ANN timeseries prediction has been successfully implemented and tested on Nairobi securities exchange (NSE) stocks prediction by Barack (2014) and other stock exchanges (Safi & White 2017) worldwide. Many of the studies have focused on factors like training algorithm, network size and learning parameters bypassing selection of activation function. With the different type’s activation functions currently available for use in ANN, further studies need to be done to test if the activation functions or their combinations can improve performance of the ANN The study involved implementing of different networks containing varied activation functions and training and testing them with NSE data t
Download