Analysis of Zocdoc NYC

Posted on May 18, 2020

Zocdoc is a doctor’s appointment booking platform which was founded in April of 2007. Zocdoc syncs its platform with the doctor’s appointment software which lets it’s platform show real time appointment information to patients.  Patients can search for doctors by illness, appointment date, city, insurance and more. It uses machine learning techniques to optimize its search and to show the best results. Zocdoc is an amazing platform to find and book appointments and it currently serves more than six million people every month. For this web scraping project, I scraped data for New York City and asked these following research questions:

  • Is there any correlation between the ratings?
  • What are the top languages spoken by doctors?
  • What are the top specialties by gender?
  • How is the distribution of doctors across New York City?
  • Which doctors have the most foot traffic?
  • Which doctors are offering video visits?

I used Selenium to scrape the data which took about 5 hours. The data includes doctor’s name, specialties, gender, language, city, zip code, total reviews, overall ratings, manner ratings, waittime ratings, video visit.

First, I calculated correlation between overall ratings, manner ratings, waittime ratings to find out which 2 variables have the highest correlation. Manner seems to be the most correlated with overall ratings of doctors as shown in the table. Even though there is a positive relationship between these variables, further analysis must be done to prove if there is any causation.

Correlation Coefficients of Ratings

To find out the top languages spoken by doctors, I needed to do some data cleaning. Since most of the doctors spoke multiple languages, I had to separate the languages into new rows to get the total count for each. Below is a pie chart showing the top 5 languages spoken by Zocdoc doctors besides English. I wanted to compare this finding with the top languages spoken in New York City homes to see if the languages are representative. According to, besides English, Spanish, Chinese, Russian, French and Bengali are the top 5 languages of NYC. Even though the first 4 of the languages are in the top 5 list of zocdoc languages, Bengali is spoken by less than 5% of the doctors of Zocdoc. Perhaps, Zocdoc can try to bring in more doctors who speak this language which might increase their patient reach and grow their business. 

To find out what are the top specialties by gender in NYC, I had to seperate the specialties column into new rows, since many of the doctors had more than one specialties. I also renamed some of the specialties because there were more than 200 types and reduced it down to 46 specialties. As shown below with the pie charts for female and male doctors, both gender has 2 common fields which are dentist and general doctor with dentists being the top specialties in both genders. Therapist, OB-GYN and Eye Doctor seems to be the other 3 top specialties in female doctors whereas, Surgeon, Specialties and Internist are other 3 top specialties among male doctors. 

To find the distribution of doctors across NYC, I decided to look at the distributions of top 3 doctors in NYC which are Dentists, Therapists and General Doctors. There are about 123 cities in NYC. Since I can not fit all the city names in one graph I only kept cities with count greater than or equal to 2. Below are 3 bar graphs showing the distributions going from high to low for each plot. As we can see in the graphs, more than two-thirds of the doctors are located in Manhattan compared to the rest of NYC. According to, Queens (2.27 million) and Brooklyn (2.58 million) had more population than Manhattan (1.63) in 2018 but the doctors on Zocdoc platform does not seem to represent the population since it has most of its doctors located in Manhattan. 

I found the numbers on foot traffic with the percentage of reviews for each specialties and created a bar graph of specialties with more than or equal to 5 percent of total reviews. Below is a bar graph showing the result. As we can see, General Doctors have the most reviews at 16% followed by Internists (11.3%), Dermatologist (11%), Dentist(11%), OB-GYN (10.3%), Eye Doctor (6.3%) and Specialists (6%).

Below is a bar graph which plotted the percentage of doctors going from high to low, who are offering video visits. Therapists, General Doctors and Internists seem like the top 3 in this list. Video visit is a new feature that has started to appear in various platforms such as Patientpop and has been very helpful specially in this COVID-19 pandemic. If a patient is looking for a general consultation, I think this is a get feature to take advantage of. You will save a lot of time and you also have the flexibility to see doctors who are very far from you whom you otherwise will not visit.

For future work, I plan on scraping review data and do sentiment analysis. I also want to scrape data on other states and analyze trends among them. 

To find more about this project, follow this link

To find out more about me, follow this link.

About Author


Suborna Nath

Data Scientist with a background in biomedical research, passionate about problem-solving and uncovering actionable insights from data.
View all posts by Suborna Nath >

Related Articles

Leave a Comment

No comments found.

View Posts by Categories

Our Recent Popular Posts

View Posts by Tags

#python #trainwithnycdsa 2019 airbnb Alex Baransky alumni Alumni Interview Alumni Reviews Alumni Spotlight alumni story Alumnus API Application artist aws 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 Bundles California Cancer Research capstone Career Career Day citibike clustering Coding Course Demo Course Report D3.js data Data Analyst data science Data Science Academy Data Science Bootcamp Data science jobs Data Science Reviews Data Scientist Data Scientist Jobs data visualization Deep Learning Demo Day Discount dplyr employer networking feature engineering Finance Financial Data Science Flask gbm Get Hired ggplot2 googleVis Hadoop higgs boson Hiring hiring partner events Hiring Partners Industry Experts Instructor Blog Instructor Interview Job Job Placement Jobs Jon Krohn JP Morgan Chase Kaggle Kickstarter lasso regression Lead Data Scienctist Lead Data Scientist leaflet linear regression Logistic Regression machine learning Maps matplotlib Medical Research Meet the team meetup Networking neural network Neural networks New Courses nlp NYC NYC Data Science nyc data science academy NYC Open Data NYCDSA NYCDSA Alumni Online Online Bootcamp Online Training Open Data painter pandas Part-time Portfolio Development prediction Prework Programming PwC python python machine learning python scrapy python web scraping python webscraping Python Workshop R 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 Selenium sentiment analysis Shiny Shiny Dashboard Spark Special Special Summer Sports statistics streaming Student Interview Student Showcase SVM Switchup Tableau team TensorFlow Testimonial tf-idf Top Data Science Bootcamp twitter visualization web scraping Weekend Course What to expect word cloud word2vec XGBoost yelp