CSCI 4931 -- Financial Data Mining (Undergraduate)

CINF 4931 -- Financial Data Mining (Undergraduate)

CSCI 5931 -- Financial Data Mining (Graduate)

CINF 5931 -- Financial Data Mining (Graduate)
Updated April 22, 2010

Office and Addresses

Delta 171 Phone 281.283.3805
email: boetticher@uhcl.edu
Secretary: Ms. Kim Edwards, Delta 161 281.283.3860

Face-to-Face Class Hours

Thursday 7:00 - 9:50, Delta 242 or Delta 236.

Office Hours

Thur. 12 - 4, or by appointment. If the suite door is locked, then call my extension (last 4 digits) using the phone in the hallway.

Teaching Assistant

Dawood Moazzem, email: moazzemd3722@uhcl.edu
Office Hours: Tuesday 4 - 8, Wednesday 1 - 5, 7 - 10, Thursday 1 - 4

WebCT link (Most likely will be used for quizzes)

Why take this course?

• More than 98 percent or all college courses teach you how to earn money. This course teaches you how to get your money to work for you. This is your chance to work smarter, not harder.

• The average retirement account has lost 57 percent since October, 2007. Assuming a rate of return of 5 percent, this means you will have to work 18 years to recoup these losses.

• Your company, your stockbroker may mean well, but nobody will care about your financial health more than you.

Why take this course from me?

I have over 9 years experience as a futures trader. In October, 2007 I predicted a downward turn in the market. For 2008, I had 69% winning trades. For 2008 I averaged 16% profit per month over 5.3 months for an overall yearly profit of 120%. I took the summer off to travel. On September 24, 2008, at the UHCL Scholarly Lecture Series I accurately predicted a steep downward turn to the UHCL President, UHCL Provost, various Deans, and UHCL faculty. Two weeks later the market dropped 25 percent.

I have had a best paper in financial data mining and I have been a beta-tester for a major commercial financial data mining product.

Results from a financial data mining project in Fall, 2008

Most of the students had very little financial background for the term project. Each student started with $100,000. The table below shows how much money they made in 2.5 years. 60% of the groups made more than 4 million dollars.

GDB Cup - Fall, 2008

Course Description

Mathematically sophisticated financial models are becoming more prevalent in the financial domain. It is possible to manually construct and test various hypotheses; however the process is extremely slow. A preferred approach is to data mine financial instruments in order to identify potentially successful approaches. This course will examine different sources of data (e.g. derivatives, stocks) and how to apply machine learners in order to construct profitable models.

The traditional undergraduate student load is 5 courses. Be prepared to commit 10 to 15 hours per week to this course!

The traditional graduate student load is 3 courses. Be prepared to commit 15 to 20 hours per week to this course!

Course Goals

By the end of the course, you will

• Understand the financial data mining process;

• Understand various technical indicators;

• Have an understanding of various Machine Learners (ML) and how to apply these tools in a financial context (e.g. stock market); and

• Hopefully transcend the market

Prerequisites

The prerequisites for this course are at least one programming course or experience in C, C++, C*, Java, Delphi, or VB using Visual Studio. A class in Data Structures (CSCI3333) is recommended. A class in artificial intelligence, machine learning, pattern recognition, algorithms, or statistics would be helpful, but is not required.

I also encourage students who have a business/finance background. Please talk to me about your particular situation.

This course will assume No previous knowledge of finance.

Methodology

Face-to-face lecture and interactive problem solving.

Appraisal Undergraduate

Appraisal Graduate

Grading:

    93+ = A; 90 = A-; 87+ = B+; 83+ = B; 80+ = B-;

      77+ = C+; 73+ = C; 70 = C-; 67+ = D+; 63+ = D; 60+ = D-; 0+= F

My motto:

Seek the Truth.

Show altruistic love.

Appreciate beauty.

Required Textbook  

There is no required textbook for this course. Readings will be from various papers or tutorials.

References

• KDNuggets: Great resource for data mining.

Schedule

Jan 21 - Data Mining and Financial Overview, Go over term project (3 hours)

Jan 28 - Data Cleansing, Term Project (3 hours)

Moving averages, RSI, Bollinger Bands, Stochastics, CCI, MACD, PNF, Doji, Support, Resistance

Technical Indicators Tutorial

Technical Analysis Explained

Technical Analysis Tutorial (Investopedia)

A Primer on Technical Analysis, Lagging, Leading

Saswat Anand, Wei-Ngan Chin, Siau-Cheng Khoo, “Charting patterns on price history,” Proceedings of the sixth ACM SIGPLAN international conference on Functional programming, October, 2001.

Web Pages for Charting

A)   http://stockcharts.com/h-sc/ui?s=IBM

B)   http://www.stockta.com/

Feb 04/11 - Technical Indicators (6 hours)

Feb 18 - Chart patterns (3 hours)     

Feb 15 - Commercial Financial Data Tools - Mainly Amibroker (3 hours)     

Mar 04 - Technical Indicators, Part 3

* Last day to drop a class/withdraw for the semester is April 1^st *

Apr 01 - Go over midterm, Neural Networks (3 hours)

Apr 08 - Backtesting, Validation, Futures, Options, FOREX (3 hours)

Apr 15 - Other machine learners and case studies (3 hours)

Apr 22 - Other machine learners and case studies (3 hours)

Readings for next week

Tobias Schreck, Tatiana Tekušová, Jörn Kohlhammer, Dieter Fellner, “Trajectory-based visual analysis of large financial time series data,” ACM SIGKDD Explorations Newsletter, 9 2, December, 2007.

