| |
| Market making strategies have played an important role in the electronic stock market. However, the market making strategies without any forecasting power are not safe while trading. In this paper, we design an event-driven market making strategy and propose a trading signal generation framework based on a supervised learning approach. The framework incorporates the information within order book microstructure and market news articles to provide directional predictions, which further prevents market making strategies from profit loss led by market trending. Using half one year price tick data from Tokyo Stock Exchange and Shanghai Stock Exchange, and corresponding Thomson Reuters news of the same time period, simulation has been conducted on an industrial trading platform and a near-to-reality simulator. From the empirical results, we find that 1) strategies with signals perform better than strategies without any signal in terms of average daily Profit and Loss (PnL) and Sharpe Ratio (SR), and 2) correct predictions do help market making strategies readjust their quoting along with market trending, which avoids the strategies triggering stop loss procedure that further realizes the paper loss. |
|
| Keywords:Algorithmic Trading; Market Making Strategy; News Impact Analysis |
|
