A hybrid FLANN and adaptive differential evolution model for forecasting of stock market indices

Abstract

This paper presents a computationally efficient functional link artificial neural network (CEFLANN) based adaptive model for financial time series prediction of leading Indian stock market indices. Financial time-series data are usually nonstationary and volatile in nature. The proposed adaptive CEFLANN based model employs the least mean square (LMS) algorithm with a new cost function to train the weights of the networks. The mean absolute percentage error (MAPE) with respect to actual stock prices is selected as the performance index to estimate the quality of prediction. The CEFLANN model inputs are chosen from the past stock prices of different market sectors along with technical indicators to determine best stock trend prediction one day ahead in time. Further to improve the performance of the CEFLANN model, weights are optimized using an adaptive differential evolution (DE) algorithm and its overall prediction performance is compared with the improved LMS algorithm showing the effectiveness of the DE in producing more accurate forecast. We have selected different combinations of important technical indicators to have a strong control on changes in stock indices.

A review of artificial intelligence quality in forecasting asset prices

“…The stocks of Apple, IBM, and Microsoft were the most commonly studied due to previous work being readily accessible as a benchmark. The best results for Apple's stock price were obtained by Araújo (2010), Asadi (2019), and Tseng et al (2012), while Borovkova and Tsiamas (2019), Hadavandi et al (2010b), Lahmiri (2018), and Rout et al (2014) had the best performance for IBM's stock price data, and González‐Mancha et al (2017), Kazem et al (2013), and Sheelapriya and Murugesan (2017) for MSFT.…”

“…Conversely, excluding the RMSE of Jayanth Balaji et al (2018), a pure model, the average RMSE drops to less than 1%. The top‐five hybrids (Araújo, 2010; Khairalla & Al‐Jallad, 2017; Li et al, 2018; Rath et al, 2019; Rout et al, 2014) perform better than the nonhybrid top‐five (Dunis et al, 2012; Karathanasopoulos & Osman, 2019; Karathanasopoulos, 2017; Lakshmi & Visalakshmi, 2016; Xu, et al, 2011) with an estimated 0.65% versus 0.87%, respectively.…”

“…All numbers are percentages. (Araújo, 2010;Khairalla & Al-Jallad, 2017;Li et al, 2018;Rath et al, 2019;Rout et al, 2014) perform better than the nonhybrid top-five (Dunis et al, 2012;Karathanasopoulos & Osman, 2019;Karathanasopoulos, 2017;Lakshmi & Visalakshmi, 2016;Xu, et al, 2011) with an estimated 0.65% versus 0.87%, respectively. Data normalization proves to be effective in improving predictive power.…”

Effective forecasting of stock market price by using extreme learning machine optimized by PSO-based group oriented crow search algorithm

“…Hegazy et al [ 33 ] have applied particle swarm optimization (PSO) optimized ANN and Least Square Support Vector Machine (LS-SVM), respectively, to predict SM. Computationally Efficient Functional Link Artificial Neural Network (CEFLANN) optimized by Differential Evolution (DE) algorithm is implemented with better performance to predict SM [ 34 ]. The accuracy of stock index forecasting is enhanced by Artificial Fish Swarm Algorithm (AFSA)-based Radial Basis Functional Neural Network (RBFNN) and Grey Wolf optimization-based Elman neural network proposed by Shen et al [ 35 ] and Chander [ 36 ] respectively.…”