Kearns, M.   Ortiz, L., The Penn-Lehman automated trading project, Nov-Dec 2003, Vol. 18, Issue: 6, Pp. 22- 31

Wong, R.K.   Ng, P.N. , “A hybrid approach for automated trading systems,” Second Australian and New Zealand Conference on Intelligent Information Systems, 1994, Dec. 1994, Pp. 278-282.

Antonia Azzini, Andrea Tettamanzi, “Automated trading on financial instruments with evolved neural networks,” 9th annual conference on Genetic and evolutionary computation (GECCO), 2007: 2252.

Apr 29 - Automated Trading (3 hours)

May 01 - Midnight - Term Project is due

May 03 - Midnight - Final Exam is due

May 06 - Go over Final and Term projects

GDB Cup - Spring, 2010

Other Policies

Homework, Projects, Research Paper

• Homework and projects are due exactly at the prescribed time (usually the beginning of class). As soon as a homework or project is collected, then all others are considered 1 day late (even if it only 3 minutes). In the event you might be running late, you might want to email the assignment. Also, when preparing your assignment, be mindful of possible backlogs at the printer, jammed printer, printer out of toner, etc.

• Late homework/projects are accepted with a penalty of 10% deduction per 24-hour period after the due date. No late project will be accepted one week after the due date. The last homework/project cannot be late.

• There will be no extra-credit homework or projects in this course.

• All homework and projects must be typed not hand-written.

• VERY IMPORTANT! You may not discuss, use, email, show, give, buy, sell, borrow, trade, steal, etc. in whole or part, any of the homework or projects with anyone in any manner not prescribed by the instructor. Penalty for cheating will be extremely severe and may result in an F for this course. This condition applies even after you complete this course! Penalty for cheating will be extremely severe and may result in an F for this course. 

• Handing in an assignment for another student is considered cheating. Penalty for cheating will be extremely severe and may result in an F for this course. 

• VERY IMPORTANT! Failing to report to the instructor any incident in which a student witnesses an alleged violation of the Academic Honesty Code is considered a violation of the academic honesty code. Please see me to discuss any incidents.

• VERY IMPORTANT! Purchasing, or otherwise acquiring and submitting as one's own work any research paper or any other writing assignment prepared by others constitutes cheating. Penalty for cheating will be extremely severe and may result in an F for this course.

• Standard academic honesty procedure will be followed. See the following link for additional information: http://b3308-adm.uhcl.edu/PolicyProcedures/Policy.html

Tests and Quizzes

• There are no make-up tests except in verified medical emergencies and with immediate notification. Rescheduling a final exam in order to catch a plane flight is unacceptable. Make up exams are harder, and different, than original exams.

• There are no make-up quizzes. Allow plenty of additional time in the event that Blackboard crashes.

• You are responsible for all required readings assigned throughout the semester.

• Students are to work on test and quizzes individually.  Students may not discuss, show, give, sell, borrow, trade, share, etc. their tests or quizzes. Penalty on cheating will be extremely severe. Standard academic honesty procedure will be followed.

• VERY IMPORTANT! Providing answers for any assigned work or examination when not specifically authorized by the instructor to do so. Or, informing any person or persons of the contents of any examination prior to the time the examination is given is considered cheating. Penalty for cheating will be extremely severe and may result in an F for this course.

• VERY IMPORTANT! Failing to report to the instructor any incident in which a student witnesses an alleged violation of the Academic Honesty Code is considered a violation of the academic honesty code. Please see me to discuss any incidents.

Miscellaneous

• Any person with a disability who requires a special accommodation should inform me and contact the Disability services office or call 281 283 2627 as soon as possible.

• You are expected to come fully prepared to every class!

• Incomplete grades or administrative withdrawals occur only under extremely rare situations.

• The ringing, beeping, buzzing of cell phones, watches, and/or pagers during class time is extremely rude and disruptive to your fellow students and to the class flow. Please turn off all cell phones, watches, and pagers prior to the start of class.

• This is not a Web-based class. You are expected to attend every class! Missing 1 class is OK. Minus 1 from your final grade for each additional absense.

• I am willing to provide letters of recommendation/references only if you have attained an 'A' in one of my classes, or two 'A-' in two of my classes.

• I highly recommend that you seek out your advisor and complete you Candidate Plan of Study (CPS) as soon as possible. I am normally not available for advising during the summer months.

• Pay very careful attention to your email correspondence. It reflects on your communication skills. Below is a compilation of email errors I have received during the past year.

  dear sir.

  wen r u gonna grad the homework, bcoz i have a doubt about the third problem

  Some student

  Common problems:

     *   wen instead of when

     *   bcoz instead of because

     *   r instead of are

     *   u instead of you

     *   lowecase i instead of I

     *   starting a sentence with a lowercase letter

     *   doubt instead of question

• I immediately discard anonymous emails.

Return to Top

Home • UHCL • SCE

2700 Bay Area Boulevard
Delta Building. Office 171
Houston, Texas 77058
Voice: 281-283-3805
Fax: 281-283-3869
boetticher@uhcl.edu

© 2002-2010 Boetticher: Financial Data Mining Course, All Rights Reserved.