Mahuya Deb*

Department of Advanced Computing, St. Joseph’s College, India

*Corresponding Author: Mahuya Deb, Department of Advanced Computing, St. Joseph’s College, India.

Received: November 25, 2021; Published: April 26, 2022

Abstract

Tea constitutes a major cash crop and earns huge revenue for the state of Assam. Assam being a big exporter of tea can benefit if an early warning mechanism for the price of tea could be obtained in advance. This could benefit the buyers to calculate the price and profit before they plan to engage in the buying activity so as to retain their position both nationally as well as internationally. Such calculative decisions are important in respect to quality, quantity, time and venue since auctions are held in different parts of the country. But many a times some random fluctuation may creep in which might pose a threat for maintaining a uniformity in the tea prices over the years. As per reports due to pandemic, the local consumption of tea has increased by upto 5% therefore skewing past data trends. The packet tea enterprise have shifted their focus from their own particular blends and this has resulted in a sudden crash in prices. These factors present a serious challenge in predicting the tea prices of a particular category. The price fluctuations are dependent on the availability of specific type of tea, credit periods and the total demand at the time of bidding. Hence these fluctuations have been analyzed in detail from historical data using various statistical techniques to get an understanding of the process behaviour Amongst the various techniques used for forecasting, a time series forecasting tool called ARIMA (Auto Regressive Integrated Moving average) method has been used from time to time. In addition to this, a neural network method has also been applied and further a valid comparison has been drawn between ARIMA and Neural Network. The data of tea prices from the year July 2005 to May2020 has been collected and trained using ARIMA and Neural Network model with different parameters The test criterion like Akaike Information Criterion is has been applied to analyse the accuracy of the model. The one with the least AIC is chosen. The model is then used to forecast the price of tea for the next ten data points where the prediction error appears small. The maximum variability in tea price has been observed in the latter months of 2021 specifically May, June, July and August. A reduced variability in the tea price has been observed in the months of June, July and August when the pandemic was taking a peak. For this, R programming software is used which is an effective tool for visualization, statistical computing, scientific inference, and graphical interface.

Keywords: Arima; Neural Network Method; Forecasting

References

1. Roy S. “Historical Review of Growth of Tea Industries in India: A Study of Assam Tea”. International Conference on Social Science and Humanity, IPEDR. IACSIT Press, Singapore 5 (2011).
2. Chaudhry , et al. “A time series analysis of auction prices of Indian tea”. International Journal of Research in Economics and Social Sciences 7.6 (2017): 100-111.
3. Gunathilaka RD and Tularam GA. “The tea industry and a review of its price modelling in major tea producing countries”. Journal of Management and Strategy 7 (2016): 21-36.
4. Hossain M and Abdulla “Forecasting the Tea Production of Bangladesh: Application of ARIMA Model (2015).
5. Kumarasinghe HPASS and Peiris “Forecasting annual tea production in Sri Lanka (2018).
6. Liu H and Shao “India’s tea price analysis based on ARMA model”. Modern Economy 7.2 (2016): 118-123.
7. Sapsford D and Varoufakis Y. “An ARIMA analysis of tea prices”. Journal of Agricultural Economics 2 (1987): 329-334.
8. Tealab “Time series forecasting using artificial neural networks methodologies: A systematic review”. Future Computing and Informatics Journal 3.2 (2018): 334-340.

Citation

Citation: Mahuya Deb. “Use of Auto Regressive Moving Average and Neural Network Method for Predicting Tea Prices in Assam". Acta Scientific Computer Sciences 4.5 (2022): 43-48.

Copyright

Copyright: © 2022 Mahuya Deb. This is an open-access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.