Building Business Intelligence Reports for the City of Chicago

Protect Communities and Businesses

1. Overview
In this project, the City of Chicago wants to build web-based dashboard, data lake and microservices that will be used by business analysts and data scientists to create different business intelligence reports for the city of Chicago that will be utilized in strategic planning and industrial and neighborhood infrastructure investments. The city of Chicago publishes and updates its datasets on its data portal server (https://data.cityofchicago.org/ ) in 16 categories. The 3 categories that will be used in creating the business intelligence reports are: Transportation, Buildings, and Health & Human Services.

 

2. Protect Communities and Businesses
Requirement 1: The business intelligence reports are geared toward tracking and forecasting events that have direct or indirect impacts on
businesses and neighborhoods in different zip codes within the city of Chicago. The business intelligence reports will be used to send alerts to taxi drivers about the state of COVID-19 in the different zip codes in order to avoid taxi drivers to be the super spreaders in the different zip codes andneighborhoods. For this report, taxi trips and daily COVID-19 datasets for the city of Chicago will be used.

Requirement 2: There are two major airports within the city of Chicago: O’Hare and Midway. And we are interested to track trips from these airports to the different zip codes and the reported COVID-19 positive test cases. The city of Chicago is interested to monitor the traffic of the taxi trips from these airports to the different neighborhoods and zip codes

 

Requirement 3: The city of Chicago has created the COVID-19 Community Vulnerability Index (CCVI) (https://data.cityofchicago.org/Health-HumanServices/Chicago-COVID-19-Community-Vulnerability-Index-CCV/xhc6-88s9 ) to identify communities that have been disproportionately affected by COVID-19 and are vulnerable to barriers to COVID-19 vaccine uptake. The city of Chicago is interested to track the number of taxi trips from/to the neighborhoods that have CCVI Category with value HIGH 

 

3. Invest in Communities and Offer Incentives for Businesses
Requirement 4: For streetscaping investment and planning, the city of Chicago is interested to forecast daily, weekly, and monthly traffic patterns utilizing the taxi trips for the different zip codes.

 

Requirement 5: For industrial and neighborhood infrastructure investment, the city of Chicago is interested to invest in top 5 neighborhoods with highest unemployment rate and poverty rate and waive the fees for building permits in those neighborhoods in order to encourage businesses to develop and invest in those neighborhoods. Both, building permits and unemployment, datasets will be used in this report. 

Invest in Communities and Offer Incentives for Businesses

 

Requirement 6: According to a report published by Crain’s Chicago
Business (https://www.chicagobusiness.com/private-intelligence/industrialmarket-crazy-right-now), The “little guys”, small businesses, have trouble competing with the big players like Amazon and Walmart for warehouse spaces. To help small business, a new program has been piloted with the name Illinois Small Business Emergency Loan Fund Delta to offer small businesses low interest loans of up to $250,000 for those applicants with PERMIT_TYPE of PERMIT - NEW CONSTRUCTION in the zip code that has the lowest number of PERMIT - NEW CONSTRUCTION applications and PER CAPITA INCOME is less than 30,000 for the planned construction site. Both, building permits and unemployment, datasets will be used in this report. 

 

4. Data Lake
The following data sources are utilized to construct the data lake that will be used in in the research and development of this project requirements and deliverables:
Transportation
Taxi trips are reported to the City of Chicago in its role as a regulatory agency. The dataset is available for download from the following
URL: (https://data.cityofchicago.org/Transportation/Taxi-Trips/wrvzpsew). The dataset for the trips reported by the Transportation Network Providers (also called rideshare companies) is available for download from the following URL:
(https://data.cityofchicago.org/Transportation/TransportationNetwork-Providers-Trips/m6dm-c72p )

 

Buildings
Permits issued by the Department of Buildings in the City of Chicago. The dataset is available for download from the following URL:

(https://www.chicago.gov/city/en/depts/bldgs/dataset/building_pe rmits.html ).

 

Health and Human Services
For all datasets related to COVID-19,see the following URL:(https://data.cityofchicago.org/browse?limitTo=datasets&sortBy=alpha&tags=covid-19 ).

 

5. Analysis
Data Sources and Collection: After you read this document, review the available and relevant datasets from the City of Chicago data portal

Infrastructure and Technology Stack: The entire technology stack needed to construct the application is available:
1. Use Databricks, Redis or Postgres to create data lake.
2. Go language for building microservices. Download Go from the following URL: ( https://golang.org/dl/ )
3. Docker/Container/Kubernetes for deployment of microservices. Download Docker from the following URL: https://www.docker.com/get-started
4. Python packages for time-series forecasting and geospatial queries.
Geopy (https://geopy.readthedocs.io/en/stable/ )
Arcgis ( http://www.arcgis.com )
Google Maps ( https://github.com/googlemaps/googlemaps-services-python )
Tensorflow/Keras LSTM
(https://www.tensorflow.org/api_docs/python/tf/keras/layers/LSTM )
Facebook/Prophet ( https://facebook.github.io/prophet/ )

 

Forecasting and Strategic Planning: If you live in the City of Chicago, highly likely you have heard from the residents at some point that the city has two seasons: winter season and construction season. To better help in resource allocation, scheduling, and planning for streetscaping projects, the City of Chicago is interested to forecast the volume of traffic using the taxi trips as a proxy. The taxi trip data set will be used to forecast the daily, weekly, and monthly taxi trips for every zip code and neighborhood. The City of Chicago is also interested to forecast COVID-19 alerts (Low, Medium, High) on daily/weekly basis to the residents of the different neighborhoods considering the counts of the taxi trips and COVID-19 positive test cases.