An Agricultural Land Contractual Management Transfer Prediction Model Based on Analytic Hierarchy Process and Logistic Regression

Abstract

In the field of application prediction, there are two kinds of common methods to establish the prediction model: prediction model established by artificial data analysis relying on expert experience, and prediction model achieved by statistical model exploiting data analysis. However, the prediction accuracy of the model based on expert is restricted by the experiences, while the model based on statistical analysis is limited by the quality and scale of the training data. In view of the advantages and disadvantages of these two kinds of models, this paper presents a prediction model by integrating Analytic Hierarchy Process and Logistic Regression. The proposed prediction model uses the Analytic Hierarchy Process, which are based on the training data and expert experience to obtain the rank of predominant factor in a specific domain, and exploits the logistical regression model to learn the weights of each influencing factor. Finally, the linear combination of the two models is used to obtain the prediction model. Further, we take agricultural land contractual management transfer prediction as an example to test the proposed hybrid prediction model.