The stock market prediction is a lucrativefield of interest withpromising profit and covered with landmines for the unprecedented. The mar-kets are complex, non-linear and chaotic in nature which poses huge difficultiesto predict the prices accurately. In this paper, a stock trading system utilizingfeed-forward deep neural network (DNN) to forecast index price of Singaporestock market using the FTSE Straits Time Index (STI) in t days ahead is pro-posed and tested through market simulations on historical daily prices. There are40 input nodes of DNN which are the past 10 days’opening, closing, minimumand maximum prices and consist of 3 hidden layers with 10 neurons per layer.The training algorithm used is stochastic gradient descent with back-propagationand is accelerated with multi-core processing. A trading system is proposedwhich utilizes the DNN forecasting results with defined entry and exit rules toenter a trade. DNN performance is evaluated using RMSE and MAPE. Theoverall trading system shows promising results with a profit factor of 18.67,70.83% profitable trades and Sharpe ratio of 5.34 based on market simulation ontest data.