Dr. Schumaker has conducted dozens of keynote lectures and nearly fifty seminars, invited talks and presentations on various data science topics. His dynamic and engaging style can can be tailored for audiences ranging from novice to technical experts and audiences of tens to several thousand participants. Example talks include:
Becoming a Data Scientist
This entry-level talk is oriented towards those interested in a data science career. What is it? What jobs are available? What tools, techniques and knowledge are important? What resources are available to kickstart your career? This interactive talk will answer these questions and more.
Lessons from the Future: Predictions in Finance, Sports and Medicine
This talk explores three seemingly disparate research areas of textual/financial prediction, using sentiment analysis to predict team wins and predicting previously unknown poly-pharmaceutical drug interactions; and how the knowledge of data science begins to weave them together.
Predicting Deadly Drug Combinations through a Machine Learning Approach
The holy grail of pharmacovigilance systems has been to identify, with certainty, those post-marketed drugs that cause unexpected reactions with one another. These poly-pharmaceutical reactions may have gone unnoticed due to the absence of sufficient evidence and/or their reaction severity was not sufficiently strong enough to draw researcher attention. We plan to automate the signal detection process of adverse drug combinations with the TylerADE system by using the FDA’s Adverse Effects Reporting System (FAERS). Once collected, the data will be machine learned to identify potential n-drug adverse reactions. This system could assist in prioritizing bench studies more efficiently as well as be used in a clinical setting at the point of prescription to calculate potential adverse reactions.
Predicting Wins and Losses in Team Sports – Approaches and Examples
This technical talk explores the use of sentiment analysis on Twitter tweets to determine team wins in the English Premier League and National Football League. Using Surowiecki’s Wisdom of Crowds where a group of novice forecasters can better predict complex events than experts, forecasts are made using differential tweet sentiments as a time-series signal and analyzed using stock market technical trading techniques.
Prediction from Regional Angst – A Study of NFL Sentiment in Twitter Using Stock Market Charting
To predict NFL game outcomes, we examine the application of technical stock market techniques to sentiment gathered from social media. From our analysis we found a $14.84 average return per sentiment-based wager compared to a $12.21 average return loss on the entire 256 games of the 2015–2016 regular season if using an odds-only approach. We further noted that wagers on underdogs (i.e., the less favored teams) that exhibit a “golden cross” pattern in sentiment (e.g., the most recent sentiment signal crosses the longer baseline sentiment), netted a $48.18 return per wager on 41 wagers. These results show promise of cross-domain research and we believe that applying stock market techniques to sports wagering may open an entire new research area.
Evaluating Sentiment in Financial News Articles
Can the choice of words and tone used by the authors of financial news articles correlate to measurable stock price movements? If so, can the magnitude of price movement be predicted using these same variables? We investigate these questions using the Arizona Financial Text (AZFinText) system, a financial news article prediction system, and pair it with a sentiment analysis tool. Through our analysis, we found that subjective news articles were easier to predict in price direction (59.0% versus 50.0% of chance alone) and using a simple trading engine, subjective articles garnered a 3.30% return. Looking further into the role of author tone in financial news articles, we found that articles with a negative sentiment were easiest to predict in price direction (50.9% versus 50.0% of chance alone) and a 3.04% trading return. Investigating negative sentiment further, we found that our system was able to predict price decreases in articles of a positive sentiment 53.5% of the time, and price increases in articles of a negative sentiment 52.4% of the time. We believe that perhaps this result can be attributable to market traders behaving in a contrarian manner, e.g., see good news, sell; see bad news, buy.
If you are interested in having Dr. Schumaker speak at your event, please feel free to contact him with potential times and locations.
National Institute of Applied Science and Technology, Tunis, Tunisia
Ecole Superieure Privee d’Ingenierie et de Technologies, Tunis, Tunisia
IEEE International Conference on Advances in Big Data, Computing and Data Communication Systems (icABCD-2018), Durban, South Africa
Institute of Engineering and Management (IEM), Kolkata, India
University of Engineering and Management (UEM), Jaipur, India
US Army Corp of Engineers, Vicksburg, MS