Maven Taxi Challenge
Analyze millions of taxi trip records to help NYC dispatchers improve capacity planning.
Oct 12, 2021
Start date
Nov 7, 2021
Deadline
Free Annual Membership
Grand Prize
Live Finalist Voting Video
Challenge Objective
For the Maven Taxi Challenge, you’ll play the role of an analyst for the NYC Taxi & Limousine Commission.
Your task is to help the Lead Dispatcher understand the data, and build an interactive dashboard that gives him the key information he needs to manage his fleet.
Step 1: Clean and prep the data for analysis
Remove trips sent via store and forward
Only keep street-hailed trips paid by card or cash with a standard rate
Remove trips with dates before 2017 or after 2020
Remove trips with pickups/drop-offs into unknown zones
Trips with no passengers = 1 passenger
If a pickup date/time is AFTER the drop-off, swap them
Remove trips longer than a day
Remove trips with distance & fare amount = 0
Trips with fare, taxes, and surcharges as negative should be positive
For trips with a fare amount but no distance, calculate it: (Fare-2.5)/2.5
For trips with a distance but no fare amount, calulate it: 2.5+(distancex2.5)
Step 2: Build a weekly dashboard to answer the following questions
What's the average number of trips?
What's the average fare per trip?
What's the average distance traveled per trip?
How will trip volume change, relative to last week?
Which days of the week and times of the day will be busiest?
What will be the most popular pick-up and drop-off locations?
About the Data Set
Trip records from all green taxis in NYC in from 2017 to 2020. Records include fields capturing pick-up and drop-off dates/times, pick-up and drop-off locations, trip distances, itemized fares, rate types, payment types, and driver-reported passenger counts.
Official Terms & Conditions
For this challenge, Maven Analytics will give away up to 3 Annual Pro individual subscriptions (including awards for "First-time Entrant", "Fan Favorite" and "Challenge Winner").
After the 1 year period, subscriptions will renew at full price unless canceled (cancel at any time).
A "First-time entrant" is a Maven Analytics user who has published a project to Showcase assigned to a Maven Challenge for the first time.
To be eligible, you must publish your project and submit your entry prior to the challenge deadline
The "Fan Favorite" winner will be determined based on project likes on the Maven Showcase page exactly 1 week after the challenge deadline, and other finalists and winners will be selected by the Maven Analytics team via live vote, and announced from the Maven Analytics LinkedIn account.
No purchase is necessary to enter.
Missed the challenge deadline? No problem! All Data Playground datasets are free and available for download anytime – feel free to dig in!
