Short Bio


I am currently a Ph.D. candidate in Computer Science at Columbia University. My advisor is Prof. Luis Gravano and I am member of the Database Research Group. I have also worked closely with Prof. Kathy McKeown from the Data Science Institute.


The overarching goal of my research is to develop computational methods, tools, and systems needed to help analyze and transform into actionable knowledge large collections of evolving data (i.e., data that change over time, such as time series, time-varying measurements, and sequences of streams). To achieve this goal, my work focuses on designing scalable, accurate, and data-aware algorithms; and on building data-driven systems that harness principled methods to solve real-world problems.


In my dissertation research, I have been investigating the design of a unified computational framework that exploits patterns in data sequences to facilitate how we process, organize, store, query, retrieve, and analyze evolving data. Per above, my work embraces a variety of tools from: (i) data management; (ii) data mining and machine learning; and (iii) artifficial intelligence.

Get in Touch

Education

2017

Columbia University

Ph.D. in Computer Science

2015

Columbia University

M.Phil. in Computer Science

2011

EPFL

M.S. in Computer Science

2009

Aristotle University

B.S. in Computer Science

Professional Experience

2015

Microsoft Research

Research Intern

2014

Microsoft Research

Research Intern

2011

Yahoo! Labs

Research Intern

2010

Logitech

Project Management Intern

Selected Achievements, Awards, and Fellowships

2016Nomination for the "ISSI Paper of the Year Award"

Our work on "Predicting the Impact of Scientific Concepts Using Full Text Features" is one of the ten papers selected across papers published in 2015 or 2016 for consideration for the "ISSI Paper of The Year Award," which "recognizes high quality research in the field of Scientometrics and Informetrics." (Final award will be announced in late 2017.)

2015ACM SIGMOD Research Highlight Award

Our paper "k-Shape: Efficient and Accurate Clustering of Time Series" was selected across papers published in premier database conferences for the "ACM SIGMOD Research Highlight Award," which recognizes research papers that "address an important problem, represent a definitive milestone in solving the problem, and have the potential of significant impact."

2014Onassis Foundation Fellow

Recognition for Greek students with outstanding academic record.

Selected Publications

Recent selected referred publications in conferences and journals

Screening for Pancreatic Adenocarcinoma Using Signals From Web Search Logs

John Paparrizos, Ryen W. White, and Eric Horvitz

Journal of Oncology Practice (JOP 2016)


PDF

Predicting the Impact of Scientific Concepts Using Full Text Features

Kathy McKeown,1 Hal Daume,1 Snigdha Chaturvedi,2 John Paparrizos,2 Kapil Thadani,2 et al.

Journal of the American Society for Information Science and Technology (JASIST 2016)

1. Lead PIs 2. Lead student authors in alphabetic order


Nominated for the "ISSI Paper of the Year Award"
PDF

Detecting Devastating Diseases in Search Logs

John Paparrizos, Ryen W. White, and Eric Horvitz

ACM SIGKDD Conference on Knowledge Discovery and Data Mining (ACM SIGKDD 2016)

PDF

k-Shape: Efficient and Accurate Clustering of Time Series

John Paparrizos and Luis Gravano

ACM SIGMOD Conference on Management of Data (ACM SIGMOD 2015)


Invited to "Best of SIGMOD 2015" Special Issue of ACM TODS

Received the "2015 ACM SIGMOD Research Highlight Award"

PDF

List of Publications

Publications in peer-reviewed conferences and journals