Luca Quadrifoglio
Luca Quadrifoglio has a total of 13 co-authors. Here are the top co-authors by number of shared publications:
Cheng Zhang
Zachry Department of Civil and Environmental Engineering, Texas A&M University, TX 77843, Bryan, USA
1 shared publication- Cheng Zhang
Zachry Department of Civil and Environmental Engineering, Texas A&M University, College Station, USA
1 shared publication Dahye Lee
Zachry Department of Civil and Environmental Engineering, Texas A&M University, College Station, TX, USA
1 shared publicationDario Ballarano
Zachry Department of Civil and Environmental Engineering, Texas A&M University, TX 77843, Bryan, USA
1 shared publication- Ernesto Cipriani
Roma Tre University
1 shared publication - Gaetano Fusco
Department of Civil, Environmental and Constructional Engineering, Sapienza University of Rome, Via Eudossiana, 18, 00184 Rome, Italy
1 shared publication
Latest Publications
- 15 September 2025
- Published by Springer Nature in Transportation
- Vol. 53 (7) , 5069-5092
The critical role of the value of time in peer-to-peer ridesharing models
- 15 September 2025
- Published by Springer Nature in Transportation
- Vol. 53 (7) , 5069-5092
The critical role of the value of time in peer-to-peer ridesharing models
- Open Access
- 29 November 2024
- Published by Polish Mineral Engineering Society in Inżynieria Mineralna
- Vol. 1 (2)
Forecasting Ride-Hailing Demand in Urban Areas: A Deep Ensemble and Time Series Clustering Approach
This paper investigates the increasingly important task of forecasting demand for ride-hailing services, which have significantly disrupted traditional transportation models. Notably, the study concentrates on New York City's Yellow Cab service, which despite the surge in popularity of app-based services, continues to serve a substantial number of commuters. The study highlights the necessity of accurate demand prediction for efficient resource allocation, reduced wait times and improved user satisfaction. Traditional forecasting methods like Historical Average, Exponential Weighted Moving Averaes, ARIMA etc., are examined, alongside the more recent machine learning and data mining techniques, CNN-LSTM and XGBoost. A novel approach, utilizing an ensemble of machine learning models – XGBoost and Convolutional Neural Network – LSTM along with creative feature engineering is proposed for real-time demand forecasting across numerous locations. Furthermore, the study also tries to understand the application of time-series clustering methods and their effectiveness in grouping similar time-series together and extracting clustering features to improve the performance of the model. Additionally, the study observes the ineffectiveness of generalized model to forecast demand in low-demand reasons and presents possible research direction for solving the issue. This study contributes to the growing literature on demand forecasting in the ride-hailing industry and provides insights into the use of time-series clustering for the same.
- 29 November 2024
- Published by Polish Mineral Engineering Society in Inżynieria Mineralna
- Vol. 1 (2)
Open AccessForecasting Ride-Hailing Demand in Urban Areas: A Deep Ensemble and Time Series Clustering Approach
This paper investigates the increasingly important task of forecasting demand for ride-hailing services, which have significantly disrupted traditional transportation models. Notably, the study concentrates on New York City's Yellow Cab service, which despite the surge in popularity of app-based services, continues to serve a substantial number of commuters. The study highlights the necessity of accurate demand prediction for efficient resource allocation, reduced wait times and improved user satisfaction. Traditional forecasting methods like Historical Average, Exponential Weighted Moving Averaes, ARIMA etc., are examined, alongside the more recent machine learning and data mining techniques, CNN-LSTM and XGBoost. A novel approach, utilizing an ensemble of machine learning models – XGBoost and Convolutional Neural Network – LSTM along with creative feature engineering is proposed for real-time demand forecasting across numerous locations. Furthermore, the study also tries to understand the application of time-series clustering methods and their effectiveness in grouping similar time-series together and extracting clustering features to improve the performance of the model. Additionally, the study observes the ineffectiveness of generalized model to forecast demand in low-demand reasons and presents possible research direction for solving the issue. This study contributes to the growing literature on demand forecasting in the ride-hailing industry and provides insights into the use of time-series clustering for the same.
- 1 January 2023
- Published by AIP Publishing in AIP Conference Proceedings
- Vol. 2928 (1)
A pairing ridesharing model to reduce congestion in large urban areas
Modern world is facing difficult times with regard to newly developed concepts like livability and sustainability. Increasingly growing urban areas are dealing with an escalation of traffic congestion and all its consequences in terms of overall delay experienced by travelers. Ridesharing is intuitively a practical solution to improve the congestion issues in our modern cities. The largely unused capacity of the private vehicles would be utilized in place of other vehicles to satisfy the mobility needs of individual passengers. A large-scale proper implementation of it would be one of the effective methods to satisfy the mobility need of travelers and reduce congestion effects. This research utilizes the available large dataset of taxi data from the City of Chicago. Taxi demand is analyzed and spatial-temporal distributions are developed to perform simulation analyses intended to investigate the effects on the transportation network assuming a percentage of the demand is willing to be served in a ridesharing mode. Service level constraints are considered to ensure acceptable quality for travelers in terms of added journey time and waiting time. We are considering the pairing model, consisting of assuming only pairs of compatible passengers are combined. The goal is to maximize the total mileage saving and therefore reduce the total driving time on the road network. The main finding of this study includes quantification of the mileage saving as a function of: 1) The participation of the passengers in the ridesharing mode; 2) The service level guaranteed to participating customers, in terms of maximum waiting time and additional riding time. The findings provide convincing tools and detailed information for planners and policy makers to consider incentives for the transformation of traditional taxi services to ridesharing service, improving traffic congestion conditions.
