Dima Karamshuk, PhD
Research Scientist at Facebook

karamshuk [at] fb [dot] com
[Linkedin] [Twitter] [Slideshare] [Google Scholar]

About Me

I am a research scientist on the Facebook Core Data Science team, working on understanding and modelling large-scale user behaviour. Before joining Facebook I worked as a data scientist at Skyscanner and as a researcher at King’s College London. My research interests lie on the intersection between systems design, data analysis and machine learning.



  • A Cost-Driven Approach to Caching-as-a-Service in Cloud-Based 5G Mobile Networks. Seyed Ehsan Ghoreishi, Dmytro Karamshuk, Vasilis Friderikos, Nishanth Sastry, Mischa Dohler, Hamid Aghvami. IEEE Transactions on Mobile Computing, 2019. [Link]
  • 2018

  • Learning Cheap and Novel Flight Itineraries. Dmytro Karamshuk, David Matthews. European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases - ECMLPKDD, 2018. [PDF] [Slides]
  • Consume Local: Towards Carbon Free Content Delivery. Aravindh Raman, Dmytro Karamshuk, Nishanth Sastry, Andrew Secker, Jigna Chandaria. International Conference on Distributed Computing Systems - ICDCS, 2018. [PDF]
  • 2017

  • Wearing many (social) hats: How different are your different social network personae? Changtao Zhong, Hau-wen Chang, Dmytro Karamshuk, Dongwon Lee, Nishanth Sastry. International AAAI Conference On Web and Social Media - ICWSM, 2017. [PDF]
  • Bridging big data and qualitative methods in the social sciences: A case study of Twitter responses to high profile deaths by suicide. Dmytro Karamshuk, Frances Shaw, Julie Brownlie, Nishanth Sastry. Elsevier journal on Online Social Networks and Media - OSNEM, 2017. [PDF]
  • Survey on Peer-assisted Content Delivery Networks. Nasreen Anjum, Dmytro Karamshuk, Mohammad Shikh-Bahaei, Nishanth Sastry. Elsevier journal on Computer Networks - CompNet, 2017. [PDF]
  • 2016

  • Identifying Partisan Slant in News Articles and Twitter during Political Crises. Dmytro Karamshuk, Tetyana Lokot, Oleksandr Pryymak, Nishanth Sastry. International Conference on Social Informatics - SocInfo, 2016. [PDF] [Slides]
  • Take-away TV: Recharging Work Commutes with Greedy and Predictive Preloading of TV Content. D. Karamshuk, N. Sastry, M. al-Bassam, A. Secker, J. Chandaria. IEEE Journal On Selected Areas In Communications - J-SAC [Top-6 in Computer Networks, H5 – 66], 2016. [PDF] [Slides]
  • Provisioning Cost-Effective Mobile Video Caching. E. Ghoreishi, V. Friderikos, D. Karamshuk, N. Sastry, and H. Aghvami. IEEE International Conference on Communications - ICC [Top-18 in Computer Networks, H5 – 46], Kuala Lumpur, 2016. [PDF]
  • Towards transdisciplinary collaboration between computer and social scientists: Initial experiences and reflections. D. Karamshuk, M. Pupavac, F. Shaw, J. Brownlie, V. Pupavac, N. Sastry. Book chapter in "Social Network Analysis: Interdisciplinary Approaches and Case Studies", Taylor & Francis Group, 2016.
  • 2015

  • Predicting Pinterest: Automating a distributed human computation. C. Zhong, D. Karamshuk, N. Sastry, World Wide Web Conference - WWW [AR – 14%, Top-1 in Information Systems, H5 – 75], Florence, 2015. [PDF]
  • ISP-friendly Peer-assisted On-demand Streaming of Long Duration Content in BBC iPlayer. D. Karamshuk, N. Sastry, A. Secker, J. Chandaria, IEEE INFOCOM [AR - 19%, Top-3 in Computer Networks, H5 – 78], Hong Kong, 2015. [PDF] [Slides]
  • On Factors Affecting the Usage and Adoption of a Nation-wide TV Streaming Service. D. Karamshuk, N. Sastry, A. Secker, J. Chandaria, IEEE INFOCOM [AR - 19%, Top-3 in Computer Networks, H5 – 78], Hong Kong, 2015. [PDF] [Slides]  [Press Coverage]
  • SCORE:Exploiting global broadcasts to create offline personal channels for on-demand access. G. Nencioni, N. Sastry, G. Tyson, V. Badrinarayanan, D. Karamshuk, J. Chandaria, J. Crowcroft, IEEE/ACM Transactions on Networking [Top-10 in Computer Networks, H5 – 58], 2015. [PDF]
  • Identifying Geographic Clusters: A Network Approach. R. Catini, D. Karamshuk, O. Penner, M. Riccaboni, Elsevier Journal on Research Policy [Top-3 in Social Sciences, H5 – 77], 2015. [PDF]
  • Prior to 2015

  • SPoT: Representing the Social, Spatial, and Temporal Dimensions of Human Mobility with a Unifying Framework. D. Karamshuk, C. Boldrini, M. Conti, and A. Passarella, Elsevier Journal on Pervasive and Mobile Computing - PMC [H5 – 35], , 11, 2014. [PDF]
  • Geo-Spotting: Mining Online Location-based Services for Optimal Retail Store Placement. D. Karamshuk, A. Noulas, S. Scellato, V. Nicosia, C. Mascolo, ACM SIGKDD Conference on Knowledge Discovery and Data Mining - KDD [AR – 17%, Top-2 in Data Mining, H5 - 64], Chicago, 2013. [PDF] [Slides] [Press Coverage]
  • An arrival based framework for human mobility modeling. D. Karamshuk, C. Boldrini, M. Conti, and A. Passarella, IEEE International Symposium on a World of Wireless Mobile and Multimedia Networks - WoWMoM [AR - 18%, H5 – 22], San Francisco, 2012. [PDF]
  • Human mobility models for opportunistic networks. D. Karamshuk, C. Boldrini, M. Conti, and A. Passarella, IEEE Communications Magazine [Top-1 in Computer Networks, H5 – 90], 2011. [PDF]
  • PhD Thesis

  • Modeling and Understanding the Role of Human Mobility in the Cyber-Physical World, IMT Institute for Advanced Studies, Lucca, 2013. [PDF]

My presentations on SlideShare

Press Coverage

  • Major study links low internet usage to slow broadband. [BBC]
  • Foursquare check-ins tell stores where to set up shop. [New Scientist]
  • Who are YOU on social media? Study shows we have very different personas on Facebook, Twitter, LinkedIn and Instagram. [Daily Mail]
  • Social media users adopt completely different 'personas' on Facebook, Twitter, LinkedIn and Instagram, study shows. [Mirror]
  • Social Media & Machine Learning tell Stores where to locate: Dmytro Karamshuk Interview. [Data Science Weekly]
  • Scotland affected by worst broadband speeds in UK. [The Scotsman]
  • UK Study Claims Slow Broadband Speed Fosters Low Internet Use. [ISP Review]
  • UK let down by slow broadband. [Advanced Television]
  • Regions with worst broadband speeds 'use modern services the least'. [USwitch]
  • Harnessing the Matrix or how to build an intelligent city. [TedXKyiv]
  • How Foursquare Helps to Plan Cities. [KPIshnik.com.ua]
  • Why Fast Food Restaurants need big data. [Computerra.ru]

Visualizing Swarming Behavior in BBC iPlayer