Designing Multi-sensory Models for Finding Patterns in Stock Market Data

  • Authors:
  • Keith V. Nesbitt

  • Affiliations:
  • -

  • Venue:
  • ICMI '00 Proceedings of the Third International Conference on Advances in Multimodal Interfaces
  • Year:
  • 2000

Quantified Score

Hi-index 0.00

Visualization

Abstract

The rapid increase in available information has lead to many attempts to automatically locate patterns in large, abstract, multiattributed information spaces. These techniques are often called 'Data Mining' and have met with varying degrees of success. An alternative approach to automatic pattern detection is to keep the user in the 'exploration loop'. A domain expert is often better able to search data for relationships. Furthermore, it is now possible to construct user interfaces that provide multi-sensory interactions. For example, interfaces can be designed which utilise 3D visual spaces and also provide auditory and haptic feedback. These multi-sensory interfaces may assist in the interpretation of abstract information spaces by providing models that map different attributes of data to different senses. While this approach has the potential to assist in exploring these large information spaces what is unclear is how to choose the best models to define mappings between the abstract information and the human sensory channels. This paper describes some simple guidelines based on real world analogies for designing these models. These principles are applied to the problem of finding new patterns in stock market data.