Luca Pappalardo (PI) is a full-time researcher at the Institute of Information Science and Technologies of the National Research Council of Italy (ISTI-CNR) in Pisa (since 2017). Luca is a member of the KDD Lab – Knowledge Discovery and Data Mining Laboratory, a joint research initiative of the University of Pisa, the Italian National Research Council (CNR), and Scuola Normale Superiore of Pisa. Luca’s research focuses on data science, AI, computational social science and their impact on society, with a particular focus on the (privacy-preserving) analysis of human mobility and the design of mechanistic and AI models for the prediction and generation of human mobility. Luca is also part of SoBigData.eu, the European H2020 Research Infrastructure “Big Data Analytics and Social Mining Ecosystem”, in which he is responsible for coordinating the research that is conducted within the infrastructure. Luca has been a visiting scientist at Barabasi Lab (Center for Complex Network Research) of Northeastern University, Boston, and at the Central European University (CEU) in Budapest, Hungary, and at the Pontifícia Universidade do Rio de Janeiro, Brazil. In 2014, Luca received a grant from Google and the Italian National Statistics Bureau (ISTAT) for the most innovative ideas in using big data sources to study complex economic phenomena.
2 months of visit: 8th May – 8th July 2022
ISTI-CNR (Institute of Information Science and Technologies
– Italian National Research Council)
Inria Saclay – Ile de France
Axe scientifique DigiCosme ComEx, IID
Expected outcomes and impact of the program of work
Predicting mobility-related behavior is an important, but challenging task. On one hand, factors such as one’s routine or preferences for a few favorite locations may help in predicting her mobility. On the other hand, there are several other factors, such as changes in preferences, weather, traffic, or even a person’s friends, that make individual mobility prediction quite challenging. A fundamental approach to study mobility-related behavior is to assess how predictable such behavior is, deriving theoretical limits on the accuracy that a prediction model can achieve given a specific dataset. This approach focuses on the inherent nature and fundamental patterns of human behavior captured in datasets, filtering out factors that depend on the specificities of the prediction method adopted. However, the current state-of-the-art method to estimate predictability in human mobility suffers from two major limitations, notably, low interpretability and hardness to incorporate external factors which are known to help mobility prediction (e.g., contextual information, such as spatiotemporal information).
In this context, the research project described at the “Program of work” intends to make several direct contributions. One outcome is the establishment and consolidation of a thematic and collaboration between the partners to deal with the challenges of investigating and predicting patterns in human behavior from a theoretical (i.e., predictability) and practical (i.e., Markov Chain and ML predictors) point of view. Building on the newly acquired knowledge we intend to develop a novel generalized predictability metric for human mobility that overcomes current metrics limitations by accounting for
spatial, temporal and sequential dimensions in mobility behaviors. As a case of study, a direct outcome will be the leveraging of resulting mobility understanding and its AI-enhanced anticipation in future generation transit systems, optimized to consider transit schedules, individuals mobility preferences and habits, and on demand services. It is worth mentioning accurately predicting human trajectories is relevant to many domains and applications such as targeted advertising, epidemic prevention, or smooth resource and handover management for mobile networks. More generally, by improving knowledge and prediction of user behaviors, the project can enhance the construction of human-aware business models, technological services and applications, and public services.
Finally, a large spectrum of new research opportunities can be fostered by the multidisciplinary nature of the problem. We strongly believe the combined expertise of Luca Pappalardo, Aline C. Viana, and Andrea Araldo as well as their research complementarity will be of great impact to literature, Digicosme, and respective institutions.
Program of work during the visit
Generalized predictability measure for human mobility
accounting for spatial, temporal, and sequential dimensions – GenPM-STD
Program of courses during the visit