International Journal of Statistics and Applied Mathematics
  • Printed Journal
  • Indexed Journal
  • Refereed Journal
  • Peer Reviewed Journal

2023, Vol. 8, Special Issue 5

Tree-based ensemble models for productivity trend of minor millets


Author(s): RS Parmar, GJ Kamani and YR Ghodasara

Abstract: India is one of the leading producers of minor millets, and cultivation of these millets has been declining during the last few years. The present investigation was carried out to study the productivity trend of minor millets in India for the period 1990-91 to 2019-20. Estimation of minor millet productivity trends plays a crucial role in agricultural management in India as an agriculture-based economy. Five tree-based ensemble models viz., Bagging Decision Stump, Bagging M5P, Bagging Random Forest, Bagging Random Tree, and Bagging REP Tree were studied. The statistically most fitted tree-based ensemble models were selected based on various performance measurement criteria namely MAE, RMSE, RAE, RRSE, and R2. The Bagging Random Forest has achieved the highest estimation accuracy of 87% as compared with other fitted tree-based ensemble models. It has the lowest MAE of 33.86 and RMSE of 42.64. Thus, the bagging Random Forest model emerged as the best-fitted trend model for the estimation of the productivity trend of minor millets in India.

Pages: 170-174 | Views: 278 | Downloads: 5

Download Full Article: Click Here
How to cite this article:
RS Parmar, GJ Kamani, YR Ghodasara. Tree-based ensemble models for productivity trend of minor millets. Int J Stat Appl Math 2023;8(5S):170-174.

Call for book chapter
International Journal of Statistics and Applied Mathematics