Regression-Based AGRO Forecasting Model

  • B. V. Balaji PrabhuEmail author
  • M. Dakshayini
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 755)


Prediction plays an important role everywhere particularly in business, technology, and many others. It helps all types of organizations to improve profits and reduce the loss by taking timely decisions. Agriculture is also like an organization where farmers suffer with the loss most of the time in this business. This could be mainly because, there is no system to ensure the synchronization between the demand and supply for various food commodities required by the society. Science, enormous amount of data from different authorized sources like government websites revealing the demand and supply of various food commodities for forgoing period, this paper proposes a novel regression based AGRO forecasting model. This could help the farmers to make timely decisions and work towards fulfilling the actual needs of the society and avoiding putting themselves into the loss by growing unnecessary crops. Proposed model has been implemented using MapReduce parallel programming approach with Hadoop Distributed File System. This processes time series data with Regression model for predicting the demand, supply and price for the agricultural commodities in distributed environment. Resulting forecasted values are in the range of real values.


Prediction Decision Agriculture Demand–supply Forecast Parallel programming model Hadoop distributed file system Regression MapReduce Time series 


  1. 1.
  2. 2.
  3. 3.
  4. 4.
    Kumar, P., Joshi, P.K., Birthal, P.S.: Demand projections for foodgrains in India. Agric. Econ. Res. 22, 237–243 (2009)Google Scholar
  5. 5.
    Balaji Prabhu, B.V., Dakshayini, M.: A novel cloud based data analytics framework for effective crop management. Int. J. Control Theory Appl. 9(22), 257–264 (2016)Google Scholar
  6. 6.
    Arputhamary, B.: PAFHWKM: an enhanced parallel approach to forecast time series data using holt-winters and K-Means algorithmGoogle Scholar
  7. 7.
    Chen, M., Mao, S., Liu, Y.: Big Data: A Survey, pp. 171–209 (2014)Google Scholar
  8. 8.
    Shvachko, K.: The Hadoop distributed file system. In: IEEE 26th Symposium on Mass Storage Systems and Technologies, pp. 1–10 (2010)Google Scholar
  9. 9.
    Saldhi, A., Yadav, D., Saksena, D., Goel, A., Saldhi, A., Indu, S.: Big data analysis using Hadoop cluster. In: 2014 IEEE International Conference on Computational Intelligence and Computing Research, 2014.
  10. 10.
    Elagib, S.B., Najeeb, A.R., Hashim, A.H., Olanrewaju, R.F.: Big data analysis solutions using MapReduce framework. In: Proceedings of 5th International Conference on Computer and Communication Engineering Emerging Technologies via Comp-Unication Convergence, ICCCE 2014, pp. 127–130 (2015)Google Scholar
  11. 11.
    İşlek, İ., Öğüdücü, Ş.G.: A retail demand forecasting model based on data mining techniques. In: 2015 IEEE 24th International Symposium on Industrial Electronics (ISIE), pp. 55–60 (2015)Google Scholar
  12. 12.
    Kaur, N., Kaur, A.: Predictive modelling approach to data mining for forecasting electricity consumption. In: 2016 6th International Conference, Cloud System and Big Data Engineering, pp. 331–336 (2016)Google Scholar
  13. 13.
    Planning, P., Cell, M.: Supply and demand for selected fruits and vegetables in Karnataka. Int. J. Farm Sci. 5(2), 184–197 (2012)Google Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2019

Authors and Affiliations

  1. 1.Department of ISEBMS College of EngineeringBangaloreIndia

Personalised recommendations