School Seminars and Colloquia

A Swingtum Theory of Intelligent Finance Integrating Technical, Fundamental, Quantitative and Strategic Analysis of the Financial Markets

ORSUM

by Dr Heping Pan


Institution: University of Ballarat
Date: Fri 3rd December 2004
Time: 1:05 PM
Location: Room 213, Richard Berry Building, The University of Melbourne

Abstract: 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. The
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. To describe the multilevel swings and momentum for a single
market, the scale space of phase provides the most essential information as
input features to a SBIN model. Multifractality, log-periodic power laws, and
physical cycles provide much of the building blocks to the unimarket swingtum
models. Asymmetrical Dependence Test with conditionality and scaling of time
provides a major tool for detecting intermarket influence relations. The
Swingtum Theory focuses not only on abstract market modeling, but also on
continuous monitoring the global financial markets, looking for pockets of
predictability and profitability with the Global Influence Networks as an
actual application of SBIN. Although this theory is still at an early stage
of development, a SBIN for predicting daily direction of Australian All
Ordinary Index (High, Low, Close) has already shown significant and nontrivial
performance.

For More Information: Mark Fackrell: tel. 8344-8053 email m.fackrell@ms.unimelb.edu.au