Massimiliano Luca
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Massimiliano Luca has a total of 46 co-authors. Here are the top co-authors by number of shared publications:
- Bruno Lepri
Fondazione Bruno Kessler, Trento, Italy
13 shared publications - Luca Pappalardo
Institute of Information Science and Technologies (ISTI), National Research Council (CNR), Pisa, Italy
5 shared publications Bruno Lepri
Fondazione Bruno Kessler Via Sommarive 18 38123 Povo TN Italy
4 shared publicationsAndra Lutu
Telefónica Research, Madrid, Spain
2 shared publications- Annapaola Marconi
Motivational Digital Systems, Fondazione Bruno Kessler, Trento, Italy
2 shared publications - Antonio Bucchiarone
University of L'Aquila, L'Aquila, Italy
2 shared publications
Latest Publications
- Open Access
- 28 September 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Intelligent Systems and Technology
- Vol. 17 (6) , 1-41
The LLM Wears Prada: Analyzing Gender Bias and Stereotypes through Online Shopping Data
With the wide and cross-domain adoption of Large Language Models (LLMs), it becomes crucial to assess the extent to which the statistical correlations in training data hide subtle and potentially troubling biases. Gender bias in LLMs has been widely investigated from the perspectives of work, hobbies, and emotions typically associated with a specific gender. In this study, we introduce a novel perspective. We investigate whether LLMs can predict an individual’s gender based solely on online shopping histories and whether these predictions are influenced by gender biases and stereotypes. Using a dataset of historical online purchases from users in the United States, we evaluate the ability of five LLMs to predict the buyer’s gender, and we analyze their reasoning and product–gender co-occurrences. Results indicate that while models can infer gender with moderate accuracy, their decisions are often rooted in stereotypical associations between product categories and gender that differ from the actual behaviors of the individuals present in the dataset. Furthermore, explicit instructions to avoid bias reduce the certainty of model predictions, but do not eliminate stereotypical patterns. Our findings highlight the persistent nature of gender biases in LLMs and emphasize the need for robust bias-mitigation strategies as LLMs are currently amplifying the stereotypes analyzed.
- 28 September 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Intelligent Systems and Technology
- Vol. 17 (6) , 1-41
Open AccessThe LLM Wears Prada: Analyzing Gender Bias and Stereotypes through Online Shopping Data
With the wide and cross-domain adoption of Large Language Models (LLMs), it becomes crucial to assess the extent to which the statistical correlations in training data hide subtle and potentially troubling biases. Gender bias in LLMs has been widely investigated from the perspectives of work, hobbies, and emotions typically associated with a specific gender. In this study, we introduce a novel perspective. We investigate whether LLMs can predict an individual’s gender based solely on online shopping histories and whether these predictions are influenced by gender biases and stereotypes. Using a dataset of historical online purchases from users in the United States, we evaluate the ability of five LLMs to predict the buyer’s gender, and we analyze their reasoning and product–gender co-occurrences. Results indicate that while models can infer gender with moderate accuracy, their decisions are often rooted in stereotypical associations between product categories and gender that differ from the actual behaviors of the individuals present in the dataset. Furthermore, explicit instructions to avoid bias reduce the certainty of model predictions, but do not eliminate stereotypical patterns. Our findings highlight the persistent nature of gender biases in LLMs and emphasize the need for robust bias-mitigation strategies as LLMs are currently amplifying the stereotypes analyzed.
- Open Access
- 3 September 2026
- Published by Springer Nature in EPJ Data Science
Multimodal large language models predict urban safety perception but encode non-neutral demographic priors
- 3 September 2026
- Published by Springer Nature in EPJ Data Science
Open AccessMultimodal large language models predict urban safety perception but encode non-neutral demographic priors
- Open Access
Time Series Foundation Models are Flow Predictors
We investigate the effectiveness of time series foundation models (TSFMs) for crowd flow prediction, focusing on Moirai and TimesFM. Evaluated on three real-world mobility datasets-Bike NYC, Taxi Beijing, and Spanish national OD flows-these models are deployed in a strict zero-shot setting, using only the temporal evolution of each OD flow and no explicit spatial information. Moirai and TimesFM outperform both statistical and deep learning baselines, achieving up to 33% lower RMSE, 39% lower MAE and up to 49% higher CPC compared to state-of-the-art competitors. Our results highlight the practical value of TSFMs for accurate, scalable flow prediction, even in scenarios with limited annotated data or missing spatial context.
