NORMA eResearch @NCI Library

Short term forecasting of Agro-products pricing using Multivariate time series analysis

Kumar, Raghav Krishna (2020) Short term forecasting of Agro-products pricing using Multivariate time series analysis. Masters thesis, Dublin, National College of Ireland.

[thumbnail of Master of Science]
PDF (Master of Science)
Download (705kB) | Preview
[thumbnail of Configuration manual]
PDF (Configuration manual)
Download (1MB) | Preview


Agro-products constitute to the daily needs of every person in this world. Frequent change in the prices of Agro-products create a huge pressure on the farmers and the consumers due to the money factor involved in cultivating the crops and buying daily food items. Determining and analysing the price fluctuation is a very complex study due to a large number of factors affecting it such as rainfall, temperature, holidays, air pollution and so on. Many researches have been done in the past to predict the commodity pricing but fails to explain the reliability factor and robustness of the model on the futuristic data. This research follows the designed framework to select the appropriate statistical/machine learning model based on data. This selects the model based on the data to forecast the future prices of Agro-products more accurately and increases the robustness of the model. Based on the framework Recurrent Neural Networks with Long-Short-Term-Memory is selected to predict the prices. Seasonal ARIMA and multiple linear regression models are also performed to compare the efficiency of the framework selected model. Based on the evaluations metrics and results of the three models, the RNN with LSTM model shows highly accurate results with a fit of 94% for predicting the prices of the Agro products. This research project creates a model which helps the farmers and the consumers to identify the prices of the commodities for the future dates which helps them in avoiding any concurring losses.
Keywords: agricultural commodity price prediction, multivariate time series analysis, model selection framework, RNN with LSTM, Seasonal ARIMA, Multiple linear regression.

Item Type: Thesis (Masters)
Subjects: Q Science > QA Mathematics > Electronic computers. Computer science
T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science
Q Science > QA Mathematics > Computer software
T Technology > T Technology (General) > Information Technology > Computer software
Divisions: School of Computing > Master of Science in Data Analytics
Depositing User: Dan English
Date Deposited: 20 Jan 2021 16:53
Last Modified: 20 Jan 2021 16:53

Actions (login required)

View Item View Item