Project Name: Enron Email Analysis Using NLP
This is an unsupervised machine learning project where we are using Natural Language Processing and Time Series methods to explore and analyze Enron emails. We will be using topic modeling and word frequency analysis to identify trends in communication themes over time. For our MVP we are looking at a corpus of 5,575 emails sent by people of interest, as identified by the official congressional report on the role of Enron’s board of directors (https://bit.ly/3Hjz5rI) on the collapse of the company. Our initial hypothesis is that there will be uniquely identifiable trends in email topics over time and that organizations will be able to use our analysis to identify key themes in communication between persons of interest in the early stages of investigating suspicious organizational activity.
I am eager in learning new skills to solve business problem. I am adaptable to new environment and persistent with my daily, short term and long term goal. I don't give up on anything quickly.
It's not about what I can do with data. Its about does my findings have a business value and it aligns with our company's short term and long term goal.
Willing to relocate anywhere but preferred location Belton, Austin, Dallas, San Antonio
Self Motivator, Persistent and Business Goal Oriented
Data Analyst, Data Engineer, Junior Data Scientist