Randy Calistri-Yeh





Overview
I am the founder of Custom Chamber Music, which provides custom arrangements of classical music for any combination of instruments. I have been a cellist for over 30 years, and am active in several music groups.

I also have a long history in the computer industry building artificial intelligence personalization systems, with a Ph.D. in computer science. My research areas have included personalization, user modeling, data mining, heuristics, and search engines.



Music

Founder, arranger, programmer, web designer (2003-present)

Custom Chamber Music creates custom arrangements of classical music for chamber groups. We also have a large collection of arrangements ready for immediate download.

Principal Cellist, founder (2005-present)

Livingston Symphony Orchestra (NJ)
Principal Cellist (2007-present)

Mercury Opera Rochester (NY)
Assistant Principal Cellist (2006-2007)

Penfield Symphony Orchestra (NY)
Acting Principal Cellist (2005-2007)

Finger Lakes Symphony Orchestra (NY)
Principal Cellist (1996-2005)





Computers

Everyday Health
Vice President of Marketing Applications (2011-2016)
Senior Director of Search Technology (2009-2011)

Led team of up to 32 people in 3 countries spanning system development, business intelligence (both back-end data and front-end reporting), data & content analysis, machine learning, quality assurance, and project/product management. Selected projects:
  • Predictive User Modeling: I led a combined machine learning and data team to build models that predict whether users have a specific medical condition.
  • Content Personalization for Health Education: I designed, led, and championed two pilot programs that treat content as medicine. A patient gets a “prescription” for content specially tailored to their personal health conditions. The prescription. Users progress through the material at their own pace, and have their own personal topics that others might not have. The system automatically monitors to ensure that the patient is “taking her medicine”. The goal is that as users become more educated about their conditions, their overall health improves.
  • Newsletter Personalization: I built a system to optimize and personalize daily electronic newsletters based on users’ registration and behavioral data (design, algorithms, initial implementation, and team management for subsequent implementations). At its peak, the system sent >5 million personalized emails every day.

Ask.com
Senior Director of Context Mining and Content Management (2008-2009)
Director of Context Mining (2006-2008)

Responsibilities include search heuristics for billions of webpages and images, personalization for millions of users, content classification and quality analysis, vertical search optimization, and tools for user productivity and back-end analysis. Directed up to 25 people on 3 continents. Mentored other managers, worked closely with other business units and partner companies. Selected projects:
  • www.ask.com (related search with path-based personalization, spell checker, web results with geo-biased personalization, triggering & content for specialized vertical search, major components of ranking)
  • www.dictionary.com (related search, crossword solver)
  • www.rushmoredrive.com (customized search for black community)

TextWise / Manning & Napier Information Services
Director of Research (2000-2006)
Head of Advanced Technology (1998-2000)
Computer Scientist (1996-1998)

Responsible for all science/research decisions and overall science direction of the company. Provide technical management and leadership for a geographically distributed team of up to 11 scientists, linguists, and analysts. Involved in all aspects of project planning, proposal writing, and customer presentations. Selected projects:
  • Semantic Signatures: contextual advertising product places highly relevant ads on any webpage in real time. Principal inventor of the underlying Trainable Semantic Vector technology.
  • CINDOR (Conceptual Interlingua for Document Retrieval): cross-language search.
  • ContentTailor / ShrinkText: summarization and readable text compression for first-generation wireless devices.
  • PatentMiner: the first commercial natural-language data mining systems that search and analyze the full text of millions of patents in real time.

ORA / Odyssey Research Associates
Manager, Artificial Intelligence Group (1993-1996)
Computer Scientist (1990-1993)

Project manager and principal investigator of a three-year government contract with Cornell University and the University of Iowa to build an intelligent planning architecture using techniques from planning, scheduling, machine learning, and distributed computing.



Education

Ph.D. in Computer Science, Brown University, 1990 (advisor: Eugene Charniak).

MS in Computer Science, SUNY Albany, 1987.

BS summa cum laude in Computer Science and Mathematics, SUNY Albany, 1986.

Minors: Music, German, Russian, Statistics.



Additional Information

Member of AAAI, ACL, ACM, IEEE Computer Society, Phi Beta Kappa, Sigma Xi.
More information available on my LinkedIn page.




Publications

Author of numerous published papers and patents. Selected titles:

N. Habash, C. Mah, S. Imran, R. Calistri-Yeh, and P. Sheridan, "Design, Construction and Validation of an Arabic-English Conceptual Interlingua for Cross-language Information Retrieval." In Proc. 5th International Conference on Language Resources and Evaluation (LREC-2006), 107-112, 2006.

R.J. Calistri-Yeh and A.M. Segre, "ALPS: An Adaptive Learning and Planning System." Rome Laboratory Technical Report RL-TR-96-225, 1997.

