Fedorov A. Information technology for performing stock operations using the trading robots

The thesis deals with the problem of development and implementation of a new information technology for performing operations at the stock exchange. The main goal of the research is to enhance the effectiveness of stock trading operations by making use of a set of trading robots. Ananalysis of existing methods for forecasting financial processes and technologies of trading has been performed. The advantages and drawbacks of existing systems were revealed. The special development and implementation features of trading robots are also studied. A set of mathematical models for forecasting of a value and direction of stock price are developed using technical analysis indicators. The use of indicators gave a possibility to improve substantially the forecasts quality. The integrated forecasting models are also proposed that are based on a set of separate models. Ananalys is of nonstationary financial processes heteroscedasticity was performed, and several model structures were selected to describe conditional variance. It was shown that the best forecasting model turned out to be E-GARCH. It was used for short term forecasting of volatility with further use of the forecasts for trading decisions making.