Abstract

In this thesis, we explore the ability of statistical classification methods to predict financial events in the bond and stock markets. Our classification methods include conventional Linear Dicriminant Analysis (LDA), and a number of less familiar non-linear techniques such as Probabilistic Neural Network (PNN), Learning Vector Quanization (LVQ), Oblique Classifer (OCI), and Ripper Rule Induction (RRI).

Publication Type:	Thesis (Doctoral)
Subjects:	H Social Sciences > HG Finance
Departments:	Bayes Business School Doctoral Theses Bayes Business School > Bayes Business School Doctoral Theses

Preview

PDF - Accepted Version Download (40MB) | Preview

Export

Downloads