Amer Alzaidi and Dimitar Kazakov
Equation Discovery, Islamic Banking, Financial Forecasting
This paper describes an equation discovery approach based on machine learning using LAGRAMGE as an equation discovery tool, using two sources of input, a dataset and model presented in context-free grammar. The approach is searching a large range of potential equations using a specific model. The parameters of the equation are fitted to find the best equations. We illustrate experiments with commodity prices from the London Metal Exchange for the time period of January-October 2009. The outputs of the experiments are a large number of equations; some of the equations display that the predicted prices are following the market trends in perfect patterns.
Important Links:
Go Back
