I am a Senior Researcher at Microsoft Research. My research focuses on augmenting data management systems to better support all stages of business analytics, with special emphasis on data-driven predictive and prescriptive analytics, for faster and easier decision making. The main goal of my research is to democratize decision making in a variety of practical applications, across different disciplines and industries.
In my dissertation, I built complete and efficient data management systems able to support a broad class of decision-making problems that can be expressed as integer linear programs (ILP), on both certain and uncertain data. My current and future research aims at enlarging the scope of these systems to even broader classes of problems. Given the complexity and the broad scope of my research endeavors, my work has been largely interdisciplinary, it led to several top-tier publications, spanning also other research areas such as natural language processing, information retrieval, text summarization, AI, and robotics, and has been recognized by several ACM awards.
I obtained my Ph.D. in Computer Science from the University of Massachusetts Amherst, where I collaborated with members of the DREAM Lab. During my Ph.D., I also collaborated with the Human Data (HuDa) Interaction Lab at NYU Abu Dhabi. I received my Bachelor's and Master's degrees in Computer Science from the Computer Science and Engineering Department at the University of Bologna, Italy.
During summer 2017, I interned at Microsoft Research, in the Data Management, Exploration and Mining (DMX) group. During summer 2016, I interned at IBM Watson. During spring 2016, I visited NYU Abu Dhabi, UAE. During summer 2015, I visited the AMPLab at the University of California, Berkeley. During my Master's studies, I visited the Data-Intensive Systems group at Aarhus University, Denmark. During my Bachelor's studies, I interned in the Database Lab at the University of California, Riverside.
VLDB 2020 Best Demonstration Award:
SIGMOD 2020 Technical Paper Presentation:
- SubSumE: A Dataset for Subjective Summary Extraction from Wikipedia Documents
- Solving Markov Decision Processes with Partial State Abstractions
sPaQLTooLs: A Stochastic Package Query Interface for Scalable Constrained Optimization
VLDB 2020 (demo)
SuDocu: Summarizing Documents by Example
VLDB 2020 (demo)
- Stochastic Package Queries in Probabilistic Databases
- Scalable Computation of High-Order Optimization Queries
Package queries: efficient and scalable computation of high-order constraints
VLDBJ 2018 (Special Issue on Best Papers of VDLB 2016)
- A Scalable Execution Engine for Package Queries
- Redistributing Funds across Charitable Crowdfunding Campaigns
- Scalable Package Queries in Relational Database Systems
- Improving Package Recommendations through Query Relaxation
PackageBuilder: From Tuples to Packages
VLDB 2014 (demo)
PackageBuilder: Querying for packages of Tuples
SIGMOD 2014 (poster)
- Metric Spaces for Temporal Information Retrieval
- Recognising and Interpreting Named Temporal Expressions