Marios Kokkodis

Marios Kokkodis
Assistant Professor of Information Systems
Carroll School of Management
Boston College


Short Bio


Marios Kokkodis is an Assistant Professor of Information Systems at the Carroll School of Management, Boston College. He received his PhD in Information Systems from NYU Stern in May 2015, under the guidance of Panos Ipeirotis. His research focuses on interdisciplinary data-driven problems (online markets, data mining, econometrics, social science). His teaching includes data-analytics and data mining courses for both undergraduate and graduate business majors. His research appears in major Information Systems (Management Science, ICIS) and Computer Science (WSDM, WWW) outlets. He has received multiple awards including the NYU Stern Harold W. MacDowell Award for his dissertation in online labor markets.

Research


My research focuses on identifying problems in the way that online markets operate, and propose solutions. The explosion of online platforms has created an abundance of data to analyze which in term provided researches with opportunities to study problems from a data-driven perspective. By combining data mining, social science and econometrics, I currently focus on the following projects:

  • Online Labor Markets (with P. Ipeirotis)

    In an online labor marketplace (OLM) employers post jobs, receive applications from workers who are looking for opportunities, and make hiring decisions. Once hired, workers complete the tasks online and receive their payment along with feedback about their performance. Because of the natural heterogeneity that appears in task categories, skills, and the latent abilities of workers and employers, these markets suffer from a series of inefficiencies. In this work we focus on understanding these inefficiencies and propose solutions. In particular, we study three problems: (1) Reputation Transferability (2) Career Development Paths and (3) Hiring Decisions. We first propose and evaluate different approaches that explain how workers’ reputation transfers across different task categories. Next, we define the utility of a set of skills in an OLM by taking into account the level of expertise of the worker and the demand of each skill in the marketplace. We then use this definition to further build and showcase a career development framework. Finally, we build a series of explanatory and predictive models that describe employers’ choices, and we further study how each one of the available worker-employer characteristics affect hiring decisions.

    Kokkodis Marios and Ipeirotis G. Panagiotis. “Reputation Transferability in Online Labor Markets”. Management Science, 2015.

    Kokkodis Marios, Papadimitriou Panagiotis and Ipeirotis G. Panagiotis. “Hiring Behavior Models for Online Labor Markets”. Proceedings of the eighth ACM international conference on Web search and data mining (WSDM). ACM, 2015.

    Kokkodis Marios and Ipeirotis G. Panagiotis. “The Utility of Skills in Online Labor Markets”. Proceedings of the International Conference on Information Systems (ICIS), 2014.

    Kokkodis Marios and Ipeirotis G. Panagiotis. “Have you done anything like that? Predicting user performance using inter-category reputation”. Proceedings of the sixth ACM international conference on Web search and data mining (WSDM). ACM, 2013.



  • Online Markets and Promoting Agencies (with K. Pelechrinis and T. Lappas)

    Electronic marketplaces have been booming in the past decade. Many of them (e.g., Amazon, Apple App Store and Google Play) create an almost zero barrier-to-entry environment, facilitating independent authors, programmers and artists to list their books, software and songs respectively for sale. Existing literature supports the hypothesis that promoting a product has a strong effect on sales. In parallel, many of the users that participate in these environments collaborate with promoting agencies, such as publishers, software companies and music labels. In this work, we are interested in identifying the importance of these agencies as well as ways to overcome potential 'invisible barriers' that such agencies impose.

  • Online Reviews (with K. Pelechrinis and T. Lappas)

    Despite the unprecedented volume and well-documented diversity of online review data, all of these platforms assume that all the reviewers of a given business have the same standards and expectations. Based on this assumption of uniformity, all the reviews on a business are used to compute a global average rating, appear together in ranked lists, and are jointly indexed by the platform's search engine. In this project we provide evidence that raise the need for customization and we further discuss how the design of an online marketplace affects the overall helpfulness of the platform reviews.

