Back To Projects

Predicting International Commodity Prices, Production, and Land Usage Towards Reducing Agricultural Emissions

Sahir G.

Our long-term goal for this research project was to analyze food insecurity and determine if we could predict the emissions and pricing of different food commodities.


Our long-term goal for this research project was to analyze food insecurity and determine if we could predict the emissions and pricing of different food commodities. Towards this goal, we needed to understand the changes in food production, land use, efficiency, and pricing of these commodities in a sample of different countries. Given the rampant food insecurity heavily influenced by climate change, aiding in reducing the impacts of climate change could be a crucial step towards alleviating food insecurity. Our approach to answering this question was to first gather and analyze data and then use an univariate ARIMA model for time series to further develop our hypothesis and figure out if it was possible to predict future trends. Despite not including external factors like world conflicts, inflations, weather, and trade, the univariate ARIMA is able to predict the prices, production, and efficiency well on some commodities for some countries. Our major conclusions were that our research could be used to make cursory predictions for future values of the food prices and agricultural emissions.

Explore More!

Sahir G.
Landon Butler
PhD Candidate at Berkeley, UPenn CS Master's

Related Projects

Predicting the Price of New York City Airbnbs

How can one predict the price of a New York City Airbnb? We are trying to create a machine learning model that can predict the price of a NYC Airbnb given some factors with high accuracy.
Bobby B.
Mentored by Tomer Arnon
Predicting State-Wide Cotton Yield using Geospatial Data

The focus of this study was to use Geospatial Linear Regression to predict cotton yield.
Gregory G.
Mentored by Ribhav Gupta
workspace_premium
Predicting Climate Change Using an Autoregressive Long Short-Term Memory Model

This study aims to create a baseline machine learning model that utilizes an Autoregressive Recurrent Neural network with a Long Short term memory implementation for the purpose of predicting climate.
Seokhyun C.
Mentored by Victoria Lloyd