Saving Unemployed by Data Science
The Problem (How to estimate survival duration after layoff?):
Many people afraid layoffs. Why? If an individual dose not have enough financial resources, he/she will unable to cover basic living costs after layoff. This project tries to quantify fear by estimating how long an individual can survive after layoff. The longer survival duration, the less to afraid.
The Solution (Using time series to predict survival duration by considering individual location and financial status):
FRED is a plentiful database of U.S. and international economic data maintained by the research department of the Federal Reserve Bank of St. Louis. We prepare an API to extract time series data from FRED with location as query input. Then we can apply time series prediction mechanisms, auto-regressive integrated moving average (ARIMA) model and Exponential Smooth (ES) model, to predict living expanse from previous historical data at given area. Finally, the survival duration after layoff can be determined by an individual financial status after layoff and predicted living expanse at his/her living area.
Project Website
For more details, check out the project's website here.
Important Figures
System Structure
Query Example with Location Query Input
Estimated Survival Duration in Different Cities of USA
