Forecasting and classification of Indian stocks using different polynomial functional link artificial neural networks

Abstract

Forecasting stock price index is one of the major challenges in the trade market for investors. Time series data for prediction are difficult to manipulate, but can be focused as segments to discover interesting patterns. In this paper we use several functional link artificial neural networks to get such patterns for predicting stock indices. The novel architecture of functional link artificial neural network with working principle of different models are provided to achieve best forecasting and classification with increase in accuracy of prediction and decrease in training time. Various FLANN models with different polynomials are investigated using different Indian stock indices like IBM, BSE, Oracle, & RIL. The main absolute percentage error (MAPE), sum squared error (SSE) and the standard deviation error (SDE) have been considered to measure the performance of the different FLANN models. In this paper we have presented the result using Reliance Industries Limited (RIL) stock data between 22/12/1999 to 30/12/2011 on closed price of every trading day. Keywords-Artificial Neural Network (ANN); Functional Link ANN (FLANN); Power Functional Link ANN (PFLANN); Laguerre Functional Link ANN (LFLANN); Legendre Functional Link ANN (LeFLANN); Chebyshev Functional Link ANN (CFLANN); Absolute Percentage Error (MAPE); Sum of Squared Error (SSE); Standard Deviation of Error (SDE)I.978-1-4673-2272-0/12/$31.00

Polynomial Based Functional Link Artificial Recurrent Neural Network adaptive System for predicting Indian Stocks

“…A wide variety of FLANNs [18][19][20] This paper is organized in six sections. In Section 2, the architecture of the Polynomial recurrent FLANN model is proposed and various polynomial basis functions are outlined.…”

“…Differential Evolution (DE) [19] is a population-based stochastic function optimizer, which uses a rather greedy and less stochastic approach for problem solving in comparison to classical evolutionary algorithms, such as genetic algorithms, evolutionary programming, and PSO. DE combines simple arithmetical operators with the classical operators of recombination, mutation, and selection to evolve from a randomly generated starting population to a final solution.…”

Comparing Unsupervised Layers in Neural Networks for Financial Time Series Prediction

“…Therefore, a wide range of investigations is ongoing in the financial domain. Predicting financial time series has an effect on the trading decisions of many companies and organizations, which are searching for new technologies that will support them in becoming more profitable and competitive [1], [2], [3]. Financial time series are highly non-linear and complex [4], as many risk factors, affect prices and exchange rates [5].…”

Functional Expansions Based Multilayer Perceptron Neural Network for Classification Task

“…Second phase is to classify the unknown objects. The impact of classification task can be viewed in real life phenomena's such as stock exchange [1] From last few decades, a variety of models have been developed for data mining. Statistical and artificial neural network models are prominent models.…”