- 1 January 2023
- Published by AIP Publishing in AIP Conference Proceedings
- Vol. 2928 (1)
A pairing ridesharing model to reduce congestion in large urban areas
Modern world is facing difficult times with regard to newly developed concepts like livability and sustainability. Increasingly growing urban areas are dealing with an escalation of traffic congestion and all its consequences in terms of overall delay experienced by travelers. Ridesharing is intuitively a practical solution to improve the congestion issues in our modern cities. The largely unused capacity of the private vehicles would be utilized in place of other vehicles to satisfy the mobility needs of individual passengers. A large-scale proper implementation of it would be one of the effective methods to satisfy the mobility need of travelers and reduce congestion effects. This research utilizes the available large dataset of taxi data from the City of Chicago. Taxi demand is analyzed and spatial-temporal distributions are developed to perform simulation analyses intended to investigate the effects on the transportation network assuming a percentage of the demand is willing to be served in a ridesharing mode. Service level constraints are considered to ensure acceptable quality for travelers in terms of added journey time and waiting time. We are considering the pairing model, consisting of assuming only pairs of compatible passengers are combined. The goal is to maximize the total mileage saving and therefore reduce the total driving time on the road network. The main finding of this study includes quantification of the mileage saving as a function of: 1) The participation of the passengers in the ridesharing mode; 2) The service level guaranteed to participating customers, in terms of maximum waiting time and additional riding time. The findings provide convincing tools and detailed information for planners and policy makers to consider incentives for the transformation of traditional taxi services to ridesharing service, improving traffic congestion conditions.
- 29 August 2022
- Published by Taylor & Francis in Transportation Letters
- Vol. 15 (8) , 969-979
The ridesharing problem without predetermined drivers and riders: formulation and heuristic
We consider a ridesharing service in which no driver and rider’s roles are pre-determined, but left to decide by the system to further reduce costs compared to the typical version with preassigned roles. Travelers are motivated to participate in the service by saving individual transportation costs and accept its rules. We first formally define it as a generalized ridesharing optimization problem (RSP), propose its transformation into a single-depot multiple traveling salesman problem with pickup and delivery constraints (SDMTSP-PD) and provide its mixed-integer program (MIP) formulation. We then develop a polynomial-time solution method based on optimal pair matching among participants, improved by a construction insertion-based heuristic to obtain approximate solutions to the SDMTSP-PD. Experiments show that this approach could solve the problem very fast and provide near-optimal solutions and that the proposed RSP model provides substantial system-wide travel cost saving (25%+) and vehicle-trip saving (50%) compared to the non-ridesharing system and perform better than companion services with preassigned roles (P-RSP).
- 29 August 2022
- Published by Taylor & Francis in Transportation Letters
- Vol. 15 (8) , 969-979
The ridesharing problem without predetermined drivers and riders: formulation and heuristic
We consider a ridesharing service in which no driver and rider’s roles are pre-determined, but left to decide by the system to further reduce costs compared to the typical version with preassigned roles. Travelers are motivated to participate in the service by saving individual transportation costs and accept its rules. We first formally define it as a generalized ridesharing optimization problem (RSP), propose its transformation into a single-depot multiple traveling salesman problem with pickup and delivery constraints (SDMTSP-PD) and provide its mixed-integer program (MIP) formulation. We then develop a polynomial-time solution method based on optimal pair matching among participants, improved by a construction insertion-based heuristic to obtain approximate solutions to the SDMTSP-PD. Experiments show that this approach could solve the problem very fast and provide near-optimal solutions and that the proposed RSP model provides substantial system-wide travel cost saving (25%+) and vehicle-trip saving (50%) compared to the non-ridesharing system and perform better than companion services with preassigned roles (P-RSP).
- 30 October 2018
- Published by Taylor & Francis in Transportation Planning and Technology
- Vol. 42 (1) , 84-97
Transit network design for small-medium size cities
This paper proposes a novel heuristic to solve the network design problem for public transport in small-medium size cities. Such cities can be defined as those with a diameter of a few kilometers with up to a few hundred thousand residents. These urban centers present a specific spatial configuration affecting the land use and mobility system. Transportation demand is widespread in origin and concentrated in a small number of attraction points close to each other. This particular structure of demand (‘many-to-few’) suggests the need for specific methodologies for the design of a transit system at a network level. In this paper, such design methodologies are defined in terms of models and solution procedures and tested on a selected case study. The solution methods show promising results. The key variables of the model are the routes and their frequencies. The constraints of the problem affect the overall demand to be served, the quality of the proposed service (transfer, load factors) and the definition of routes.
- 30 October 2018
- Published by Taylor & Francis in Transportation Planning and Technology
- Vol. 42 (1) , 84-97
Transit network design for small-medium size cities
This paper proposes a novel heuristic to solve the network design problem for public transport in small-medium size cities. Such cities can be defined as those with a diameter of a few kilometers with up to a few hundred thousand residents. These urban centers present a specific spatial configuration affecting the land use and mobility system. Transportation demand is widespread in origin and concentrated in a small number of attraction points close to each other. This particular structure of demand (‘many-to-few’) suggests the need for specific methodologies for the design of a transit system at a network level. In this paper, such design methodologies are defined in terms of models and solution procedures and tested on a selected case study. The solution methods show promising results. The key variables of the model are the routes and their frequencies. The constraints of the problem affect the overall demand to be served, the quality of the proposed service (transfer, load factors) and the definition of routes.
- 1 February 2011
- Published by Springer Nature in Public Transport
- Vol. 3 (1) , 89-104
2-Vehicle zone optimal design for feeder transit services
- 1 February 2011
- Published by Springer Nature in Public Transport
- Vol. 3 (1) , 89-104
2-Vehicle zone optimal design for feeder transit services