Extra-tree learning based Socio-economic factor analysis and multi-class adaptive boosting meta-estimator for prediction of agricultural productivity

Abstract

Background/Objectives: In socioeconomic factor analysis, the observed data are essential in the random distribution for the adequate representation of the random components associated with various factors and lead to poor prediction in the case of the Logit and Probit model. The objective of this work is to have machine learning based model for socioeconomic factors analysis and ensemble learning based model for efficient prediction of agricultural productivity. Methods: In this work, extra-tree classifier machine learning model based socioeconomic factors selection has been used and found capable to evaluate the socioeconomic factors that contain relevant information to the target variable agricultural productivity. In addition to this, the multi-class adaptive boosting ensemble learning approach is used for the prediction of agricultural productivity of respondents (farmers) from their socioeconomic profiles. This proposed research has been evaluated by using the test case of analyzing the socioeconomic factors of the farmers affecting agricultural productivity in Sambalpur District, of Odisha State, India. The farmers' socioeconomic data are collected by using structured interviews through questionnaires that are in line with standard Participatory Rural Appraisal. Findings: It is found that the proposed approach of socioeconomic factor identification is efficient for computing the relationships between socioeconomic factors and agricultural productivity. Novelty: In this application domain of socioeconomic factor analysis, the proposed method employs extra-tree classifier and boosting ensemble learning for socioeconomic factor analysis towards agricultural productivity which is found efficient than other existing approaches such as Logit, Probit, Linear Regression, Linear Discriminant Analysis, Naïve Baise, and other counterparts.