cv
General Information
| Full Name | Francesco Guerra |
| Date of Birth | 21st May 1973 |
| Languages | Italian, English, French |
| Affiliation | Department of Engineering "Enzo Ferrari", University of Modena and Reggio Emilia, Italy |
| Office | MO-27-01-034, DIEF, via Vivarelli 12, 41125 Modena, Italy |
Education
-
2004 PhD in Information Engineering
University of Modena and Reggio Emilia, Italy -
2000 M.Sc. in Information Engineering
University of Modena and Reggio Emilia, Italy -
1992 Diploma di Maturita Classica
Liceo Classico "L. A. Muratori", Modena, Italy
Academic Positions
-
2022 - present Full Professor in Information Engineering
University of Modena and Reggio Emilia, Italy - Teaching Software Engineering and Big Data Analysis.
-
2019 Visiting Professor
University of Rijeka, Croatia -
2015 - 2022 Associate Professor in Information Engineering
University of Modena and Reggio Emilia, Italy -
2005 - 2015 Assistant Professor in Information Engineering
University of Modena and Reggio Emilia, Italy
Institutional Roles
-
2022 - present President of the Bachelor's and Master's Degree Course Councils in Computer Engineering
Department of Engineering "Enzo Ferrari", University of Modena and Reggio Emilia, Italy -
2024 - 2025 Rector's Delegate for ICT
University of Modena and Reggio Emilia, Italy -
2021 - 2023 Coordinator of the Computer Engineering and Science Curriculum, ICT Doctoral School
University of Modena and Reggio Emilia, Italy -
2022 - 2024 Visiting Reviewer for AI Theses
University of Malta
Research Profile
- Trustworthy data-centric AI systems connecting models, data, evidence and explanations.
- Scalable data management and data integration methods for heterogeneous, structured, semi-structured and textual data.
- Machine learning and deep learning techniques for entity resolution, entity matching and explainable data integration.
- NLP and LLM systems for fact-checking, evidence grounding, source attribution, table understanding and decision support.
- Explainable, auditable and reproducible AI pipelines for textual evidence, tables, financial signals, time series and structured records.
Academic Interests
-
Data Integration and Explainable Entity Matching
- Entity matching, entity resolution, record linkage and data cleaning over heterogeneous sources
- Machine learning and deep learning techniques for entity matching
- Explainable entity matching with landmark-based, evidence-based and cluster-based explanations
- Analysis of BERT-based and transformer-based models for entity matching
- Data quality, deduplication and interpretable data integration pipelines
-
Scalable Data Management and Structured Data Analytics
- Scalable techniques for managing, integrating and analysing large structured and semi-structured datasets
- Discovery and summarization of structured data
- Application of NLP and machine learning techniques to structured data
- Integration of textual, tabular and relational evidence in data-intensive pipelines
-
Evidence-grounded NLP and LLMs
- Claim verification and fact-checking over textual, tabular and structured evidence
- Evidence retrieval, source attribution and evidence-level explanations
- RAG and LLM pipelines whose outputs can be inspected, audited and validated by domain experts
- Table QA and Multi-table QA over complex reports and semi-structured sources
- Automatic textual and tabular data analysis
-
Explainable and Auditable AI
- Post-hoc explanations for black-box machine learning models
- Evidence attribution, feature contribution analysis and model-agnostic diagnostics
- Counterfactual explanations for interpretability, recourse and fairness auditing
- Explainable decision-support systems for high-impact domains
-
Semantic Robustness and Red-teaming of Textual Models
- Adversarial testing of NLP models and LLM-based systems
- Universal triggers and semantic-preserving perturbations
- Robustness auditing of fact-checking, RAG and language-based AI pipelines
- Bias diagnosis and vulnerability analysis in textual models
-
Interpretable Time-series Analysis
- Interpretable clustering of multivariate time series
- Novelty and anomaly detection for system health monitoring
- Forecasting of irregularly sampled multivariate time series
- Self-supervised learning and decomposition-based methods for time-series forecasting
-
Benchmarking and Reproducible Evaluation
- Controlled benchmarks for evaluating LLMs on complex evidence
- Evaluation protocols for textual, tabular, semi-structured and financial data
- Synthetic and reproducible benchmarks for comparing AI pipelines
- Stress testing of models under noise, layout variation, missing data and heterogeneous evidence
-
Fairness, Auditability and Responsible AI
- Fairness-aware machine learning and fair classification
- Scalable mitigation of fairness harms
- Auditability of model behaviour across groups and decision settings
- Transparent trade-offs between accuracy, fairness and operational constraints
-
Financial AI and Decision Support
- Reproducible benchmarking for stock market prediction and portfolio allocation
- Integration of heterogeneous financial signals, including prices, macroeconomic indicators, relations and news
- Evaluation of classification, regression and ranking models for financial prediction
- Portfolio-oriented evaluation and decision-support workflows
-
Controllable LLM Systems for Education and Expert Workflows
- LLM systems guided by explicit phases, interaction moves and assessment criteria
- Intelligent tutoring systems and reading comprehension support
- Expert-guided workflows for education, training, compliance and decision support
-
Keyword Search on Structured Data
- Keyword search techniques for relational and multi-table databases
- Semantic keyword search over structured data sources
- Search and exploration of structured datasets
-
Semantic Web and Ontology Integration
- Ontology alignment and integration
- Semantic data integration
- Knowledge-oriented data management
Teaching
-
Current teaching
- Software Engineering
- Big Data Analysis
-
Main teaching areas
- Big data management and analytics
- Text analytics and natural language processing
- Data integration and data management
- Software engineering
Selected Projects
-
2023 - present PANACEA
PRIN 2022 - AI-based cybersecurity, anomaly detection, intrusion response and explainable decision support.
- DTALab contributes expertise on explainable AI, anomaly interpretation, evidence-aware analysis and trustworthy decision-support pipelines.
-
2024 - present RESIST0
PR FESR Emilia-Romagna - Digital twins, production resilience, ESG indicators, ESG-washing detection and decision support.
- DTALab contributes methods for data analysis, explainable AI, ESG indicators and evidence-aware decision-support workflows.
-
2013 - 2017 KEYSTONE COST Action - Semantic Keyword Search on Structured Data Sources
COST Action IC1302 - Coordinator of the European COST Action on semantic keyword search over structured data sources.
-
2017 - 2019 Re-search Alps
INEA/CEF/ICT/A2016/1296967 - Research data integration and information systems.
Online Profiles
| Institutional page | https://unimore.unifind.cineca.it/get/person/090294 |
| DBLP | https://dblp.org/pid/g/FrancescoGuerra.html |
| Personal website | https://fguerra73.github.io/ |