Description:
This paper presents a computational approach for predicting the Australian stock market index AORD using multi-layer feed-forward neural networks front the time series data of AORD and various interrelated markets. This effort aims to discover an effective neural network, or a set of adaptive neural networks for this prediction purpose, which can exploit or model various dynamical swings and inter-market influences discovered from professional technical analysis and quantitative analysis. Within a limited range defined by our empirical knowledge, three aspects of effectiveness on data selection are considered: effective inputs from the target market (AORD) itself, a sufficient set of interrelated markets,. and effective inputs from the interrelated markets. Two traditional dimensions of the neural network architecture are also considered: the optimal number of hidden layers, and the optimal number of hidden neurons for each hidden layer. Three important results were obtained: A 6-day cycle was discovered in the Australian stock market during the studied period; the time signature used as additional inputs provides useful information; and a basic neural network using six daily returns of AORD and one daily, returns of SP500 plus the day of the week as inputs exhibits up to 80% directional prediction correctness.
Description:
This paper presents a computational approach for predicting the Australian stock market index AORD using multi-layer feed-forward neural networks front the time series data of AORD and various interrelated markets. This effort aims to discover an effective neural network, or a set of adaptive neural networks for this prediction purpose, which can exploit or model various dynamical swings and inter-market influences discovered from professional technical analysis and quantitative analysis. Within a limited range defined by our empirical knowledge, three aspects of effectiveness on data selection are considered: effective inputs from the target market (AORD) itself, a sufficient set of interrelated markets,. and effective inputs from the interrelated markets. Two traditional dimensions of the neural network architecture are also considered: the optimal number of hidden layers, and the optimal number of hidden neurons for each hidden layer. Three important results were obtained: A 6-day cycle was discovered in the Australian stock market during the studied period; the time signature used as additional inputs provides useful information; and a basic neural network using six daily returns of AORD and one daily, returns of SP500 plus the day of the week as inputs exhibits up to 80% directional prediction correctness.
Description:
This study predicts whether it is best to buy, hold or sell shares (trading signals) of the All Share Price Index (ASPI) of the Colombo Stock Exchange, using a modified neural network (NN) algorithm. Most commonly used classification techniques are not successful in predicting trading signals when the distribution of the actual trading signals, among these three classes, is imbalanced. The structure of this modified neural network is same as that of feedforward neural networks. This algorithm minimises a modified Ordinary Least Squares (OLS) error function. An adjustment relating to the contribution from the historical data used for training the networks, and penalisation of incorrectly classified trading signals were accounted for, when modifying the OLS function. A global optimization algorithm was employed to train these networks. Results obtained were satisfactory.
Description:
This paper presents a computational approach for predicting the Australian stock market index - AORD using multi-layer feed-forward neural networks from the time series data of AORD and various interrelated markets. This effort aims to discover an optimal neural network or a set of adaptive neural networks for this prediction purpose, which can exploit or model various dynamical swings and intermarket influences discovered from professional technical analysis and quantitative analysis. Four dimensions for optimality on data selection are considered: the optimal inputs from the target market (AORD) itself, the optimal set of interrelated markets, the optimal inputs from the optimal interrelated markets, and the optimal outputs. Two traditional dimensions of the neural network architecture are also considered: the optimal number of hidden layers, and the optimal number of hidden neurons for each hidden layer. Three important results were obtained: A 6-day cycle was discovered in the Australian stock market; the time signature used as additional inputs provides useful information; and a minimal neural network using 6 daily returns of AORD and 1 daily returns of SP500 plus the day of the week as inputs exhibits up to 80% directional prediction correctness.
Description:
The aim of this paper is to present modified neural network algorithms to predict whether it is best to buy, hold, or sell shares (trading signals) of stock market indices. Most commonly used classification techniques are not successful in predicting trading signals when the distribution of the actual trading signals, among these three classes, is imbalanced. The modified network algorithms are based on the structure of feed forward neural networks and a modified Ordinary Least Squares (OLSs) error function. An adjustment relating to the contribution from the historical data used for training the networks and penalisation of incorrectly classified trading signals were accounted for, when modifying the OLS function. A global optimization algorithm was employed to train these networks. These algorithms were employed to predict the trading signals of the Australian All Ordinary Index. The algorithms with the modified error functions introduced by this study produced better predictions.
Description:
This study investigates how intermarket influences can be used to help the prediction of the direction (up or down) of the next day's close price of the Australian All Ordinary Index (AORD). First, intermarket influences from the potential influential markets on the AORD are quantified by assigning weights for all influential markets. The weights were defined as a solution to an optimization problem which aims to maximise rank correlation between the current day's relative return of the AORD and the weighted sum of lagged relative returns of the potential influential markets. Then, the next day's relative return of the AORD is predicted by applying the neural networks as a classifier. Two different scenarios were compared: 1) using the current day's relative returns of different sets of influential markets as separate inputs; and, 2) using only the weighted sum of these relative returns as a "combined market". The results revealed that the second approach provides better predictions in all cases. This shows the effectiveness of the proposed approach for quantifying intermarket influences and the potential of using the "weighted combined markets" for the prediction
Description:
This research investigated the feasibility and capability of neural network-based approaches for predicting the direction of the Australian Stock market index (the target market). It includes several aspects: univariate feature selection from the historical time series of the target market, inter-market analysis for finding the most relevant influential markets, investigations of the effect of time cycles on the target market and the discovery of the optimal neural network architectures. Previous research on US stock markets and other international markets have shown that the neural network approach is one of most powerful techniques for predicting stock market behaviour. Neural networks are capable of capturing the non-linear stochastic and chaotic patterns in the stock market time series data. This study discovered that the relative return series of the Open, High, Low and Close prices of the target market, show 6-day cycles during the studied period of about 14 years. Multi-layer feedforward neural networks trained with a backpropagation algorithm were used for the experiments. Two major testing methods: testing with randomly selected test data and forward testing, were examined and compared. The best neural network developed in this study has achieved 87%, 81% 83% and 81% accuracy respectively in predicting the next-day direction of the relative return of the Open, High, Low and Close prices of the target market. The architecture of this network consists of 33 input features, one hidden layer with 3 neurons and 4 output neurons. The best input features set includes the relative returns from 1 to 6 days in the past of the Open, High, Low and Close prices of the target market, the day of the week, and the previous day’s relative return of the Close prices of the US S&P 500 Index, US Dow Jones Industrial Average Index, US Gold/Silver Index, and the US Oil Index.
