Stock price forecasting is a classic problem facing analysts. Forecasting models have been developed for predicting individual stocks and stock indices around the world and in numerous industries. According to a literature review, these models have yet to be applied to the restaurant industry. Strategies for forecasting typically include fundamental and technical variables. In this research, fundamental and technical inputs were combined into an artificial neural network (ANN) stock prediction model for the restaurant industry. Models were designed to forecast 1 week, 4 weeks, and 13 weeks into the future. The model performed better than the benchmark methods, which included, an analyst prediction, multiple linear regression, trading, and Buy and Hold trading strategies. The prediction accuracy of the ANN methodology presented reached accuracy performance measures as high as 60%. The model also shown resiliency over the housing crisis in 2008.
Spiking neural network training using evolutionary algorithms
