Key points are not available for this paper at this time.
Financial forecasting is one of the imperative fields of research, where investors invest money and get restless for the future changes of the stock values in the market. In the recent course of time forecasting stock price is one of the challenging tasks. To predict the stock price most Artificial Neural Network (ANN) based model are used in the historical data along with statistical measures, technical indicators etc. With the development of ANNs, investors are hoping the best prediction because networks have great capability of machine learning problems such as classification and prediction. ANNs particularly Back Propagation (BP) has overlooked the non-stationary and noise characteristics of stock market data, as the training of BP is intricate due to the noise data and the network fall into a natural solution such as always predict an usual output. Most optimization techniques have been used for training the weights of forecasting models. Since no single optimization technique is invariably superior to others. Recently various nature inspired optimization techniques have been introduced and successfully employed to many fields of Financial Engineering. This survey aims to study the mostly used Bio-inspired optimization techniques on Stock Market Prediction and makes a comparative analysis between them.
Das et al. (Sat,) studied this question.