Inspiration
We love MTA while hating it at the same time. There are a lot of complaints that we can never rely on MTA. Therefore, we want to predict the demand for subways to help the MTA better allocate its resources.
What it does
- visualize and understand variables that influence the demand for MTA
- build a linear regression model for prediction
- use predictions and optimize the resources
How we built it
- Python, Jupyter Notebook, Tableau
- Geopandas, Matplotlib, statsmodels, Pandas
Challenges we ran into
- Data cleaning & manipulation: huge amounts of data, wrong data types when reading into dateframes, null values
- Could not integrate two datasets
- Not enough time to implement our ideas
Accomplishments that we're proud of
We can analyze data on MTA activity and draw insight from those data to give recommendations to improve the services of MTA.
What we learned
We can enhance our critical thinking process through the lessons learned from this event. Looking forward, if we encounter similar opportunities, we can embark on future projects and delve even deeper into research and data analysis.
What's next for MTA, MTA
- Web scraping and text analysis to understand potential problems with MTA
- Collect additional information such as weather that might influence the demand and fit the data into the model
- Build an app to MTA monitor the demand
Log in or sign up for Devpost to join the conversation.