Analyzing and Modeling a City’s Spatiotemporal Taxi Supply and Demand: A Case Study for Munich

Jager, Benedikt; Wittmann, Michael; Lienkamp, Markus

doi:10.18178/jtle.4.2.147-153

Cited by 11 publications

(9 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A study on the Asian market revealed spatio-temporal patterns to help taxi drivers spend less time for cruising [1]. Another example of demand prediction introduced based on city district scale in Munich, revealed timedvariant demand prediction for individual districts [2]. Mineta National Transit Consortium presented a report with results of taxi demand across time and space using GPS data from taxis [3].…”

Section: Literature Reviewmentioning

confidence: 99%

Predicting taxi unmet trip demand

Ahmed,

Kalinin,

Famili

et al. 2024

ACE

View full text Add to dashboard Cite

The purpose of this project is to predict the number of taxi trip that goes unmet in NYC by using available trip data generated by Taxi Cabs. The expected outcome from this project is to identify the areas in NYC that experiences unmet demand and to identify socio-economic features that impact trip demand. The project was broken down into 2 phases. To account for daily trip trends the study is broken down in 7 periods on Monday to Saturday and 4 periods on weekends. In the rst phase 3 approaches were developed to identify census tract where the demand of taxi is not met. The rst approach was to compare the monthly total pickup and drop-of counts. The second approach identied the underserved census tracts by nding those with the least number of vacant taxis within a given time duration. In the third approach, the rate of change Uber pickup was compared with the rate of change of combined pick up of all taxi services over a 6 months period. The nal output was: 358 unmet trip demand CT that had pick-ups to drop-offs ratio lower than 25%, Less than 2 vacant taxi a minute and a Uber growth rate more than 4%. These areas were in North-east Queens, South Brooklyn and North of the Bronx. In Phase II, the socio-economic features were ranked to understand their inuence on taxi demand. Out of the 11 selected features the top 5 features were neighborhoods with high number of offices and employees, residential areas, income and rent. Using the 11 features as predictors and pick-up from CT with satisfactory as target variable a model was developed to predict demand for underserved areas. The model predicted overall 92,000 trips per day goes unmet in NYC which is 4.2% of the total current daily trips.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Predicting taxi unmet trip demand

Ahmed,

Kalinin,

Famili

et al. 2024

ACE

View full text Add to dashboard Cite

show abstract

“…A fleet of 550 taxis served ≈10 M customer trips between 2015 and 2020. The data are being continuously retrieved from the fleet management interface, which is usually used for dispatching by the local taxi agency [30]. The data are directly provided by the dispatching agency with full information about trip start, trip end, and driven route.…”

Section: Taxi Datamentioning

confidence: 99%

The Influence of Public Transport Delays on Mobility on Demand Services

2021

Self Cite

View full text Add to dashboard Cite

Demand for different modes of transportation clearly interacts. If public transit is delayed or out of service, customers might use mobility on demand (MoD), including taxi and carsharing for their trip, or discard the trip altogether, including a first and last mile that might otherwise be covered by MoD. For operators of taxi and carsharing services, as well as dispatching agencies, understanding increasing demand, and changing demand patterns due to outages and delays is important, as a more precise demand prediction allows for them to more profitably operate. For public authorities, it is paramount to understand this interaction when regulating transportation services. We investigate the interaction between public transit delays and demand for carsharing and taxi, as measured by the fraction of demand variance that can be explained by delays and the changing OD-patterns. A descriptive analysis of the public transit data set yields that delays and MoD demand both highly depend on the weekday and time of day, as well as the location within the city, and that delays in the city and in consecutive time intervals are correlated. Thus, demand variations must by corrected for these external influences. We find that demand for taxi and carsharing increases if the delay of public transit increases and this effect is stronger for taxi. Delays can explain at least 4.1% (carsharing) and 18.8% (taxi) of the demand variance, which is a good result when considering that other influencing factors, such as time of day or weather exert stronger influences. Further, planned public transit outages significantly change OD-patterns of taxi and carsharing.

show abstract

“…The recent popularity of e-hailing taxi services has generated substantial interest in developing efficient taxi demandsupply prediction algorithms [5], [6], [7], [8]. In the past, taxi demand-supply prediction was mainly formulated as a classical time-series forecasting problem.…”

Section: A Related Workmentioning

confidence: 99%

Grids versus Graphs: Partitioning Space for Improved Taxi Demand-Supply Forecasts

Davis¹,

Raina²,

Jagannathan³

2019

Preprint

View full text Add to dashboard Cite

Accurate taxi demand-supply forecasting is a challenging application of ITS (Intelligent Transportation Systems), due to the complex spatial and temporal patterns. We investigate the impact of different spatial partitioning techniques on the prediction performance of an LSTM (Long Short-Term Memory) network, in the context of taxi demand-supply forecasting. We consider two tessellation schemes: (i) the variable-sized Voronoi tessellation, and (ii) the fixed-sized Geohash tessellation. While the widely employed ConvLSTM (Convolutional LSTM) can model fixed-sized Geohash partitions, the standard convolutional filters cannot be applied on the variable-sized Voronoi partitions. To explore the Voronoi tessellation scheme, we propose the use of GraphLSTM (Graph-based LSTM), by representing the Voronoi spatial partitions as nodes on an arbitrarily structured graph. The GraphLSTM offers competitive performance against Con-vLSTM, at lower computational complexity, across three realworld large-scale taxi demand-supply data sets, with different performance metrics. To ensure superior performance across diverse settings, a HEDGE based ensemble learning algorithm is applied over the ConvLSTM and the GraphLSTM networks.

show abstract

Analyzing and Modeling a City’s Spatiotemporal Taxi Supply and Demand: A Case Study for Munich

Cited by 11 publications

References 19 publications

Predicting taxi unmet trip demand

Predicting taxi unmet trip demand

The Influence of Public Transport Delays on Mobility on Demand Services

Grids versus Graphs: Partitioning Space for Improved Taxi Demand-Supply Forecasts

Contact Info

Product

Resources

About