US Soybean Market Forecasting Using Statistics & Machine Learning Techniques

Presenter Information/ Coauthors Information

Zhuoning Li, Minnesota State University, MankatoFollow

Presentation Type

Poster

Student

Yes

Track

Finance/Insurance Application

Abstract

The agricultural product stock market is very stochastic and difficult to predict. The market is especially affected due to different political and economic policies. This year, the soybean trading market has been affected the most due to the trade war between the U.S. and China. According to USDA, 17% of the U.S. agriculture produce exports to China and 62% of those products were soybeans. Thus, the soybean market has a remarkable change from previous years. In this study, Long-Short Term Memory (LSTM), Time Series Regression model and GARCH model are explored to analyze the soybean market. Google trend and other factors are evaluated as important indicators to the market.

Start Date

2-11-2020 1:00 PM

This document is currently not available here.

Share

COinS
 
Feb 11th, 1:00 PM

US Soybean Market Forecasting Using Statistics & Machine Learning Techniques

Volstorff A

The agricultural product stock market is very stochastic and difficult to predict. The market is especially affected due to different political and economic policies. This year, the soybean trading market has been affected the most due to the trade war between the U.S. and China. According to USDA, 17% of the U.S. agriculture produce exports to China and 62% of those products were soybeans. Thus, the soybean market has a remarkable change from previous years. In this study, Long-Short Term Memory (LSTM), Time Series Regression model and GARCH model are explored to analyze the soybean market. Google trend and other factors are evaluated as important indicators to the market.