analysts' predictions (consensus). CorpInterlock used these metrics to forecast the trend of the cumulative abnormal return and earnings surprise of S&P 500 companies. The rationality behind this approach is that the corporate interlock has a direct effect on future earnings and returns because these variables affect directors and managers' compensation. The financial analysts engage in what the agency theory calls the "earnings game": Managers want to meet the financial forecasts of the analysts and analysts want to increase their compensation 123 420 G. Creamer, S. Stolfo or business of the company that they follow. Following the CorpInterlock algorithm, we calculated a group of well-known social network metrics and integrated with economic variables using Logitboost. We used the results of the CorpInterlock algorithm to evaluate several trading strategies. We observed an improvement of the Sharpe ratio (risk-adjustment return) when we used "long only" trading strategies with the extended corporate interlock instead of the basic corporate interlock before the regulation Fair Disclosure (FD) was adopted (1998)(1999)(2000)(2001). There was no major difference among the trading strategies after 2001. Additionally, the CorpInterlock algorithm implemented with Logitboost showed a significantly lower test error than when the CorpInterlock algorithm was implemented with logistic regression. We conclude that the CorpInterlock algorithm showed to be an effective forecasting algorithm and supported profitable trading strategies.

Analysis and Prediction of Fluctuations for Sector Price Indices with Cross-Correlation and Association Mining Based Networks: Tehran Stock Exchange Case

“…Betweenness and network constraint, both try to find bridges in the network topology. Lower network constraint and higher betweenness indicate bridging [42], [43]. This means that in the results section, the nodes with the lowest network constraint or with the highest betweenness or degree are presented as important nodes (sectors in our case).…”

“…Not all the nodes have the same importance and having link to some nodes are more important than others. Eigenvector centrality and page rank are increased if having links to other important nodes [42], [43].…”

A Comprehensive Survey of Link Mining and Anomalies Detection

“…Link mining is a newly developed research area, bringing together research insights from the fields of web mining, graph theory and machine learning. Link mining applications have been shown to be highly effective in addressing many important business issues such as telephone fraud detection (Fawcett & Provost, 1999), crime detection (Sparrow, 1991), money laundering (Kirkland et al, 1999), terrorism (Badia & Kantardzic, 2005;Skillicorn, 2004), financial applications (Creamer & Stolfo, 2009), social networks and health care problems (Provana et al, 2010;Wadhah et al, 2012). The trend in the building and use of link mining models for critical business, law enforcement and scientific decision support applications are expected to grow.…”

Privacy in Online Social Networks

“…On these networks, a number of node-related, link-related, and graph-related link mining tasks has been used. Meanwhile, on criminal [131], epidemiology [130], financial [124], and linked data networks [141] [125] [128], node-related techniques have been used. As for link-related approaches, they also examined the data management [133], digital libraries [137], and lexical networks [134].…”