Due to their complex systems dynamics, financial markets are challenging to anticipate. Although several recent research have attempted to anticipate the financial markets using machine learning techniques, the results have not been adequate. To forecast changes in the financial market, we suggest a brand-new one-dimensional convolutional neural networks (CNN) model. Customized one-dimensional convolutional layers scan historical financial trading data over time while sharing parameters (kernels) with other forms of data, such as prices and volume. Instead of utilising conventional technical indicators, our model automatically extracts characteristics, which helps it avoid biases brought on by the choice of technical indicators and pre-defined coefficients in technical indicators. We carefully backtest our prediction model using historical trade data for six futures from January 2010 to October 2017 to assess its performance. The experiment's findings demonstrate that our CNN model extracts more broad and useful characteristics than conventional technical indicators and produces more stable and lucrative financial performance than prior machine learning techniques. final year project is based on IEEE Paper.this will be one of the best Final year engineering project for computer science. Components that we will provide are.
1.complete documentation support
2.complete working hardware/software implemented in students environment 3.classes will held accordingly.