Open AccessTime Series Foundation Models are Flow Predictors
We investigate the effectiveness of time series foundation models (TSFMs) for crowd flow prediction, focusing on Moirai and TimesFM. Evaluated on three real-world mobility datasets-Bike NYC, Taxi Beijing, and Spanish national OD flows-these models are deployed in a strict zero-shot setting, using only the temporal evolution of each OD flow and no explicit spatial information. Moirai and TimesFM outperform both statistical and deep learning baselines, achieving up to 33% lower RMSE, 39% lower MAE and up to 49% higher CPC compared to state-of-the-art competitors. Our results highlight the practical value of TSFMs for accurate, scalable flow prediction, even in scenarios with limited annotated data or missing spatial context.
- Top Cited PapersOpen Access
- 1 May 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 77456-77467
Large Language Models are Zero-Shot Next Location Predictors
Predicting the locations an individual will visit in the future is crucial for solving many societal issues like disease diffusion and pollution reduction. However, next-location predictors often require a significant amount of individual-level information that may be scarce or unavailable (e.g., in cold-start scenarios). Large Language Models (LLMs) have demonstrated strong generalization and reasoning capabilities while being rich in geographical knowledge, suggesting that they can operate as zero-shot next-location predictors. In our study, we evaluate over 15 LLMs on three real-world mobility datasets and find that they achieve accuracies up to 36.2%, representing a relative improvement of almost 640% compared to traditional models designed for human mobility. We further assess data contamination risks and explore the potential for using LLMs as text-based explainers for next-location predictions. Our results indicate that, irrespective of model size, LLMs can both predict and justify their decisions effectively.
- 1 May 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 77456-77467
Top Cited PapersOpen AccessLarge Language Models are Zero-Shot Next Location Predictors
Predicting the locations an individual will visit in the future is crucial for solving many societal issues like disease diffusion and pollution reduction. However, next-location predictors often require a significant amount of individual-level information that may be scarce or unavailable (e.g., in cold-start scenarios). Large Language Models (LLMs) have demonstrated strong generalization and reasoning capabilities while being rich in geographical knowledge, suggesting that they can operate as zero-shot next-location predictors. In our study, we evaluate over 15 LLMs on three real-world mobility datasets and find that they achieve accuracies up to 36.2%, representing a relative improvement of almost 640% compared to traditional models designed for human mobility. We further assess data contamination risks and explore the potential for using LLMs as text-based explainers for next-location predictions. Our results indicate that, irrespective of model size, LLMs can both predict and justify their decisions effectively.
- Open Access
- 23 April 2025
- Published by National Academy of Sciences in Proceedings of the National Academy of Sciences
- Vol. 122 (17)
Mixing individual and collective behaviors to predict out-of-routine mobility
Predicting human displacements is crucial for addressing various societal challenges, including urban design, traffic congestion, epidemic management, and migration dynamics. While predictive models like deep learning and Markov models offer insights into individual mobility, they often struggle with out-of-routine behaviors. Our study introduces an approach that dynamically integrates individual and collective mobility behaviors, leveraging collective intelligence to enhance prediction accuracy. Evaluating the model on millions of privacy-preserving trajectories across five US cities, we demonstrate its superior performance in predicting out-of-routine mobility, surpassing even advanced deep learning methods. The spatial analysis highlights the model’s effectiveness near urban areas with a high density of points of interest, where collective behaviors strongly influence mobility. During disruptive events like the COVID-19 pandemic, our model retains predictive capabilities, unlike individual-based models. By bridging the gap between individual and collective behaviors, our approach offers transparent and accurate predictions, which are crucial for addressing contemporary mobility challenges.
- 23 April 2025
- Published by National Academy of Sciences in Proceedings of the National Academy of Sciences
- Vol. 122 (17)
Open AccessMixing individual and collective behaviors to predict out-of-routine mobility
Predicting human displacements is crucial for addressing various societal challenges, including urban design, traffic congestion, epidemic management, and migration dynamics. While predictive models like deep learning and Markov models offer insights into individual mobility, they often struggle with out-of-routine behaviors. Our study introduces an approach that dynamically integrates individual and collective mobility behaviors, leveraging collective intelligence to enhance prediction accuracy. Evaluating the model on millions of privacy-preserving trajectories across five US cities, we demonstrate its superior performance in predicting out-of-routine mobility, surpassing even advanced deep learning methods. The spatial analysis highlights the model’s effectiveness near urban areas with a high density of points of interest, where collective behaviors strongly influence mobility. During disruptive events like the COVID-19 pandemic, our model retains predictive capabilities, unlike individual-based models. By bridging the gap between individual and collective behaviors, our approach offers transparent and accurate predictions, which are crucial for addressing contemporary mobility challenges.
