ADMIRAL: A Data Mining Based Financial Trading System

Author

Rachlin, Gil ; Last, Mark ; Alberg, Dima ; Kandel, Abraham

Author_Institution

Dept. of Inf. Syst. Eng., Ben-Gurion Univ. of the Negev

fYear

2007

fDate

March 1 2007-April 5 2007

Firstpage

720

Lastpage

725

Abstract

This paper presents a novel framework for predicting stock trends and making financial trading decisions based on a combination of data and text mining techniques. The prediction models of the proposed system are based on the textual content of time-stamped Web documents in addition to traditional numerical time series data, which is also available from the Web. The financial trading system based on the model predictions (ADMIRAL) is using three different trading strategies. In this paper, the ADMIRAL system is simulated and evaluated on real-world series of news stories and stocks data using the C4.5 decision tree induction algorithm. The main performance measures are the predictive accuracy of the induced models and, more importantly, the profitability of each trading strategy using these predictions

Keywords

Internet; data mining; decision trees; financial data processing; stock markets; text analysis; ADMIRAL trading system; data mining; decision tree induction; financial trading system; making financial trading decisions; model predictions; numerical time series data; stock trend prediction; text mining; time-stamped Web documents; Data engineering; Data mining; Economic forecasting; Predictive models; Relational databases; Spatial databases; Stock markets; Text mining; Time series analysis; Transaction databases;

fLanguage

English

Publisher

ieee

Conference_Titel

Computational Intelligence and Data Mining, 2007. CIDM 2007. IEEE Symposium on

Conference_Location

Honolulu, HI

Print_ISBN

1-4244-0705-2

Type

conf

DOI

10.1109/CIDM.2007.368947

Filename

4221371