• DocumentCode
    3310062
  • Title

    SEPT: a hybrid intelligent support system for the bank treasury dealing room

  • Author

    Gardin, Francesco ; Power, Richard ; Taylor, Hadley C. ; Baldassi, Gianluigi

  • Author_Institution
    Dept. of Comput. Sci., Milan Univ., Italy
  • fYear
    1991
  • fDate
    9-11 Oct 1991
  • Firstpage
    122
  • Lastpage
    127
  • Abstract
    The treasurers of Italian commercial banks manage liquidity mainly by short-term interbank operations in lira. After the introduction of a telematic domestic money market, such operations cannot be planned effectively without computer support. The planning of liquidity flows and the exploitation of arbitrage opportunities cannot be done by sheer calculations since future trends can be predicted only by wide knowledge and experience. On the other hand, the discovery of good but counter-intuitive solutions requires mathematical techniques rather than heuristic search. The authors have therefore developed a hybrid system, SEPT, which combines expert system rules and mathematical optimization. SEPT has been installed in several banks; some improvements and extensions are under consideration
  • Keywords
    bank data processing; electronic trading; expert systems; optimisation; Italian commercial banks; SEPT; arbitrage opportunities; bank treasury dealing room; computer support; counter-intuitive solutions; expert system rules; hybrid intelligent support system; liquidity; liquidity flows; mathematical optimization; mathematical techniques; short-term interbank operations; telematic domestic money market; Artificial intelligence; Computer science; Decision support systems; Economic indicators; Expert systems; Hybrid intelligent systems; Research and development; Telematics; Uncertainty; Wire;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Artificial Intelligence Applications on Wall Street, 1991. Proceedings., First International Conference on
  • Conference_Location
    New York, NY
  • Print_ISBN
    0-8186-2240-7
  • Type

    conf

  • DOI
    10.1109/AIAWS.1991.236562
  • Filename
    236562