C. David Byrd

Error message

Brightcove client is not found
Photo of C. David Byrd

C. David Byrd

Research Scientist II

Email: dave@imtc.gatech.edu

Office: Coda 1444A

 

 

Biography: 

David Byrd is a research scientist and PhD student at the Georgia Institute of Technology focusing on machine learning, discrete event simulation, and financial markets.  In his PhD research with advisor Tucker Balch, he has investigated mutual fund portfolio inference, intraday equity market forecasting, stock market simulation, and machine learning approaches to the evaluation of market efficiency. As part of his PhD research, and to support AI research in interactive markets, David is leading the development of an open-source multi-agent equity trading simulation environment: ABIDES (https://github.com/abides-sim/abides).  David also instructs classes for the College of Computing: CS 3600 Intro AI (Spring 2017, Summer 2017, Summer 2018) and CS 4646/7646 Machine Learning for Trading (Summer 2016, Summer 2017, Spring 2018, Fall 2019). In 2018 he won the Graduate Student Instructor of the Year Award in the School of Interactive Computing.

As a research scientist, David works at Georgia Tech's Institute for People and Technology where he has applied machine learning to business intelligence, animal tracking and activity recognition.  He has also worked on a variety of projects including augmented reality for STEM education, jaw gesture recognition for wearables, “big data” analytics for public radio, and cognitive training games for disabled persons.  Prior to joining Georgia Tech, David spent several years as a software developer and manager at internet startups and in the telecommunications industry.

Research Interests
  • Time series machine learning
  • Intelligent agents, multi-agent systems
  • Financial markets
Application Areas
  • Quantitative finance
  • Business intelligence
  • Activity recognition
Recent Publications & Presentations
  1. Bedri, A., Sahni, H., Thukral, P., Starner, T., Byrd, D., Presti, P., Reyes, G., Ghosvanloo, M., and Guo, Z., "Toward silent-speech control of consumer wearables," IEEE Computer, vol. 48, no. 10, pp. 54-62, 2015.
  2. Bedri, A., Byrd, D., Presti, P., Sahni, H., Gue, Z., and Starner, T., "Stick it in your ear: building an in-ear jaw movement sensor," Adjunct Proceedings of the 2015 ACM International Join Conference on Pervasive and Ubiquitous Computing and Proceedings of the 2015 ACM International Symposium on Wearable Computers, pp. 1333-1338, 2015.
  3. Thompson, B., Levy, L., Lambeth, A., Byrd, D., Alcaidinho, J., Radu, I., and Gandy, M., “Participatory design of STEM education AR experiences for heterogeneous student groups: Exploring dimensions of tangibility, simulation, and interaction,” IEEE International Symposium on Mixed and Augmented Reality, ISMAR 2016 Adjunct, ISBN 978-1-5090-3740-7, pp. 53-58, 2016.
  4. Balch, T. and Byrd, D., “Deep Q-Learning for Trading,” QuantCon 2017, video archived.
  5. Brian Hrolenok, Tucker Balch, David Byrd, Scott Gilliland, Chanho Kim, James M. Rehg, Rebecca Roberts, and Kim Wallen, “Use of Position Tracking to Infer Social Structure in Rhesus Macaques,” in Proceedings of the Fifth International Conference on Animal-Computer Interaction (ACI). 2018.
  6. Byrd, David, Maria Hybinette, and Tucker Hybinette Balch. "ABIDES: Towards High-Fidelity Market Simulation for AI Research."  arXiv preprint arXiv:1904.12066 (2019).  https://arxiv.org/abs/1904.12066
  7. Balch, Tucker Hybinette, et al. "How to Evaluate Trading Strategies: Single Agent Market Replay or Multiple Agent Interactive Simulation?."  arXiv preprint arXiv:1906.12010 (2019).  Also presented at ICML 2019 Workshop on AI in Finance.  https://arxiv.org/abs/1906.12010
  8. Byrd, David, and Tucker Hybinette Balch. "Intra-day Equity Price Prediction using Deep Learning as a Measure of Market Efficiency." arXiv preprint arXiv:1908.08168  (2019).  Also presented at ICML 2019 Workshop on AI in Finance.  https://arxiv.org/abs/1908.08168
  9. Byrd, David, Sourabh Bajaj, and Tucker Hybinette Balch. "Fund Asset Inference Using Machine Learning Methods: What’s in That Portfolio?."  The Journal of Financial Data Science 1.3 (2019): 98-107.  https://www.cc.gatech.edu/~cb107/098-107_Byrd_JFDS.pdf