Welcome To

Djordje Gligorijevic

ABOUT ME

Hi there, my name is Djordje Gligorijevic (pronounced as JORJ-e GLIG-oh-ree-E-vich), though I also go by George.

I am applied sciences manager at eBay, leading team in eBay’s sponsored search program developing novel machine learning solutions for a variety of both existing and emerging problems including prediction & forecasting, dynamic control, auction mechanisms and A/B testing for search ranking and monetization.

I received PhD in computer science from Temple University, and a B.Sc. in information systems from the University of Belgrade.

For more info checkout the Journal & Conference Publications pages or my CV.

Research Interests

My research interests encompass Machine Learning, Spatial and Temporal Data Mining, Structured Regression, Extreme Multi-Label Classification, Natural Language Processing, Large Language Models, and the Integration of Qualitative Knowledge into predictive models. I specialize in Computational Healthcare & Precision Medicine, Auction Bid Valuation & Landscape Prediction, Search, Ranking, and Recommendation Systems, along with Computational Advertising.

Journal Publications

Title
Year
Authors
Journal
Page
Paper

Importance of social capital for knowledge acquisition – DeepLIFT learning from international development projects

Predicting Actions of Users using Heterogeneous Online Signals

Use of Disease Embedding Technique to Predict the Risk of Progression to End-Stage Renal Disease

Optimizing Clinical Trials Recruitment via Deep Learning

Social Network Analysis for better Understanding of Influenza

The influence of social capital on knowledge management maturity of nonprofit organizations - predictive modelling based on a multilevel analysis

Deeply Supervised Model for Click-Through Rate Prediction in Sponsored Search

Large-Scale Discovery of Disease-Disease and Disease-Gene Associations

* datasets available

Disease Types Discovery from a Large Database of Inpatient Records: A Sepsis Study

Modeling Healthcare Quality via Compact Representations of Electronic Health Records

* datasets available

Conference Publications

Title
Year
Authors
Conference
Page
Paper

Optimization-Based Budget Pacing in eBay Sponsored Search

Practical Budget Pacing Algorithms and Simulation Test Bed for eBay Marketplace Sponsored Search

Extreme Multi-label Classification for Ad Targeting using Factorization Machines

Efficient deep distribution network for bid shading in First-Price Auctions

Prospective Modeling of Users for Online Display Advertising via Deep Time-Aware Model

* datasets available

Bid Shading in The Brave New World of First-Price Auctions

Bid Shading by Auction Clearing Price Prediction and Fast Surplus Maximization Search

Time-Aware User Embeddings as a Service

Time-Aware Prospective Modeling of Users for Online Display Advertising

Decomposition Based Reparameterization for Efficient Estimation of Sparse Gaussian Conditional Random Fields

Spatially Aware Ensemble-Based Learning to Predict Weather-Related Outages in Transmission

Modeling Mobile User Actions for Purchase Recommendations using Deep Memory Networks

Deep Attention Model for Triage of Emergency Department Patients

Modeling Customer Engagement from Partial Observations

Uncertainty Propagation in Long-term Structured Regression on Evolving Networks

* code available

Improving Confidence while Predicting Trends in Temporal Disease Networks

Semi-supervised learning for structured regression on partially observed attributed graphs

Education

Ph.D., Computer and Information Sciences

B.Sc., Information Systems and Technologies

Let's Connect

Follow me on social media