Teaching


TBA

Contact


kokkodisbcedu

TBA

140 Commonwealth Ave, Fulton Hall 412C Chestnut Hill, MA 02467

Industry Collaborations


During my PhD years I had the opportunity to intern at Microsoft Research and oDesk:

  • Research Scientist at Microsoft Research (Summer 2013)

    In summer of 2013 I joined the Search Labs group at Microsoft Research (Mountain View Campus). There I worked with Anitha Kannan and Krishnaram Kenthapadi on algorithmically augmenting education textbooks with videos. My work has lead to two publications and one patent application (pending).

  • Data Scientist at oDesk.com (Summer 2012)

    In summer of 2012 I joined oDesk Research. There I worked with Panagiotis Papadimitriou on building a framework for recommending potential good contractors to employers. The framework we developed is currently in use by oDesk. Furthermore, my involvement in this project sparked my interest in hiring decisions in Online Labor Markets, a subject that ended up being a whole chapter in my dissertation.

  • Data Scientist at oDesk.com (Summer 2011)

    In summer of 2011 I joined for the first time oDesk Research. There I worked with John Horton on finding associations amongst the available skills in the market place. This was my first exposure to online labor markets. My very good collaboration with John, as well as the exciting questions that were naturally arising is this area of paid crowdsourcing were a few of the fundamental reasons I ended up pursuing a dissertation about inefficiencies in Online Labor Markets.

The Invisible Barrier: The Effect of Promoting Agencies on Sales in Electronic Markets

Kokkodis Marios, Konstantinos Pelechrinis and Theodoros Lappas.


Disclosing Purchase Information and Review Helpfulness

Kokkodis Marios and Theodoros Lappas.


Career Development Paths

Kokkodis Marios and Ipeirotis G. Panagiotis.


On hiring Decisions in Online Labor Markets

Kokkodis Marios, Papadimitriou Panagiotis and Ipeirotis G. Panagiotis.


The Effect of Promoting Agencies on Sales in Electronic Markets

Kokkodis Marios

INFORMS 2015


Disclosing Purchase Information and Review Helpfulness

Kokkodis Marios

INFORMS 2015


The Effect of Disclosing Purchase Information on Review Helpfulness: Evidence from Amazon.com

Kokkodis Marios

Conference on Information Systems and Technology (CIST), 2015


Reputation Transferability in Online Publications Labor Markets

Kokkodis Marios Ipeirotis G. Panagiotis.

Management Science, 2015


Hiring Behavior Models for Online Labor Markets

Kokkodis Marios, Papadimitriou Panagiotis and Ipeirotis G. Panagiotis.

ACM Web Search and Data Mining (WSDM), 2015


The Utility of Skills in Online Labor Markets

Kokkodis Marios and Ipeirotis G. Panagiotis.

International Conference on Information Systems (ICIS), 2014


Assigning Educational Videos at Appropriate Locations in Textbooks

Kokkodis Marios, Anitha Kannan, and Krishnaram Kenthapadi.

International Educational Data Mining Society (EDM), 2014


Assigning Videos to Textbooks at Appropriate Granularity

Kokkodis Marios, Anitha Kannan, and Krishnaram Kenthapadi.

ACM Learning at Scale (LAS), 2014


On hiring Decisions in Online Labor Markets

Kokkodis Marios, Papadimitriou Panagiotis and Ipeirotis G. Panagiotis.

Workshop on Information Systems Economics (WISE), 2014


Online Labor Markets: Reputation Transferability, Career Development Paths and Hiring Decisions

Kokkodis Marios

Doctoral Consortium, AAAI Conference on Human Computation & Crowdsourcing (HCOMP), 2014


Who Should I Hire? Maximizing Employer’s Utility in Online Labor Markets

Kokkodis Marios, Papadimitriou Panagiotis, Ipeirtotis, G, Panagiotis

Winter Conference on Business Intelligence, 2013


Credibility dimensions in online reviews

Kokkodis Marios

Winter Conference on Business Intelligence, 2013


Have you done anything like that? Predicting user performance using inter-category reputation

Kokkodis Marios, Ipeirotis G. Panagiotis.

