Ritanjali Majhi

Development and performance evaluation of FLANN based model for forecasting of stock markets

A trigonometric functional link artificial neural network (FLANN) model for short (one day) as well as long term (one month, two months) prediction of stock price of leading stock market indices: DJIA and S&P 500 is developed in this paper. The proposed FLANN model employs the least mean square (LMS) as well as the recursive least square (RLS) algorithms in different experiments to train the weights of the model. The historical index data transformed into various technical indicators as well as macro economic data as fundamental factors are considered as inputs to the proposed models. The mean absolute percentage error (MAPE) with respect to actual stock prices is selected as the performance index to gauge the quality of prediction of the models. Extensive simulation and test results show that the application of FLANN to the stock market prediction problem gives out results which are comparable to other neural network models. In addition the proposed models are structurally simple and requires less computation during training and testing as the model contains only one neuron and one layer. Between the two models proposed the FLANN-RLS requires substantially less experiments to train compared to the LMS based model. This feature makes the RLS-based FLANN model more suitable for online prediction.

Efficient prediction of stock market indices using adaptive bacterial foraging optimization (ABFO) and BFO based techniques

The present paper introduces the use of BFO and ABFO techniques to develop an efficient forecasting model for prediction of various stock indices. The structure used in these forecasting models is a simple linear combiner. The connecting weights of the adaptive linear combiner based models are optimized using ABFO and BFO by minimizing its mean square error (MSE). The short and long term prediction performance of these models are evaluated with test data and the results obtained are compared with those obtained from the genetic algorithm (GA) and particle swarm optimization (PSO) based models. It is in general observed that the new models are computationally more efficient, prediction wise more accurate and show faster convergence compared to other evolutionary computing models such as GA and PSO based models.

Efficient prediction of exchange rates with low complexity artificial neural network models

In recent years forecasting of financial data such as interest rate, exchange rate, stock market and bankruptcy has been observed to be a potential field of research due to its importance in financial and managerial decision making. Survey of existing literature reveals that there is a need to develop efficient forecasting models involving less computational load and fast forecasting capability. The present paper aims to fulfill this objective by developing two novel ANN models involving nonlinear inputs and simple ANN structure with one or two neurons. These are: functional link artificial neural network (FLANN) and cascaded functional link artificial neural network (CFLANN). These have been employed to predict currency exchange rate between US

Stock market prediction of S&P 500 and DJIA using Bacterial Foraging Optimization Technique

to British Pound, Indian Rupees and Japanese Yen. The performance of the proposed models have been evaluated through simulation and have been compared with those obtained from standard LMS based forecasting model. It is observed that the CFLANN model performs the best followed by the FLANN and the LMS models.

A comparative performance assessment of a set of multiobjective algorithms for constrained portfolio assets selection

The present paper introduces the bacterial foraging optimization (BFO) technique to develop an efficient forecasting model for prediction of various stock indices. The connecting weights of the adaptive linear combiner based model are optimized by the BFO so that its mean square error(MSE) is minimized. The short and long term prediction performance of the model is evaluated with test data and the results obtained are compared with those obtained from the multilayer perceptron (MLP) based model. It is in general observed that the proposed model is computationally more efficient, prediction wise more accurate and takes less training time compared to the standard MLP based model.

Prediction of S&P 500 and DJIA stock indices using Particle Swarm Optimization technique

Abstract This paper addresses a realistic portfolio assets selection problem as a multiobjective optimization one, considering the budget, floor, ceiling and cardinality as constraints. A novel multiobjective optimization algorithm, namely the non-dominated sorting multiobjective particle swarm optimization (NS-MOPSO), has been proposed and employed efficiently to solve this important problem. The performance of the proposed algorithm is compared with four multiobjective evolution algorithms (MOEAs), based on non-dominated sorting, and one MOEA algorithm based on decomposition (MOEA/D). The performance results obtained from the study are also compared with those of single objective evolutionary algorithms, such as the genetic algorithm (GA), tabu search (TS), simulated annealing (SA) and particle swarm optimization (PSO). The comparisons of the performance include three error measures, four performance metrics, the Pareto front and computational time. A nonparametric statistical analysis, using the Sign test and Wilcoxon signed rank test, is also performed, to demonstrate the superiority of the NS-MOPSO algorithm. On examining the performance metrics, it is observed that the proposed NS-MOPSO approach is capable of identifying good Pareto solutions, maintaining adequate diversity. The proposed algorithm is also applied to different cardinality constraint conditions, for six different market indices, such as the Hang-Seng in Hong Kong, DAX 100 in Germany, FTSE 100 in UK, S&P 100 in USA, Nikkei 225 in Japan, and BSE-500 in India.

On the development of improved adaptive models for efficient prediction of stock indices using clonal-PSO (CPSO) and PSO techniques

The present paper introduces the particle swarm optimization (PSO) technique to develop an efficient forecasting model for prediction of various stock indices. The connecting weights of the adaptive linear combiner based model are optimized by the PSO so that its mean square error(MSE) is minimized. The short and long term prediction performance of the model is evaluated with test data and the results obtained are compared with those obtained from the multilayer perceptron (MLP) based model. It is in general observed that the proposed model is computationally more efficient, prediction wise more accurate and takes less training time compared to the standard MLP based model.

Efficient Prediction of Foreign Exchange Rate using Nonlinear Single Layer Artificial Neural Model

The present paper introduces a new clonal particle swarm optimisation (CPSO) and PSO techniques to develop efficient adaptive forecasting models for short and long-term prediction of S&P 500 and DJIA stock indices. The basic structure of the models is an adaptive linear combiner whose weights are iteratively updated by PSO and CPSO-based learning rules. The technical indicators are computed from past stock indices and are used as input to the models. Using simulation study the prediction performances in terms of the convergence rate, the minimum mean square error (MSE), training time and the mean average percentage error (MAPE) of CPSO, PSO and GA-based models are obtained for all ranges of prediction. Comparison of these results demonstrates that the proposed CPSO and PSO-based models yield superior performance compared to the GA one. However the CPSO model provides the best performance compared to other two.

Constrained portfolio asset selection using multiobjective bacteria foraging optimization

The present paper proposes an efficient adaptive forecasting model for one month ahead prediction of foreign exchange using single layer artificial neural network. Using real time series of rupees, pounds and yens the dollar exchange rate is predicated in each case. It is demonstrated that the proposed nonlinear model yields excellent prediction in each case

Portfolio management assessment by four multiobjective optimization algorithm

Portfolio asset selection (PAS) is a challenging and interesting multiobjective task in the field of computational finance, and is receiving the increasing attention of researchers, fund management companies and individual investors in the last few decades. Selecting a subset of assets and corresponding optimal weights from a set of available assets, is a key issue in the PAS problem. A Markowitz model is generally used to solve this optimization problem, where the total profit is maximized, while the total risk is to be minimized. However, this model does not consider the practical constraints, such as the minimum buy in threshold, maximum limit, cardinality etc. The Practical constraints are incorporated in this study to meet a real world financial scenario. In the proposed work, the PAS problem is formulated in a multiobjective framework, and solved using the multiobjective bacteria foraging optimization (MOBFO) algorithm. The performance of the proposed approach is compared with a set of competitive multiobjective evolutionary algorithms using six performance metrics, the Pareto front and computational time. On examining the performance metrics, it is concluded that the proposed MOBFO algorithm is capable of identifying a good Pareto solution, maintaining adequate diversity. The proposed algorithm is also successfully applied to different cardinality constraint conditions, for six different market indices.