 |
Nominated for the James LaSalle Teaching Award; 2004 and 2006
|
|
Nominated for the GPSC Outstanding Research Assistant of the Year; 2005 and 2007
|
|
GRS Scholarship recipient - University of Arizona Spring; 2005-2007
|
|
Tuition Scholarship recipient - University of Arizona; 2003-2007
|
|
Graduate Assistantship - University of Arizona; 2003-2007
|
|
Tuition Scholarship recipient - University of Akron; 2000-2001
|
|
Graduate Assistantship - University of Akron; 1999-2000
|
|
Partial Scholarship recipient - University of Cincinnati
|
|
Inducted into Sigma Iota Epsilon - Honorary Management Fraternity
|
|
|
|
Sports Knowledge Management and Data Mining
Mining relevant data from Sports-related databases and producing accurate predictions from them can provide an edge to sports organizations and gamblers alike. Using the Moneyball style philosophy, this project analyzes the use of different machine learning techniques to predict outcomes of sporting events.
|
|
AZFinText
The AZFinText Project examines the relationship between financial news articles and their impact on stock market prices. This project utilizes various textual representation schemes, price prediction models and machine learning techniques to accomplish profitability in extreme near-term trading. Based on the premise that unexpected news events can shape the price of a stock, we capitalize on automatically identifying the relevant keywords in the news article and then execute a trade well-before human traders have a chance to read the news article.
|
|
Question Answer Systems
The AZ-ALICE and TARA chatterbot experiments were an exploration into the potential of using natural language chatterbots as conversational entities. These two studies, AZ-ALICE in Fall 2003 and TARA in Spring/Summer 2004, were built on the proven ALICE chatterbot engine (www.alicebots.org). In the AZ-ALICE experiment we tested a limited telecommunications knowledge set to see how well the chatterbot could respond to telecommunications-related questions. The TARA studies went one step further and analyzed a substantial terrorism knowledge base that was automatically gathered from the Internet. From our experiments we found several interesting facets. The most important of which was the discovery that adding more knowledge to the system actually harmed the quality of responses. Further information on these studies can be found in the publications section.
|
|
