Cüneyt Gürcan Akçora

Assistant Professor

Future Data Lab, U Manitoba

Biography

Cuneyt Gurcan Akcora is an Assistant Professor of Computer Science and Statistics at the University of Manitoba, Canada. Before that, he was a Postdoctoral Fellow in the departments of Computer Science and Statistics at the University of Texas at Dallas. He received his Ph.D. from Università degli studi dell’Insubria, Italy, and his M.S. from State University of New York at Buffalo, USA, as a Fulbright Scholar.

He has worked and collaborated with Yahoo! Research Barcelona, Qatar Computing Research Institute and Huawei Research, Turkey. His primary research interests are Data Science on Complex Networks and Graph Mining, with applications in online social networks and Blockchain networks.

CV | Research Statement

Interests

Data Science on Complex Networks
Large Scale Graph Analysis
Nonparametric Statistics

Education

PhD in Computer Science, 2014

Università degli studi dell'Insubria, Italy
MEng in Computer Science, 2010

State University of New York at Buffalo, USA
BSc in Electrical&Electronics Enginering, 2008

Karadeniz Technical University, Turkey

News

(January) Ethereum Curves has been accepted at SDM 2020

(March 2020) We are organizing a BIRS workshop on Data Science on Blockchains

(November) We will give a 3 hour tutorial Data Science on Blockchains at IEEE ICDE 2020 in Dallas, USA.

(November) We will give a 3 hour tutorial "Data Science on Blockchains" at SDM 2020 in Ohio, USA.

(September) I presented "ChainNet: Learning on Blockchain Graphs with Topological Features" at IEEE ICDM 2019, Beijing, China.

(August) Our work "On Role of Local Blockchain Network Features in Cryptocurrency Price Formation" will be published by the Canadian Journal of Statistics.

(August) We are organizing the SAMSI Workshop on Foundations Of Blockchain Data Analytics at Durham, North Carolina on October 5-6.

(August) ChainNet has been accepted to IEEE ICDM 2019 in Beijing, China.

(July 4) I will give a talk on multi-layer analysis of biological networks at ICSA 2019 in Tianjin, China.

(June 14) Our journal paper GraphBoot: Quantifying Uncertainty in NodeFeature Learning on Large Networks will be published by IEEE Transactions on Knowledge and Data Engineering (TKDE).

(June) With Yulia Gel and Bhavani Thuraisingham we will organize the first Workshop on Blockchain Data Analytics (BDA 2019) at IEEE ICDM 2019, in Beijing, China.

(11 June) I will attend the 36th Annual Quality and Productivity Research Conference and give a talk titled "Blockchain Data Analytics: A new frontier in Data Science" in Washington D.C.

(June) I will be a track chair at the IEEE International Conference on Cyberspace Data and Intelligence (Cyber DI 2019) in Beijing, China.

(May) I will be a demo co-chair at the 26th International Conference on Data Engineering, ICDE 2010 .

(March) We gave a Blockchain Data Analytics tutorial at the Pacific-Asia Conference on Knowledge Discovery and Data Mining (PAKDD2019） in Macao, China.

(17 Jan) I will be a panelist at the 9th ACM Conference on Data and Application Security and Privacy (CodaSPY).

(25 Dec) Our Using Deep Learning to Generate Relational HoneyData paper is published in the Autonomous Cyber Deception, by Springer.

(23 Dec) Our invited paper on Blockchain Data Analytics will appear in the December issue of IEEE Intelligent Informatics Bulletin.

(17 Dec) I will chair the Future of Blockchain from a Big Data perspective session at BigDIA 2018 in Houston, USA.

(3 Dec) I will give a talk on using machine learning models to detect criminal usage of cryptocurrencies at ACSAC 2018 in Puerto Rico.

(17-20 Nov) ICDM changed the schedule and assigned a whole day to Blockchain. We shared the stage with C. Mohan of IBM.

(17-20 Nov) We will give a Blockchain Data Analytics tutorial at IEEE ICDM 2018.

