Data Analysis of COVID-19 and NYC Taxis

Posted on Apr 16, 2022

The skills the authors demonstrated here can be learned through taking Data Science with Machine Learning bootcamp with NYC Data Science Academy.

data

Introduction:


With the onset of the pandemic in 2020 many industries experienced sever setbacks, the for hire industry was not the exception. Within this industry it was reported that for hire vehicles (FHV's) experienced an 84% reduction in demand during March 2020 with only 26% of drivers still on the road by April of that year [1]. For the daring FHV's that decided to continue working their earnings had declined by ~26% based on data [1].

data

From the above figure we can see that in 2020 the number of reported trips in April has severely declined as compared to previous years. We can also see that there's a steady increase in trips until the end of 2020 with the increase continuing in 2021.

The below box plot shows that median number of trips reported in 2021 is higher than in 2016 however we are still no where near pre-pandemic levels which reported ~170k in 2019.

data

With this background in mind we now see that the FHV industry has not yet completely recovered from the COVID pandemic and perhaps one factor of this recovery is due to a lag in TLC driver application approvals.

Goal:


Its a known fact that various industries related to the FHV industry suffered major backups during the pandemic. The TLC depends highly on the DMV in order to schedule drivers test and written exams, however the DMV also experienced high levels of saturation of work that seem to be lasting until today [2].

The goal of this study is to understand how the pandemic has effected the ability of the TLC to complete new driver applications using data. The goal is to recommend actions for hiring more personnel based on relevant statistics that show how much lag there is.

Data Overview:


All the data used in the present analysis was taken from NYC Open Data . The major data sets were:

  • TLC New Driver Application Status: Rows: 7212 ; Columns: 12. Contains historical data of driver applicants grouped into three main categories:
    • Completed: TLC driver license approved
    • Needed: Needs one or more requirements prior to granting license
    • N/A: Not applicable.

*NOTE: An extra dataset was used and merged with the above dataset since the above dataset only had values going back to 2020. This data set can be found here and contains values going back to 2016.

  • FHV Base Aggregate Report: Rows: 41.4k ; Columns: 9. Contains data of monthly trips completed by NYC taxi base stations. This was used to understand the decline in taxi usage historically.

Data Analysis:


Having identified a clear correlation between demand and the covid pandemic (see introduction) we not delve into how this impacted the new TLC driver applications.

data

The above bar chart shows that historically the total number of applications which have completed the driver exam for a new TLC license has been declining concurrently with the total number of "Needed" (aka Incomplete). The driver exam was choosen as a significant figure of merit (FOM) for this study since it was observed to be the most impacted part of the TLC application process due to the inability to socialize during the pandemic.

In 2021 we have completed nearly 4x the driver exams as compared to 2020, however, we also an uptick in the needed category.

data

The above line plot shows a more descriptive statistic. Here we plot the percentage of Completed, Needed and Not Applicable TLC driver applications as a function of the total applications present any given year. We can see that there was a clear decline in 2020, however, in 2021 both the Completed as well as the Needed percentages are comparable to the highest pre-pandemic year in 2018. Although this shows that we have clearly made significant efforts to recover in 2021, the data from the 1st quarter of 2022 shows that for the first time there a more Needed applications than there are completed, suggesting a large potential backlog for 2022.

data

Diving deeper into the data, we plot the percent applications per month. historically we can see that February is indeed a month were applications pile up and more personnel is needed. This coincides with the fact that the 1st quarter data for 2022 shows a large backlog as well.

Conclusion


The TLC is clearly suffering from the pandemic effects. Efforts have clearly been made to catch up the new driver applications that were lagging from 2020 as the numbers were greatly improved in 2021, however these efforts need to continue since in 2022 there are allready more incomplete applications overall than complete.

It is recommended that more personnel should be added for the 2022 calendar year to continue the efforts demonstrated in 2021.

Overall, a quarterly hiring trend can also  be implemented  in the future since it was observed that the 1st quarters of every year suffer from a large amount of incomplete applications. This hiring trend could help sustain a steady completion number of applications.

