The article highlights the reasons for changes in the price quotations of financial assets on stock exchanges. The article models the process of a situation when a trader fixes the period of holding his trading position. It defines periods of buying and selling and, taking into account that high-frequency stock trading on ultra-short intervals shows low profitability, introduces an important condition that allows a stock trader to freely open and close trading positions during the entire period of buying and selling with consideration of the proposed restrictions. The article offers modelling of the trader's strategy of carrying out trading actions aimed at maximisation of profit. Taking into account the liquidity constraints and quantitative limitations for trading orders, the article proposes to determine the optimal high-frequency trading strategy for buying and selling by a trader, which can be formulated as the task of minimising the cost of trading orders. Based on the number of available exchange trade orders and the values relative to the respective trade order at specific moments, determining the optimal high-frequency trading strategy for buying and selling a trader can be reduced to solving a simple cost minimisation problem under the given conditions of liquidity constraints for each trade order, completion of the trading portfolio without active positions before the end of the period and the total number of exchange buy and sell transactions. The key phases in building the structure on which the stock trading strategy itself is based are described. The need to determine what data will be entered into the algorithm of the artificial neural network based on the input data and to determine which algorithm will be used for a particular task is established. The structure of the software model of the system for intelligent forecasting of trading on stock exchanges is designed. The complex of the automated trading system includes the development of a graphical display of quotes and a tool for visual analysis. At the same time, information about proven trading strategies can be stored in a database that can be added and deleted by traders in the developed intelligent system for forecasting trading on stock exchanges.