Project: Coffee Price Forecasting
Overview
For my Senior Capstone, I am building a Predictive Model to analyze how Inflation price momvements can specifically impact the coffee supply chain.
The Problem
Coffee prices are volatile and heavily influenced by supply shocks (e.g., frosts in Brazil or production booms in Vietnam). My goal is to determine/ predict a price range of coffee from the price shock of other factors such as coco beans, milk, sugar. Once I have the correct formula for this, I will expand to Fred 50+ years of price data to predict future prices.
"A predictive dashboard that models how different shocks, like a frost in Brazil or a shipping crisis in Vietnam, or a sugar shortage can impact the price of coffee."
Tools
I currently have used 4 tools so far:
- Notepad ++: HTML & CSS Style
- R Studio: Data Cleaning & Model Work + Results
- Excel: EDA & Pivot Tabels
- Python: Dynamic Model
Methodology
I am developing an interactive html dashboard with a python script taking the users inputs and running the model in the background. The model is dynamic and has a set formula and will enter in the users inputs and calculate out answer. Once the model is successfull and formula is set, then I will expand to previous 50+ year dataset and expand to international impacts. The model is trained on 30 years of historical data from:
- USDA Foreign Agricultural Service: Production, exports, and ending stocks.
- FRED (St. Louis Fed): US City Average CPI for Coffee.
- Cecafé & ICO: Brazilian Monthly Exports and Composite daily prices.
Current Status
I'm currently testing the virtual python environment as this is needed for python script to run live on html dashboard. It is a little hard to test as there are some hoops to have to jump through such as working with flask and having to be on campus as my vpn does not work.
Project Timeline