Future Work


Although we were able to demonstrate the need for additional hiring in 2022, this was merely a descriptive view. Gathering data on number of personnel as a function of time can enable us to give a more quantitative answer to how many people need to be hired.

Although the pandemic was one of the largest factor that affected the TLC driver applications, other emerging can also be studied such as the hike in gas prices in 2022. Other potential factors could be the amount of drivers deciding to drive outside of NYC (where no special TLC license is needed).

Thank you for reading through my post, and comments or suggestions are very welcome. Linked-In

References:

[1] 2020, "CCOVID-19 Impact on the NYC For-Hire Industry", Report.

[2] "COVID-19 DMV Delays and Their Impact", Online source.

About Author

BRCC

Trained Electrical Engineer by day and data scientist in training by night. For my day job I work with large sets of electrical data which I try to untangle and understand any deviations then subsequently correlate them to...
View all posts by BRCC >

Related Articles

Leave a Comment

No comments found.

View Posts by Categories


Our Recent Popular Posts


View Posts by Tags

#python #trainwithnycdsa 2019 2020 Revenue 3-points agriculture air quality airbnb airline alcohol Alex Baransky algorithm alumni Alumni Interview Alumni Reviews Alumni Spotlight alumni story Alumnus ames dataset ames housing dataset apartment rent API Application artist aws bank loans beautiful soup Best Bootcamp Best Data Science 2019 Best Data Science Bootcamp Best Data Science Bootcamp 2020 Best Ranked Big Data Book Launch Book-Signing bootcamp Bootcamp Alumni Bootcamp Prep boston safety Bundles cake recipe California Cancer Research capstone car price Career Career Day citibike classic cars classpass clustering Coding Course Demo Course Report covid 19 credit credit card crime frequency crops D3.js data data analysis Data Analyst data analytics data for tripadvisor reviews data science Data Science Academy Data Science Bootcamp Data science jobs Data Science Reviews Data Scientist Data Scientist Jobs data visualization database Deep Learning Demo Day Discount disney dplyr drug data e-commerce economy employee employee burnout employer networking environment feature engineering Finance Financial Data Science fitness studio Flask flight delay gbm Get Hired ggplot2 googleVis H20 Hadoop hallmark holiday movie happiness healthcare frauds higgs boson Hiring hiring partner events Hiring Partners hotels housing housing data housing predictions housing price hy-vee Income Industry Experts Injuries Instructor Blog Instructor Interview insurance italki Job Job Placement Jobs Jon Krohn JP Morgan Chase Kaggle Kickstarter las vegas airport lasso regression Lead Data Scienctist Lead Data Scientist leaflet league linear regression Logistic Regression machine learning Maps market matplotlib Medical Research Meet the team meetup methal health miami beach movie music Napoli NBA netflix Networking neural network Neural networks New Courses NHL nlp NYC NYC Data Science nyc data science academy NYC Open Data nyc property NYCDSA NYCDSA Alumni Online Online Bootcamp Online Training Open Data painter pandas Part-time performance phoenix pollutants Portfolio Development precision measurement prediction Prework Programming public safety PwC python Python Data Analysis python machine learning python scrapy python web scraping python webscraping Python Workshop R R Data Analysis R language R Programming R Shiny r studio R Visualization R Workshop R-bloggers random forest Ranking recommendation recommendation system regression Remote remote data science bootcamp Scrapy scrapy visualization seaborn seafood type Selenium sentiment analysis sentiment classification Shiny Shiny Dashboard Spark Special Special Summer Sports statistics streaming Student Interview Student Showcase SVM Switchup Tableau teachers team team performance TensorFlow Testimonial tf-idf Top Data Science Bootcamp Top manufacturing companies Transfers tweets twitter videos visualization wallstreet wallstreetbets web scraping Weekend Course What to expect whiskey whiskeyadvocate wildfire word cloud word2vec XGBoost yelp youtube trending ZORI