Prediction of Euro 50 Using Back Propagation Neural Network (BPNN) and Genetic Algorithm (GA)
Modeling time series is often associated with the process forecasts certain characteristics in the next period. One of the methods forecasts that developed nowadays is using artificial neural network or more popularly known as a neural network. Use neural network in forecasts time series can be a good solution, but the problem is network architecture and the training method in the right direction. One of the choices that might be using a genetic algorithm. A genetic algorithm is a search algorithm stochastic resonance based on how it works by the mechanisms of natural selection and genetic variation that aims to find a solution to a problem. This algorithm can be used as teaching methods in train models are sent back propagation neural network. The application genetic algorithm and neural network for divination time series aim to get the weight optimum. From the training and testing on the data index share price euro 50 obtained by the RMSE testing 27.8744 and 39.2852 RMSE training. The weight or parameters that produced by has reached an optimum level in second-generation 1000 with the best fitness and the average 0.027771 the fitness of 0.0027847.Model is good to be used to give a prediction that is quite accurate information that is shown by the close target with the output.
Keywords: Genetic Algorithm, Back Propagation Neural Network, Euro 50, Prediction, Neural Network.
Business activities and the economy, and the prediction to a more accurate next is needed. In the field of economy share price trading day-to-day, both in the form fluctuation gains as well as experienced and to share price that fluctuates allow the corporate investors in the advantages and disadvantages suffered modeling time series is often associated with the inaccurate forecasting certain characteristics in the next period. Divination is suspected or bets that a state in the future based on the past condition and now that is needed to determine when an incident will happen, so that appropriate action can be done
That were faced by the buyback inaccurate to data it is data that has changed with. This was in the case data financial and financial fluctuations have a very large and did not remain. In addition, the method conventional forecasts that are used in doing forecasts, the method inaccurate using Neural Network model (NN) can be used as an alternative in divination. NN are able to identify the pattern of a data input by using the method of learning to be trained to learn more about the pattern data the past and try to look for a function that connects the pattern data the past to the exodus was wanted at this time. Forecasts as a mean to resolve the problems economy very important especially in predicting these things that happened in the future so that the application in NN forecast economic data, of course, is very helpful in solving economic problems.
Use NN in forecasts time series can be a solution that good, but the problem is network architecture and the presidential election training method in the right direction. One of the choices that might is to use a Genetic algorithm (GA). GA is suitable to solve the problem combinatorial that require time computing for a long time. Scientists have two different perspectives about AI. The first believes that AI as part of that only a focus on the process to think. While the second believes that AI as knowledge that focuses on their way in demand. This point to two see AI wider because of an appearance must be preceded by a process to think. That is the most suitable AI Definition for the moment is acting rationally with the approach rational agent. This was based on a thought that computer can make a logical reasoning and can also do the action in a rational reasoning based on the result was. A major impediment to scientific progress in many fields is the inability to make sense of the huge amounts of data that have been collected via experiment or computer simulation. In the fields of statistics and machine learning there have been major efforts to develop automatic methods for finding significant and interesting patterns in complex data, and for forecasting the future from such data. In general, however, the success of such efforts has been limited, and the automatic analysis of complex data analysis and prediction can often be formulated as search problems.
Please download this full paper in RESEARHGATE