Aggregated information representation for technical analysis on stock market with csiszár divergence

  • Authors:
  • Ryszard Szupiluk;Piotr Wojewnik;Tomasz Ząbkowski

  • Affiliations:
  • Polska Telefonia Cyfrowa Ltd, Warsaw, Poland and Warsaw School of Economics, Warsaw, Poland;Polska Telefonia Cyfrowa Ltd, Warsaw, Poland and Warsaw School of Economics, Al. Niepodleglosci, Warsaw, Poland;Polska Telefonia Cyfrowa Ltd, Warsaw, Poland and Warsaw University of Life Sciences, Warsaw, Poland

  • Venue:
  • KES-AMSTA'10 Proceedings of the 4th KES international conference on Agent and multi-agent systems: technologies and applications, Part II
  • Year:
  • 2010

Quantified Score

Hi-index 0.00

Visualization

Abstract

The paper presents a new method for multidimensional representation of financial information in the context of technical analysis. Typically, technical analysis of given financial instrument does not take into account a broader view on the market. We want to analyze the information about the environment of the primary instrument. Hence, there is the problem of the results synthesis in a coherent and a transparent way. In this paper we propose aggregation of the information from different sources into a single aggregate graph which enables a technical analysis. The complete information is obtained with the p-norms approach. To assess the impact of particular information on the primary instrument we applied divergence measures such as Csiszár divergence and Beta divergence. Practical experiment on the stock exchange data confirmed the validity of proposed approach.