Parallel prediction of stock volatility

The financial industry is an industry that requires multidisciplinary expertise. To be a good financial engineer, one should possess skills in math, finance, economics, and coding. Volatility is a measurement of the risk of financial products. A stock will hit new highs and lows over time and if these highs and lows fluctuate wildly, then it is considered a high volatile stock. Such a stock is considered riskier than a stock whose volatility is low. High tech stocks usually have high volatility. Although these stocks are riskier, the returns that they generate for investors can be quite high. Of course, with a riskier stock also comes the chance of losing money and yielding negative returns. In this project, we will use historic stock data to help us forecast volatility. The financial industry usually uses S&P 500 as the indictor of the market. Therefore, S&P 500 would be a benchmark to compute the risk. We will use artificial neural networks as a tool to predict volatilities for a period of time frame that will be set when we configure this neural network. There have been reports that neural networks with different numbers of layers and different numbers of hidden nodes may generate varying results. As a matter of fact, we may be able to find the best configuration of a neural network to compute volatilities. We will implement this system using the parallel approach. The system can be used as a tool for investors to allocating and hedging assets.