(15 Nov) I will give a talk at the City University of Hong Kong, China

(8 Nov) I presented our Attack Graph paper at IEEE ISI 2018 in Florida, Miami.

(6 Nov) I will give a short course at the Statistics Dept, University of Minnesota.

(13 Oct) I will give a Cryptocurrency talk at the Mathematical Statistics Symposium (in honor of Hira Koul), Michigan State University.

(3 Oct) Our Verizon attack paper was accepted to IEEE ISI 2018.

Selected Publications

Forecasting Bitcoin Price with Graph Chainlets

Over the last couple of years, Bitcoin cryptocurrency and the Blockchain technology that forms the basis of Bitcoin have witnessed a flood of attention. In contrast to fiat currencies used worldwide, the Bitcoin distributed ledger is publicly available by design. This facilitates observing all financial interactions on the network, and analyzing how the network evolves in time. We introduce a novel concept of chainlets, or Bitcoin subgraphs, which allows us to evaluate the local topological structure of the Bitcoin graph over time. Furthermore, we assess the role of chainlets on Bitcoin price formation and dynamics. We investigate the predictive Granger causality of chainlets and identify certain types of chainlets that exhibit the highest predictive influence on Bitcoin price and investment risk.

Cuneyt Gurcan Akcora, Asim K. Dey, Yulia Gel, Murat Kantarcioglu

In PaKDD, 2018

Preprint PDF Code Dataset Project Slides

Blockchain: A Graph Primer

Bitcoin and its underlying technology Blockchain have become popular in recent years. Designed to facilitate a secure distributed platform without central authorities, Blockchain is heralded as a paradigm that will be as powerful as Big Data, Cloud Computing and Machine learning. Blockchain incorporates novel ideas from various fields such as public key encryption and distributed systems. As such, a reader often comes across resources that explain the Blockchain technology from a certain perspective only, leaving the reader with more questions than before. We will offer a holistic view on Blockchain. Starting with a brief history, we will give the building blocks of Blockchain, and explain their interactions. As graph mining has become a major part its analysis, we will elaborate on graph theoretical aspects of the Blockchain technology. We also devote a section to the future of Blockchain and explain how extensions like Smart Contracts and De-centralized Autonomous Organizations will function. Without assuming any reader expertise, our aim is to provide a concise but complete description of the Blockchain technology.

Cuneyt Gurcan Akcora, Yulia Gel, Murat Kantarcioglu

Tutorial on Arxiv.org, 2017

Preprint PDF Project

Recent Publications

Cuneyt Gurcan Akcora, Asim K. Dey, Yulia Gel, Murat Kantarcioglu. Forecasting Bitcoin Price with Graph Chainlets. In PaKDD, 2018.

Preprint PDF Code Dataset Project Slides

Cuneyt Gurcan Akcora, Yulia Gel, Murat Kantarcioglu. Blockchain: A Graph Primer. Tutorial on Arxiv.org, 2017.

Preprint PDF Project

Recent & Upcoming Talks

Understanding Cryptocurrency Price Formation from Time Series of Local Blockchain Graph Features

Jul 30, 2018 1:00 PM

Joint Statistical Meetings

Project

Blockchain Analytics - A Data Science Perspective

Mar 13, 2018 1:00 PM

Souther Methodist University, Colloqium Series in the Statistics Department

Project

Projects

Blockchain Data Analytics

Tools to anayze data created through Blockchains.

Deep Learning

Node and subgraph embeddings for deep learning.

The Upinion Project

The first crowd-sourced sensing and public opinion mining framework on Twitter.

Teaching

Fall 2018

I am teaching the Statistical Methods for Data Science course at the University of Texas at Dallas. 86 Grad students from Statistics and Computer Science take this core Data Science specialization course. See the course description here.

My office hours are Tuesday 11:00-12:00 at ECSS 3.205.
Course material will be posted to the university course page.

Contact

cuneyt.akcora@fulbrightmail.org
cuneytgurcan
800 W. Campbell Road, Richardson, TX 75080 U.S.A.
Monday 9:00 to 17:00 or email for appointment