Modeling Intraday Information In Financial Markets With The Scatter Search Metaheuristic

Intraday information about stocks or financial indexes is important for the definition of investors' strategies. In this paper two problems where the intraday information is used are studied: (i) modeling a bandwidth for the range of daily maximum and daily prices/values; (ii) modeling an upper and a lower bounds for the daily maximum and daily prices/values. A non-linear transformation of a modified AR(p) process is used, with the parameters computed by the scatter search metaheuristic. The approach is tested with historical data from NASDAQ, DAX, CAC40 and S&P financial series.