vivekd2001 / uber-data-analysis

The popular ride sharing app is not behind when it comes to using and integrating ML and deep learning in their applications. It handles billions of rides every year helping commutters to travel at any hour. Because it has a vast reach to its customers it requires excellent customer service support to solve customer issues at the earliest. The project aims to improve the effectiveness of customer support with deep learning techniques. Uber has a dataset of millions of pick up to analyze the customer rides and visualize to find insights and further improve customer experience.

Analysis of Uber's Ridership Data for NYC.

Early in 2017, the NYC Taxi and Limousine Commission (TLC) released a dataset about Uber's ridership between September 2014 and August 2015. The data contains features distinct from those in the set previously released and throughly explored by FiveThirtyEight and the Kaggle community. Check the Jupyter Notebook in this repository to see the contents of the data.

This project aims to:

• visualize Uber's ridership growth in NYC during the period
• characterize the demand based on identified patterns in the time series
• estimate the value of the NYC market for Uber, and its revenue growth
• other insights about the usage of the service
• attempt to predict the demand's growth beyond 2015 [IN PROGRESS]

Publication

The analysis and visualizations produced in the Jupyter Notebook provide support for the story to be presented in the project's page.

Required Packages

The code is written in a Jupyter Notebook with a Python 2.7 kernel, and in addition it requires the following packages:

• Numpy (version: 1.11.2)
• Pandas (version: 0.19.2)
• Matplotlib (version: 1.5.3)
• Seaborn (version: 0.6.0)