Description:
This paper presents a basic theory of intelligent finance as a new paradigm of financial investment. It is assumed that the financial market is always in a state of swing between efficient and inefficient modes on multiple levels of time scale; it is possible to go beyond the efficient market theory to study the dynamic evolving process of the market between equilibrium and far-from-equilibrium; there are robust dynamic patterns in this evolving process, which may be exploitable via intelligent trading systems. On the foundation of the four principles - comprehensive, predictive, dynamic and strategic, the basic theory takes the information sources into the loop as the starting points for all the market analysis, introducing the scale space of time into the pricing process analysis in order to detect and capture trends, cycles and seasonality on multiple intrinsic levels of time scale which are then used as the dynamic basis for constructing and managing portfolios. In stock markets, the theory exhibits itself in the form of an Intelligent Dynamic Portfolio Theory, which integrates predictive modeling of a bullbear market cycle, sector rotation, and portfolio optimization with a reactive trend following trading strategy.
Description:
Swingtum stands for Swing and Momentum. A Swingtum Theory of Intelligent Finance is presented here in order to provide a scientific and engineering foundation to professional swing trading and momentum trading. The origins of Swingtum theory naturally go deep into the empirical professional technical analysis, fundamental analysis and strategic analysis, and academic quantitative analysis including financial mathematics, econophysics and computational intelligence. The central perspective of Swingtum theory is the pervasive existence of multilevel swings and abrupt momentum moves in the market prices, business fundamentals, mass psychology, and even the news flow. The dualism of swing versus momentum may resemble the wave-particle dualism in quantum mechanics, however with much higher nonlinearity and sophistication of human traders as building elements of the markets. This view forms the Swingtum Market Hypothesis, which is closer to the reality than Efficient Market Hypothesis and Fractal Market Hypothesis are. Swingtum theory models the markets with two parallel and intertwining lines of thought: the multilevel swings and momentums of a target market, and the influences from interrelated markets and the surrounding economic environment. The two lines are then unified into a comprehensive framework - Super Bayesian Influence Networks (SBIN) consisting of many Probability Ensembles of Neural Networks (PENN).
Description:
As the oil demand continues to surge ahead and production continues to decline, it is believed that oil prices will continue to rise to unprecedented levels. As a reference, in 2004, the crude oil price was averaging $41 per barrel while it is above $130 in today’s market. This oil price increase is affecting the economy from both developing and developed countries. This paper investigates the possibility of using oil futures price to forecast spot price direction for short term, one day ahead using multilayer feedforward neural networks. The data was pre-processed to reflect the direction and the turning point of the price. Our approach is to create a benchmark based on lagged value of pre-processed spot price, then add pre-processed futures prices 1, 2, 3 and 4 months for maturity one by one and also altogether. For all the experiments, that include futures data as an input, the results show that on the short term, one day ahead, there is weak evidence to support futures price do hold new information on the spot price direction. This evidence is stronger for futures 1, 2 months to maturity.
Description:
As the oil demand continues to surge ahead and production continues to decline, it is believed that oil prices will continue to rise to unprecedented levels. As a reference, in 2004, the crude oil price was averaging $41 per barrel while it is above $130 in today’s market. This oil price increase is affecting the economy from both developing and developed countries. This paper investigates the possibility of using oil futures price to forecast spot price direction for short term, one day ahead using multilayer feedforward neural networks. The data was pre-processed to reflect the direction and the turning point of the price. Our approach is to create a benchmark based on lagged value of pre-processed spot price, then add pre-processed futures prices 1, 2, 3 and 4 months for maturity one by one and also altogether. For all the experiments, that include futures data as an input, the results show that on the short term, one day ahead, there is weak evidence to support futures price do hold new information on the spot price direction. This evidence is stronger for futures 1, 2 months to maturity.
Description:
This paper presents short-term forecasting model for crude oil prices based on three layer feedforward neural network. Careful attention was paid on finding the optimal network structure. Moreover, a number of features were tested as an inputs such as crude oil futures prices, dollar index, gold spot price, heating oil spot price and S&P 500 index. The results show that with adequate network design and appropriate selection of the training inputs, feedforward networks are capable of forecasting noisy time series with high accuracy.
Description:
This paper presents short-term forecasting model for crude oil prices based on three layer feedforward neural network. Careful attention was paid on finding the optimal network structure. Moreover, a number of features were tested as an inputs such as crude oil futures prices, dollar index, gold spot price, heating oil spot price and S&P 500 index. The results show that with adequate network design and appropriate selection of the training inputs, feedforward networks are capable of forecasting noisy time series with high accuracy.
Description:
Intelligent finance represents a new direction recently emerging from the confluence of several distinct disciplines in financial market analysis, investing and trading, removing any historical or artificial barrier between them. It is conceived as the science, technology and art of the comprehensive, predictive, dynamic and strategic analysis of global financial markets, towards a unification and integration of academic finance and professional finance. As a comprehensive approach, it is a quest for absolute positive and non-trivial returns in investing and trading by exploiting complete information about financial markets from all general perspectives, drawing ideas, theories, models and techniques from many related academic disciplines, such as macroeconomics, microeconomics, academic finance, financial mathematics, econophysics, behavioural finance and computational finance, and from professional schools of thought, such as macrowave investing, trend following, fundamental analysis, technical analysis, mind analysis, active speculation, etc. In terms of risk management, intelligent finance is expected to minimize the very last risk-the incompleteness of an investing or trading method or system. The theoretical framework of intelligent finance consists of four major components: financial information fusion, multilevel stochastic dynamic process models, active portfolio and total risk management, and financial strategic analysis. We first provide the background from which intelligent finance has recently emerged as a new direction in finance research and industry, and then provide a brief theoretical review of the predictability of financial markets since Bachelier. After these background discussions, we clarify the major research directions of intelligent finance.
Description:
This paper investigates t he predictability of moving average rules for the China stock market. We find that buy signals generate higher returns and less volatility, while returns following sell signals are negative and more volatile. Moreover, the bootstrapping results indicate that the asymmetrical patterns of return and volatility between buy and sell signals cannot be explained by four popular linear models of returns, especially the phenomenon of negative sell returns. We then test the nonlinear dynamic process of returns. Although the existing artificial neural network (ANN) model can replicate the negative sell returns, it fails to capture the volatility patterns of buy and sell returns. Furthermore, we introduce the conditional heteroskedasticity structure into the ANN model and find that the revised ANN model cannot only explain the predictability of returns, but can also capture the patterns of buy and sell volatility, which are never achieved by any linear model of returns tested in the related literature. Therefore, we conclude that the moving average trading rules can pick up some of the hidden nonlinear patterns in the dynamic process of stock returns, which may be the reason why they can be used to predict price changes.
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 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:
In this paper, we treat defaultable bond as a contingent claim in incomplete markets. By setting up an investment portfolio with risky asset and construct two backward stochastic differential equation (BSDE), we develop the bond pricing equation by finding the optimal investment strategy with minimum risk through linear-quadratic hedging method.