PREDICTING THE PRICE OF COTTON USING RNN AND LSTM

The covid-19 has resulted in the volatile fluctuation of the commodities prices such as the price of
cotton and causes a disruption in the supply chain of cotton. This research is aimed to utilize the
machine learning algorithm to try and predict the future price of cotton by using the historical price
of cotton provided by investing.com. Prediction of the cotton price will enable companies to hedge
their position in contract for difference market to minimize the effect of volatile price fluctuation
and help to stabilize the supply chain of cotton. The research will be conducted through four stages
of machine learning development methodology consisting of data gathering, data processing,
model fitting, and performance analysis. Data will be gathered by importing the historical prices
of cotton from investing.com into a csv file. The data will then be processed to eliminate the unused
columns and to fill in any void cells. The data will then be separated into training set and testing
set and will be feed to the machine learning algorithm to find the pattern and try to do prediction.
The accuracy of each machine learning algorithm will be recorded and analyze to come up with
the best model for the dataset. As of now, the data gathering, and data processing stages has been
done and the research shall continue with the model fitting and performance analysis