- 20 March 2025
- Published by Springer Nature in Nature Cities
- Vol. 2 (3) , 265
Unfolding cities from rooftops
- 20 March 2025
- Published by Springer Nature in Nature Cities
- Vol. 2 (3) , 265
Unfolding cities from rooftops
- Open Access
Urban Safety Perception Through the Lens of Large Multimodal Models: A Persona-based Approach
Understanding how urban environments are perceived in terms of safety is crucial for urban planning and policymaking. Traditional methods like surveys are limited by high cost, required time, and scalability issues. To overcome these challenges, this study introduces Large Multimodal Models (LMMs), specifically Llava 1.6 7B, as a novel approach to assess safety perceptions of urban spaces using street-view images. In addition, the research investigated how this task is affected by different socio-demographic perspectives, simulated by the model through Persona-based prompts. Without additional fine-tuning, the model achieved an average F1-score of 59.21% in classifying urban scenarios as safe or unsafe, identifying three key drivers of perceived unsafety: isolation, physical decay, and urban infrastructural challenges. Moreover, incorporating Persona-based prompts revealed significant variations in safety perceptions across the socio-demographic groups of age, gender, and nationality. Elder and female Personas consistently perceive higher levels of unsafety than younger or male Personas. Similarly, nationality-specific differences were evident in the proportion of unsafe classifications ranging from 19.71% in Singapore to 40.15% in Botswana. Notably, the model's default configuration aligned most closely with a middle-aged, male Persona. These findings highlight the potential of LMMs as a scalable and cost-effective alternative to traditional methods for urban safety perceptions. While the sensitivity of these models to socio-demographic factors underscores the need for thoughtful deployment, their ability to provide nuanced perspectives makes them a promising tool for AI-driven urban planning.
Open AccessUrban Safety Perception Through the Lens of Large Multimodal Models: A Persona-based Approach
Understanding how urban environments are perceived in terms of safety is crucial for urban planning and policymaking. Traditional methods like surveys are limited by high cost, required time, and scalability issues. To overcome these challenges, this study introduces Large Multimodal Models (LMMs), specifically Llava 1.6 7B, as a novel approach to assess safety perceptions of urban spaces using street-view images. In addition, the research investigated how this task is affected by different socio-demographic perspectives, simulated by the model through Persona-based prompts. Without additional fine-tuning, the model achieved an average F1-score of 59.21% in classifying urban scenarios as safe or unsafe, identifying three key drivers of perceived unsafety: isolation, physical decay, and urban infrastructural challenges. Moreover, incorporating Persona-based prompts revealed significant variations in safety perceptions across the socio-demographic groups of age, gender, and nationality. Elder and female Personas consistently perceive higher levels of unsafety than younger or male Personas. Similarly, nationality-specific differences were evident in the proportion of unsafe classifications ranging from 19.71% in Singapore to 40.15% in Botswana. Notably, the model's default configuration aligned most closely with a middle-aged, male Persona. These findings highlight the potential of LMMs as a scalable and cost-effective alternative to traditional methods for urban safety perceptions. While the sensitivity of these models to socio-demographic factors underscores the need for thoughtful deployment, their ability to provide nuanced perspectives makes them a promising tool for AI-driven urban planning.
- Open Access
Towards Civic Digital Twins: Co-Design the Citizen-Centric Future of Bologna
We introduce Civic Digital Twin (CDT), an evolution of Urban Digital Twins designed to support a citizen-centric transformative approach to urban planning and governance. CDT is being developed in the scope of the Bologna Digital Twin initiative, launched one year ago by the city of Bologna, to fulfill the city's political and strategic goal of adopting innovative digital tools to support decision-making and civic engagement. The CDT, in addition to its capability of sensing the city through spatial, temporal, and social data, must be able to model and simulate social dynamics in a city: the behavior, attitude, and preference of citizens and collectives and how they impact city life and transform transformation processes. Another distinctive feature of CDT is that it must be able to engage citizens (individuals, collectives, and organized civil society) and other civic stakeholders (utilities, economic actors, third sector) interested in co-designing the future of the city. In this paper, we discuss the motivations that led to the definition of the CDT, define its modeling aspects and key research challenges, and illustrate its intended use with two use cases in urban mobility and urban development.