R.J. Calistri-Yeh, A.M. Segre, and D. Sturgill, "The Peaks and Valleys of ALPS: An Adaptive Learning and Planning System for Transportation Scheduling." In Advanced Planning Technology: Technological Achievements of the ARPA/Rome Laboratory Planning Initiative (ARPI-96), 89-96, AAAI Press, May 1996.

Y. Zhu and R.J. Calistri-Yeh, "Iterative Plan Repair in ALPS." Technical Report TM-95-0067, ORA, Ithaca NY, September 1995.

R.J. Calistri-Yeh and A.M. Segre, "ALPS: An adaptive learning and planning system." In Proc. TECOM Artificial Intelligence Technology Symposium, 309-326, September 1994.

R.J. Calistri-Yeh, "Applying Blackboard Techniques to Real-Time Signal Processing and Multimedia Network Management." In Proc. 7th Int'l Conference on Industrial and Engineering Applications of Artificial Intelligence and Expert Systems (IEA/AIE-94), 593-599, Austin, TX, June 1994.

R.J. Calistri-Yeh and A.M. Segre, "The Design of ALPS: An Adaptive Learning and Planning System." In Proc. 2nd Int'l Conference on Artificial Intelligence Planning Systems (AIPS-94), 207-212, Chicago, IL, June 1994.

R.J. Calistri-Yeh, "Iterative Strengthening: An Algorithm for Generating Anytime Optimal Plans." In Proc. 6th Int'l Conference on Tools with Artificial Intelligence (TAI-94), 728-731, New Orleans, LA, November 1994. Also appears in Proc. ARPA / Rome Laboratory Knowledge Based Planning and Scheduling Initiative Workshop (ARPI-94), 3-13, Tucson, AZ, February 1994.

R.J. Calistri-Yeh, "An A* Approach to Robust Plan Recognition for Intelligent Interfaces." In N.G. Bourbakis, ed., Applications of Learning and Planning Methods, vol. 26 of World Scientific Series in Computer Science, 227-251, Teaneck, NJ, 1991.

R.J. Calistri-Yeh, "Utilizing User Models to Handle Ambiguity in Robust Plan Recognition." In User Modeling and User-Adapted Interaction: An International Journal, 1(4):289-322, 1991.

R.J. Calistri, "Classifying and Detecting Plan-Based Misconceptions for Robust Plan Recognition." In AI Magazine, 12(3), 34-35, AAAI Press, Fall 1991.

R.J. Calistri, "Classifying and Detecting Plan-Based Misconceptions for Robust Plan Recognition." Ph.D. dissertation, Department of Computer Science, Brown University, Providence, RI, May 1990.

D.L. Snyder and R.J. Calistri-Yeh, "Management and Analysis of Document Information Text." US Patent #6,038,561, issued 2000.

R.J. Calistri-Yeh, B. Yuan, G.B. Osborne, and D.L. Snyder, "Construction of Trainable Semantic Vectors and Clustering, Classification, and Searching using Trainable Semantic Vectors." US Patent #6,751,621, issued 2004.

R.J. Calistri-Yeh, B. Yuan, G.B. Osborne, and D.L. Snyder, "Construction of Trainable Semantic Vectors and Clustering, Classification, and Searching using Trainable Semantic Vectors." US Patent #7,299,247, issued 2007.

R.J. Calistri-Yeh, B. Yuan, G.B. Osborne, and D.L. Snyder, "Construction of Trainable Semantic Vectors and Clustering, Classification, and Searching using Trainable Semantic Vectors." US Patent #7,406,456, issued 2008.

R.J. Calistri-Yeh, B. Yuan, G.B. Osborne, and D.L. Snyder, "Construction of Trainable Semantic Vectors and Clustering, Classification, and Searching using Trainable Semantic Vectors." US Patent #7,444,356, issued 2008.

R.J. Calistri-Yeh, B. Yuan, G.B. Osborne, and D.L. Snyder, "Construction of Trainable Semantic Vectors and Clustering, Classification, and Searching using Trainable Semantic Vectors." US Patent Application #2004/0193414, published 2004.

R.J. Calistri-Yeh, B. Yuan, G.B. Osborne, and D.L. Snyder, "Construction of Trainable Semantic Vectors and Clustering, Classification, and Searching using Trainable Semantic Vectors." US Patent Application #2004/0199505, published 2004.

R.J. Calistri-Yeh, B. Yuan, G.B. Osborne, and D.L. Snyder, "Construction of Trainable Semantic Vectors and Clustering, Classification, and Searching using Trainable Semantic Vectors." US Patent Application #2004/0199546, published 2004.

R.J. Calistri-Yeh, W. Ruan, C.P. Mah, M.L. Howatt, M.E. McKenna, and M.J. Forrester, "Advertisement Placement Method and System Using Semantic Analysis." US Patent Application #2005/0216516, published 2005.

R.J. Calistri-Yeh, B. Yuan, G.B. Osborne, and D.L. Snyder, "Construction of Trainable Semantic Vectors and Clustering, Classification, and Searching using Trainable Semantic Vectors." US Patent Application #2008/0281814, published 2008.