A conceptual framework for forecasting noisy multivariate financial time series data

Abstract

Financial prediction is the manner in which businesses anticipate future projections, by making risky decisions based on the anticipated historical stock market. An example of financial time-series forecasting is stock market prices, nevertheless the process of forecasting is met with numerous difficulties which are obtained by the continuous fluctuations in the daily trading market. Financial data are characterized by nonlinearity, noise, chaotic in nature and volatile thus making the process of prediction cumbersome. The biggest impediment is due to the colossal nature of the capacity of transmitted data from the trading market. Hence, the main aim of forecasters is to develop an approach of forecasting that focuses on increasing profit by being able to predict future stock prices based on current stock data. However the intricacy of stock market prices, there is the need of intelligent forecasting techniques that will reduce decision making risks and predicting future stock market trends