2021 Green Taxi Trip Data contains records of individual trips made by New York City's green taxis, which are authorized for street hails in boroughs outside Manhattan. The dataset is provided by the City of New York via its open data portal and includes fields for pick-up/drop-off times, locations, distances, and detailed fare breakdowns. It was last updated in December 2023.
Use Cases
- Predict total_amount from trip_distance, tolls_amount, and congestion_surcharge using regression models.
- Analyze temporal patterns in trip frequency using lpep_pickup_datetime and lpep_dropoff_datetime.
- Cluster trips by geographic zones using PULocationID and DOLocationID to identify high-demand areas.
- Classify payment_type (e.g., cash vs. card) based on fare_amount, tip_amount, and trip_type.
- Model passenger_count distribution relative to time of day and RatecodeID.
Strengths
- Contains 20 distinct columns capturing detailed fare components and trip metadata.
- Includes precise temporal data with separate pickup and dropoff datetime columns.
Limitations
- The dataset is limited to a single year (2021), restricting longitudinal trend analysis.
- Sample size and geographic bias are unknown, as row count and exact spatial coverage are not provided.
Provenance
- Source
- data.cityofnewyork.us
- Collection Method
- Generated from trip record submissions made by green taxi Technology Service Providers (TSPs).
- Time Range
- 2021
- Freshness
- Data reflects 2021 trips, with metadata last updated in December 2023.
- Geography
- New York City, primarily boroughs outside Manhattan's central business district where green taxis operate.