Description:
This research investigated the feasibility and capability of neural network-based approaches for predicting the direction of the Australian Stock market index (the target market). It includes several aspects: univariate feature selection from the historical time series of the target market, inter-market analysis for finding the most relevant influential markets, investigations of the effect of time cycles on the target market and the discovery of the optimal neural network architectures. Previous research on US stock markets and other international markets have shown that the neural network approach is one of most powerful techniques for predicting stock market behaviour. Neural networks are capable of capturing the non-linear stochastic and chaotic patterns in the stock market time series data. This study discovered that the relative return series of the Open, High, Low and Close prices of the target market, show 6-day cycles during the studied period of about 14 years. Multi-layer feedforward neural networks trained with a backpropagation algorithm were used for the experiments. Two major testing methods: testing with randomly selected test data and forward testing, were examined and compared. The best neural network developed in this study has achieved 87%, 81% 83% and 81% accuracy respectively in predicting the next-day direction of the relative return of the Open, High, Low and Close prices of the target market. The architecture of this network consists of 33 input features, one hidden layer with 3 neurons and 4 output neurons. The best input features set includes the relative returns from 1 to 6 days in the past of the Open, High, Low and Close prices of the target market, the day of the week, and the previous day’s relative return of the Close prices of the US S&P 500 Index, US Dow Jones Industrial Average Index, US Gold/Silver Index, and the US Oil Index.
Description:
This research investigated the feasibility and capability of neural network-based approaches for predicting the direction of the Australian Stock market index (the target market). It includes several aspects: univariate feature selection from the historical time series of the target market, inter-market analysis for finding the most relevant influential markets, investigations of the effect of time cycles on the target market and the discovery of the optimal neural network architectures. Previous research on US stock markets and other international markets have shown that the neural network approach is one of most powerful techniques for predicting stock market behaviour. Neural networks are capable of capturing the non-linear stochastic and chaotic patterns in the stock market time series data. This study discovered that the relative return series of the Open, High, Low and Close prices of the target market, show 6-day cycles during the studied period of about 14 years. Multi-layer feedforward neural networks trained with a backpropagation algorithm were used for the experiments. Two major testing methods: testing with randomly selected test data and forward testing, were examined and compared. The best neural network developed in this study has achieved 87%, 81% 83% and 81% accuracy respectively in predicting the next-day direction of the relative return of the Open, High, Low and Close prices of the target market. The architecture of this network consists of 33 input features, one hidden layer with 3 neurons and 4 output neurons. The best input features set includes the relative returns from 1 to 6 days in the past of the Open, High, Low and Close prices of the target market, the day of the week, and the previous day’s relative return of the Close prices of the US S&P 500 Index, US Dow Jones Industrial Average Index, US Gold/Silver Index, and the US Oil Index.
Description:
Master of Information Technology by Research
Description:
This research investigated the feasibility and capability of neural network-based approaches for predicting the direction of the Australian Stock market index (the target market). It includes several aspects: univariate feature selection from the historical time series of the target market, inter-market analysis for finding the most relevant influential markets, investigations of the effect of time cycles on the target market and the discovery of the optimal neural network architectures. Previous research on US stock markets and other international markets have shown that the neural network approach is one of most powerful techniques for predicting stock market behaviour. Neural networks are capable of capturing the non-linear stochastic and chaotic patterns in the stock market time series data. This study discovered that the relative return series of the Open, High, Low and Close prices of the target market, show 6-day cycles during the studied period of about 14 years. Multi-layer feedforward neural networks trained with a backpropagation algorithm were used for the experiments. Two major testing methods: testing with randomly selected test data and forward testing, were examined and compared. The best neural network developed in this study has achieved 87%, 81% 83% and 81% accuracy respectively in predicting the next-day direction of the relative return of the Open, High, Low and Close prices of the target market. The architecture of this network consists of 33 input features, one hidden layer with 3 neurons and 4 output neurons. The best input features set includes the relative returns from 1 to 6 days in the past of the Open, High, Low and Close prices of the target market, the day of the week, and the previous day’s relative return of the Close prices of the US S&P 500 Index, US Dow Jones Industrial Average Index, US Gold/Silver Index, and the US Oil Index.
Description:
Master of Information Technology by Research
Description:
The class imbalanced problem is one of the major difficulties encountered by many researchers when using classification tools. Multi class problems are especially severe in this regard. The main objective of this study is to propose a suitable technique to handle multi class imbalanced problem. Probabilistic neural network (PNN) is used as the classification tool and the directional prediction of Australian, United States and Srilankan stock market indices is considered as the application. We propose an ensemble technique to handle multi class imbalanced problem that is called multi class undersampling based bagging (MCUB) technique. This is a new initiative that has not been considered in the literature to handle multi class imbalanced problem by employing PNN. The results obtained demonstrate that the proposed MCUB technique is capable of handling multi class imbalanced problem. Therefore, the PNN with the proposed ensemble technique can be used effectively in data classification. As a further study, other classification tools can be used to investigate the performance of the proposed MCUB technique in solving class imbalanced problems.