Open AccessTowards Civic Digital Twins: Co-Design the Citizen-Centric Future of Bologna
We introduce Civic Digital Twin (CDT), an evolution of Urban Digital Twins designed to support a citizen-centric transformative approach to urban planning and governance. CDT is being developed in the scope of the Bologna Digital Twin initiative, launched one year ago by the city of Bologna, to fulfill the city's political and strategic goal of adopting innovative digital tools to support decision-making and civic engagement. The CDT, in addition to its capability of sensing the city through spatial, temporal, and social data, must be able to model and simulate social dynamics in a city: the behavior, attitude, and preference of citizens and collectives and how they impact city life and transform transformation processes. Another distinctive feature of CDT is that it must be able to engage citizens (individuals, collectives, and organized civil society) and other civic stakeholders (utilities, economic actors, third sector) interested in co-designing the future of the city. In this paper, we discuss the motivations that led to the definition of the CDT, define its modeling aspects and key research challenges, and illustrate its intended use with two use cases in urban mobility and urban development.
- Open Access
- 26 February 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 12, 32693-32705
Autonomous and Human-Driven Vehicles Interacting in a Roundabout: A Quantitative and Qualitative Evaluation
Optimizing traffic dynamics in an evolving transportation landscape is crucial, particularly in scenarios where autonomous vehicles (AVs) with varying levels of autonomy coexist with human-driven cars. While optimizing Reinforcement Learning (RL) policies for such scenarios is becoming more and more common, little has been said about realistic evaluations of such trained policies. This paper presents an evaluation of the effects of AVs penetration among human drivers in a roundabout scenario, considering both quantitative and qualitative aspects. In particular, we learn a policy to minimize traffic jams (i.e., minimize the time to cross the scenario) and to minimize pollution in a roundabout in Milan, Italy. Through empirical analysis, we demonstrate that the presence of AVs can reduce time and pollution levels. Furthermore, we qualitatively evaluate the learned policy using a cutting-edge cockpit to assess its performance in near-real-world conditions. To gauge the practicality and acceptability of the policy, we conduct evaluations with human participants using the simulator, focusing on a range of metrics like traffic smoothness and safety perception. In general, our findings show that human-driven vehicles benefit from optimizing AVs dynamics. Also, participants in the study highlight that the scenario with 80% AVs is perceived as safer than the scenario with 20%. The same result is obtained for traffic smoothness perception.
- 26 February 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 12, 32693-32705
Open AccessAutonomous and Human-Driven Vehicles Interacting in a Roundabout: A Quantitative and Qualitative Evaluation
Optimizing traffic dynamics in an evolving transportation landscape is crucial, particularly in scenarios where autonomous vehicles (AVs) with varying levels of autonomy coexist with human-driven cars. While optimizing Reinforcement Learning (RL) policies for such scenarios is becoming more and more common, little has been said about realistic evaluations of such trained policies. This paper presents an evaluation of the effects of AVs penetration among human drivers in a roundabout scenario, considering both quantitative and qualitative aspects. In particular, we learn a policy to minimize traffic jams (i.e., minimize the time to cross the scenario) and to minimize pollution in a roundabout in Milan, Italy. Through empirical analysis, we demonstrate that the presence of AVs can reduce time and pollution levels. Furthermore, we qualitatively evaluate the learned policy using a cutting-edge cockpit to assess its performance in near-real-world conditions. To gauge the practicality and acceptability of the policy, we conduct evaluations with human participants using the simulator, focusing on a range of metrics like traffic smoothness and safety perception. In general, our findings show that human-driven vehicles benefit from optimizing AVs dynamics. Also, participants in the study highlight that the scenario with 80% AVs is perceived as safer than the scenario with 20%. The same result is obtained for traffic smoothness perception.
- 6 September 2023
- Published by Springer Nature in Machine Learning
- Vol. 112 (11) , 4597-4634
Trajectory test-train overlap in next-location prediction datasets
- 6 September 2023
- Published by Springer Nature in Machine Learning
- Vol. 112 (11) , 4597-4634
Trajectory test-train overlap in next-location prediction datasets