ACM Web Search and Data Mining (WSDM), 2013


Maximizing Employer’s Utility in Online Labor Markets

Kokkodis Marios

INFORMS 2013


Reputation Transferability in Online Labor Market

Kokkodis Marios

INFORMS 2013


Learning from positive and unlabeled amazon reviews: towards identifying trustworthy reviewers

Kokkodis Marios

ACM World Wide Web (WWW), 2012.


Where are you coming from, stranger? Predicting future performance using inter-category reputation

Kokkodis Marios Ipeirotis G. Panagiotis

Winter Conference on Business Intelligence, 2012


Network-level characteristics of Spamming: An empirical analysis

Kokkodis Marios, Faloutsos Michalis and Markopoulou Athina.

IEEE Network Protocols (ICNP), 2011.


Spamming Botnets: Are we losing the war?

Kokkodis Marios and Faloutsos Michalis.

Conference on Email and Anti-Spam (CEAS), 2009


Resume


Higher Education

2010-2015. NYU Stern School of Business, USA. PhD in Information Systems.
Advisor: Panos Ipeirotis
Committee Members: Arun Sundararajan, Foster Provost.

2008-2010. University of California Riverside, USA. M.Sc. in Computer Science.

2002-2007. National Technical University of Athens, Greece. Ptychion in Electrical and Computer Engineering (5-year program).


Research Interests

Online markets, machine learning, text mining, data science, big data techniques, crowdsourcing, randomized experiments and econometrics.


Professional Employment

07/2015 - present. Assistant Professor of Information Systems at Carroll School of Management, Boston College.

05/2013-08/2013. Research scientist intern at Microsoft Research. Worked on algorithmically augmenting education textbooks.

06/2012-09/2012. Data scientist intern at oDesk. Worked on oDesk’s contractor-client matching algorithm.

06/2011-09/2011. Data scientist intern at oDesk. Worked on matching skills towards a better recommendation system.


Teaching

01/2014 - 05/2014. Dealing with Data: Instructor. Feedback score: 6.4/7.0

01/2014 - 05/2014. Networks Crowds and Markets: Teaching Fellow

01/2013 - 05/2013. Networks Crowds and Markets: Teaching Fellow

09/2012 - 12/2012. Practical Data Science: Teaching Fellow

09/2011 - 12/2011. Information Technology in Business and Society: Teaching Fellow

01/2011 - 05/2011. Datamining for Business Intelligence: Teaching Fellow


Awards

May 2015. NYU Stern Harold W. MacDowell Dissertation Award.

Fall 2014. AAAI HCOMP Doctoral Consortium.

INFORMS Data Mining Best Student Paper Award Competition (runner up).

2014-2015. Lee Sproull Doctoral Fellowship.

2010-2014. New York University Fellowship.

2008-2010. University of California Riverside, Graduate Division fellowship.

2002. 1st place in the Cyprus Biology Olympiad. Represented Cyprus in the International Biology Olympiad (IBO 2002), in Latvia.

2002. 4th place in the Cyprus Physics Olympiad. Represented Cyprus in the International Physics Olympiad (IPHO 2002), in Bali, Indonesia.


Working Papers

Kokkodis Marios, Konstantinos Pelechrinis and Theodoros Lappas. “The Invisible Barrier: The Effect of Promoting Agencies on Sales in Electronic Markets”. (under review)

Kokkodis Marios and Theodoros Lappas. “Disclosing Purchase Information and Review Helpfulness”.

Kokkodis Marios and Ipeirotis G. Panagiotis. “Career Development Paths”. (under review)

Kokkodis Marios, Papadimitriou Panagiotis and Ipeirotis G. Panagiotis. “On hiring Decisions in Online Labor Markets”. (under review)


Journal Publications

Kokkodis Marios and Ipeirotis G. Panagiotis. “Reputation Transferability in Online Publications Labor Markets”. Management Science, 2015.


