BOND UNIVERSITY School of Information Technology

INFM 733 Computational Finance

Lecturer and Course Coordinator: Dr Clarence N W Tan,
BS ElecEngr (Computers), MS Ind&SysEngr, MBA (USC), Ph.D.(Bond)
ASIA, AIBF(Sr), ATAA, MASC (Australia), F. InstBA, FBSC (UK)
Assistant Professor

Office: School of Information Technology, ARCH Level 5
Tel (Office): (07) 5595 3366
Fax: (07) 5595 3320
Tel. (A/H): (0414) 988-986
e-mail: ctan@computer.org
Course URL: http://www.wave.its.bond.edu.au/INFM733
Personal URL: http://ctan.home.ml.org
Office Hours: TBA Other times: By Appointment
Best form of contact: e-mail

Computational Finance

This course aims to expose students interested in a career in the financial sector to advanced technology soft computing methods such as Artificial Intelligence (AI) methods such as Artificial Neural Networks (ANNs), Genetic Algorithms (GA), Rule-based Expert systems, and Hybrid systems and their applications to finance.

Financial applications that will be studied include financial markets forecasting, trading systems, financial analysis modeling and financial distress predictions/classifications.

The demand for financial engineers with these skills are high and this course will provided both Commerce and IT students the opportunity to enhance their marketability in the finance sector by exposing them to cutting edge financial technology. There will be hands-on laboratory sessions for students to have the opportunity to apply the methods taught. Students are expected have competency in basic computer skills such as working with spreadsheets. Basic knowledge of financial theories and markets is desirable but not required as the financial knowledge required to apply these methods will be taught.

Prerequisites: Competency in basic computer skills eg. working with spreasheets equivalent to COMP 705 End-User Computing, basic finance knowledge.

Recommended: FINC 700, COMP 705

Text:

1. Excerpts from forthcoming book by Dr C N W Tan 'Artificial Neural Networks As Applied in an OECD Market'.
   NOTE: Students will be provided with the handout for the length of the course and will have to return the notes at the end of the course. All information with regards to the handout are to be treated as confidential.
2. Lecture Notes

Recommended Text:

1. Trippi R., and Turban, E., Neural Networks in Finance and Investing 2n. Edition, Irwin, USA, ISBN 1-55738-919-6, 1996.
2. Deboeck, G. J., Trading on the Edge: Neural, Genetic, and Fuzzy Systems for Chaotic Financial Markets, ISBN 0-471-31100-6, John Wiley and Sons Inc., USA, 1994.
3. Carew, E., Fast Money 3

Check the INFM 733 web page for online books.

Assessment Details

Important: Students are strongly discouraged from missing lectures as substantial examinable material not covered by the text will be delivered in the lectures.

• Research Project 30%

This project will involve a research paper on a topic computational finance. Students are encouraged to do research on artificial intelligence in an area of their interest and to discuss it with the lecturer before starting. Students are expected to do a fifteen minute presentation on their research towards the end of the semester. Please note late project will not be accepted.

• 1 Close-Book Mid-semester Examination 30%

• 1 Final 2-hour Close-book Examination 35%

• Assignments and Participation 5%

Students will be rewarded for regularly attending sessions, participating in class discussions and completing in-class/lab assignments.

Late homework will not be tolerated

Contact Times

Attendance at formal session times are compulsory.

Course Outline