Call for Paper - January 2023 Edition
IJCA solicits original research papers for the January 2023 Edition. Last date of manuscript submission is December 20, 2022. Read More

Regression based Price and Yield Prediction of Agricultural Crop

International Journal of Computer Applications
Foundation of Computer Science (FCS), NY, USA
Year of Publication: 2016
Anjela Diana Corraya, Sonia Corraya

Anjela Diana Corraya and Sonia Corraya. Regression based Price and Yield Prediction of Agricultural Crop. International Journal of Computer Applications 152(5):1-7, October 2016. BibTeX

	author = {Anjela Diana Corraya and Sonia Corraya},
	title = {Regression based Price and Yield Prediction of Agricultural Crop},
	journal = {International Journal of Computer Applications},
	issue_date = {October 2016},
	volume = {152},
	number = {5},
	month = {Oct},
	year = {2016},
	issn = {0975-8887},
	pages = {1-7},
	numpages = {7},
	url = {},
	doi = {10.5120/ijca2016911804},
	publisher = {Foundation of Computer Science (FCS), NY, USA},
	address = {New York, USA}


Successfully predicting agricultural economy leads to maximum benefit and best effort utilization for farmers. It is very important and challenging to make correct agricultural decisions for a future stable price and yield balance. For the failure of this prediction, knowledge from historical data could not be used properly for managing agricultural revenue affecting factors.The objective of this research work is to develop an advance and efficient system for predicting future price and yield of agricultural crops considering inflation which is affected by climate conditions and other situational factors. At first, the Auto Regressive Moving Average (ARMA) Model was used for the work but the best estimates would always show a sudden and steep drop in the yield for every crop and would not show an increase until years later. Then the Weighted Linear Regression model was used by giving more weight to recent data which results 78.75% and 83.55% correct prediction for price and yield respectively after comparing the actual and predicted values over previous three years. Initially three types of rice of Bangladesh (Aus, Aman and Boro) are analyzed and there is scope for extensive use of this method.


  1. Anonymous. ARIMA model for time series forecasting,, 2011(accessed April-2016). ~rnau/411arim.htm.
  2. Anonymous. Agriculture Retrieved,, (accessed April-2015).
  3. Autoregressive Moving Average Model,, (accessed April- 2016). arma-model.html.
  4. Bangladesh Rice Research Institute,, (accessed April-2016).
  5. Git,, (accessed April-2016).
  6. Gradle Build Tool I Modern Open Source Build Automation,, (accessed April-2016).
  7. Weighted Linear Regression,, (accessed April-2016). http: // weighted-linear-regression/.
  8. Auto Regression Analysis(AR),, Novembor 1998(accessed April-2016). ar/.
  9. Mansur Ahmed and Barry Goodwin. Agricultural mechanization and non-farm labor supply of farm households: Evidence from bangladesh. Technical report, Agricultural and Applied Economics Association, 2016.
  10. Mohammad Alauddin. Recent developments in the bangladesh economy. In Economic Growth, Economic Performance and Welfare in South Asia, pages 11–27. Springer, 2005.
  11. Pramod K Joshi, Ashok Gulati, Pratap S Birthal, and Laxmi Tewari. Agriculture diversification in south asia: patterns, determinants and policy implications. Economic and Political Weekly, pages 2457–2467, 2004.
  12. AKM Golam Rabbani Mondal, Md Abdul Khalek, Md Mostafizur Rahman, and Dedar Mahmud. Price escalation of rice in bangladesh: A time series approach.
  13. BM Whelan, AB McBratney, and B Minasny. Vesper 1.5– spatial prediction software for precision agriculture. In Precision Agriculture, Proc. 6th Int. Conf. on Precision Agriculture, ASA/CSSA/SSSA, Madison, WI, USA, volume 179, 2002.


Agricultural Economy, Price, Weighted Linear Regression, Yield, Prediction