NYC Real Estate Analytics - Manhattan 2017

Fatima Hamdan
Posted on Feb 5, 2018



'When it comes to real estate business, choosing the 'real deal' is the hardest step!'

Investors search for  properties that have higher tendency to be sold with better price. The more deals they have, the more money they earn. However, it is not that simple! Having the wrong deal in buying properties means losing millions of dollars. So prior to buying a property, there should be deep analysis about the property itself, the previous sales, the previous prices, the location etc.  A lot of factors help in having the real deal!

The following application helps investors in making their decision by analyzing previous sales transactions. It provides the user some computed analysis results with statistical insights and user interactive analysis features. For the time being, this project shows all the property sales that occurred in Manhattan for year 2017.

Application Link:

Note: The application still needs some enhancements and updates. 

Data Set


The data is mainly collected for 36 different locations through 17,464 sales transactions.
It provides the following about each transaction: Neighborhood, Building Class Category, Tax Class at Present, Block, Lot, Easement, Building Class at Present, Address, Zip Code, Residential Units, Commercial Units, Total Units, Land Square Feet, Gross Square Feet, Year Built, Building Class at Time of Sale, Sales Price, Sale Date.

From an investor's point of view, this data set provides the investor all the information needed to analyze previous sales. He/She will get answers for
the following questions:
1. What is the best location in Manhattan to invest in? (whether because it has the highest sales rate or the highest sale price).
2.What is the best time of the year to invest? (depending on the sale prices changes during the year)
3. What location do people prefer for residential units as well as for commercial units?
4. Where are the old buildings located? Are people still buying apartments or houses in an old building?
A lot of questions can be answered from this data set.

The NYC Real Estate Analysis Application


Statistical Insights

The statistical insights tab answers the user two questions:

  • When is the best time to invest in Manhattan?
  • Where is the best location to invest?

The four graphs are based on the following:

  • The average price of each month

This graph shows that the best time of the year for investment in Manhattan -based on price- is December! As for the minimum average of sale price, it is  261,156 $, and the maximum average of sale price is 5,411,472 $.

  • The average number of sales of each month

In this graph, we can see that the best time of the year for investment in Manhattan-based on number of sales- is August!

Why there are two different months for the best investment?! and which month is better?

The answer is in the hand of the investor.. it depends on whether  he/she wants to earn more money or sell more properties.

  • The average price of each location

The variation in this graph shows that the best place to invest in is MidTown CBD! this is based on the sale price.

  • The average number of sales of each location

As for this graph,it  shows people's interests for some locations over the others since there are more sales in those locations. The highest number of sales is in Manhattan Valley and the second highest is Midtown CBD (which is the same place that has the highest average price as well).

The Map

The map shows the 36 locations in Manhattan with average sale price and number of sales for each location. The map is user interactive as well.

User Interactive Analysis

The interactive analysis feature provides the user the option to analyse the information himself/herself. The user can modify 5 inputs which are: the location,the type of building, show only old buildings feature, show only new buildings feature, and the price. After that, he can visualize the result in a table or graph.

For the following specific demo example: The user’s inputs are: ANY LOCATION, ANY TYPE OF BUILDING, old and new buildings, and  price rage  200,000,000 to 600,000,000 $

  1. The inputs features

  1. Visualizing the Table: the data will appear in a table filtered by the user's inputs values

  1. Visualizing the Graphs: These interactive graphs show hows the sale price vary over time and locations.


Future Enhancements


Live People Searches

Since people's interest in buying or renting a property varies with time, it is important to keep track with what people are up to! nothing is better that analyzing google trends to visualize people's searches on buying in a certain location. This tab will show the investor on daily basis and even lively what locations people are interested in the most.

Contact information:

For more information about the application, contact me on [email protected]




About Author

Fatima Hamdan

Fatima Hamdan

Fatima got her bachelor's degree in Computer Engineering from Lebanese American University. She was chosen as one of the 24 women in engineering change makers from all over the world to attend the Women in Engineering conference in...
View all posts by Fatima Hamdan >

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