Machine Learning Approaches for Evaluating Statistical Information in the Agricultural Sector

This book presents machine learning approaches to identify the most important predictors of crucial variables for dealing with the challenges of managing production units and designing agriculture policies. The book focuses on the agricultural sector in the European Union and considers statistical information from the Farm Accountancy Data Network (FADN).

Presently, statistical databases present a lot of information for many indicators and, in these contexts, one of the main tasks is to identify the most important predictors of certain indicators. In this way, the book presents approaches to identifying the most relevant variables that best support the design of adjusted farming policies and management plans. These subjects are currently important for students, public institutions and farmers. To achieve these objectives, the book considers the IBM SPSS Modeler procedures as well as the respective models suggested by this software.

The book is read by students in production engineering, economics and agricultural studies, public bodies and managers in the farming sector.

Chapter 1. Predictive machine learning approaches to agricultural output.- Chapter 2. Applying artificial intelligence to predict crops output.- Chapter 3. Predictive machine learning models for livestock output.- Chapter 4. Predicting the total costs of production factors on farms in the European Union.- Chapter 5. The most important predictors of fertiliser costs.- Chapter 6. Important indicators for predicting crop protection costs.- Chapter 7. The most adjusted predictive models for energy costs.- Chapter 8. Machine learning methodologies, wages paid and the most relevant predictors.- Chapter 9. Predictors of interest paid in the European Union’s agricultural sector.- Chapter 10. Predictive artificial intelligence approaches of labour use in the farming sector.