Conference Publications (refereed)

Kokkodis Marios, Papadimitriou Panagiotis and Ipeirotis G. Panagiotis. “Hiring Behavior Models for Online Labor Markets”. Proceedings of the eighth ACM international conference on Web search and data mining (WSDM). ACM, 2015.

Kokkodis Marios and Ipeirotis G. Panagiotis. “The Utility of Skills in Online Labor Markets”. Proceedings of the International Conference on Information Systems (ICIS), 2014.

Kokkodis Marios, Anitha Kannan, and Krishnaram Kenthapadi. “Assigning Educational Videos at Appropriate Locations in Textbooks”. Proceedings of the International Educational Data Mining Society (EDM), 2014.

Kokkodis Marios, Kannan Anitha, and Krishnaram Kenthapadi. “Assigning Videos to Textbooks at Appropriate Granularity”. Proceedings of the first ACM Learning at Scale (LAS) conference. ACM, 2014.

Kokkodis Marios and Ipeirotis G. Panagiotis. “Have you done anything like that? Predicting user performance using inter-category reputation”. Proceedings of the sixth ACM international conference on Web search and data mining (WSDM). ACM, 2013.

Kokkodis Marios. “Learning from positive and unlabeled amazon reviews: towards identifying trustworthy reviewers”. Proceedings of the 21st international conference companion on World Wide Web (WWW). ACM, 2012.

Kokkodis Marios, Faloutsos Michalis and Markopoulou Athina.“Network-level characteristics of Spamming: An empirical analysis”, IEEE Network Protocols (ICNP), Vancouver, BC, October 2011.

Kokkodis Marios and Faloutsos Michalis.“Spamming Botnets: Are we losing the war?”, CEAS, Mountain View, CA, July 2009.


Refereed Conferences without Proceedings

Kokkodis Marios. "The Effect of Disclosing Purchase Information on Review Helpfulness: Evidence from Amazon.com". Conference on Information Systems and Technology (CIST), 2015.

Kokkodis Marios Papadimitriou Panagiotis, Ipeirtotis, G, Panagiotis. “On Hiring Decisions in Online Labor Markets”. Workshop on Information Systems Economics (WISE), 2014.

Kokkodis Marios. “Online Labor Markets: Reputation Transferability, Career Development Paths and Hiring Decisions”. Doctoral Consortium, AAAI Conference on Human Computation & Crowdsourcing (HCOMP), 2014.

Kokkodis Marios, Papadimitriou Panagiotis, Ipeirtotis, G, Panagiotis. “Who Should I Hire? Maximizing Employer’s Utility in Online Labor Markets”. In 2013 Winter Conference on Business Intelligence.

Kokkodis Marios. “Credibility dimensions in online reviews”. In 2013 Winter Conference on Business Intelligence.

Kokkodis Marios and Ipeirotis G. Panagiotis. “Where are you coming from, stranger? Predicting future performance using inter-category reputation” In 2012 Winter Conference on Business Intelligence.


Invited Talks

“The Effect of Promoting Agencies on Sales in Electronic Markets”. INFORMS 2015

“Disclosing Purchase Information and Review Helpfulness”. INFORMS 2015

“Maximizing Employer’s Utility in Online Labor Markets”. INFORMS 2013

“Reputation Transferability in Online Labor Markets”. INFORMS 2013


Patents

Kokkodis Marios, Kannan Anitha, and Krishnaram Kenthapadi. “Associating content items with document sections”. (application filed).


Service

Web Chair: Conference on Human Computation & Crowdsourcing (HCOMP) 2015

Session Chair: ‘Big Data in Business and Society’, 2014, International Conference on Information Systems (ICIS)

Reviewer: Management Science (INFORMS)

Reviewer: International Conference on Information Systems (ICIS)


Languages

English

Greek