Creating adaptive farm typologies using Naive Bayesian classification

Wim Paas, Jeroen C.J. Groot*

*Corresponding author for this work

Research output: Contribution to journalArticleAcademicpeer-review

3 Citations (Scopus)

Abstract

The applicability of statistical typologies that capture farming systems diversity in innovation and development projects would increase if their adaptability would be enhanced, so that newly encountered farms can be classified and used to update the typology. In this paper we propose Naïve Bayesian (NB) classification as a method to allocate farms to types by using only a few variables, thus allowing the addition of new entries to a typology. We show for two example datasets that the performance of NB classification is already acceptable when 50% of the original survey dataset to construct the typology is used for training the NB classifier. For our datasets, the performance of Naïve Bayesian classification was improved when probabilities for observations to belong to multiple types were used, requiring a sample size of 30% of the survey dataset. Based on the results in this paper, we argue that NB classification is a powerful and promising statistical approach to increase the adaptability and usability of farm typologies.

Original languageEnglish
Pages (from-to)220-227
JournalInformation Processing in Agriculture
Volume4
Issue number3
DOIs
Publication statusPublished - 2017

Fingerprint

farm typology
typology
Farms
farm
farms
development projects
Classifiers
farming systems
development project
Innovation
farming system
innovation
sampling

Keywords

  • Clustering
  • Data distributions
  • Diversity
  • Farming systems

Cite this

@article{c90587a547aa4cc388bca42db55283c0,
title = "Creating adaptive farm typologies using Naive Bayesian classification",
abstract = "The applicability of statistical typologies that capture farming systems diversity in innovation and development projects would increase if their adaptability would be enhanced, so that newly encountered farms can be classified and used to update the typology. In this paper we propose Na{\"i}ve Bayesian (NB) classification as a method to allocate farms to types by using only a few variables, thus allowing the addition of new entries to a typology. We show for two example datasets that the performance of NB classification is already acceptable when 50{\%} of the original survey dataset to construct the typology is used for training the NB classifier. For our datasets, the performance of Na{\"i}ve Bayesian classification was improved when probabilities for observations to belong to multiple types were used, requiring a sample size of 30{\%} of the survey dataset. Based on the results in this paper, we argue that NB classification is a powerful and promising statistical approach to increase the adaptability and usability of farm typologies.",
keywords = "Clustering, Data distributions, Diversity, Farming systems",
author = "Wim Paas and Groot, {Jeroen C.J.}",
year = "2017",
doi = "10.1016/j.inpa.2017.05.005",
language = "English",
volume = "4",
pages = "220--227",
journal = "Information Processing in Agriculture",
issn = "2214-3173",
publisher = "Elsevier BV",
number = "3",

}

Creating adaptive farm typologies using Naive Bayesian classification. / Paas, Wim; Groot, Jeroen C.J.

In: Information Processing in Agriculture, Vol. 4, No. 3, 2017, p. 220-227.

Research output: Contribution to journalArticleAcademicpeer-review

TY - JOUR

T1 - Creating adaptive farm typologies using Naive Bayesian classification

AU - Paas, Wim

AU - Groot, Jeroen C.J.

PY - 2017

Y1 - 2017

N2 - The applicability of statistical typologies that capture farming systems diversity in innovation and development projects would increase if their adaptability would be enhanced, so that newly encountered farms can be classified and used to update the typology. In this paper we propose Naïve Bayesian (NB) classification as a method to allocate farms to types by using only a few variables, thus allowing the addition of new entries to a typology. We show for two example datasets that the performance of NB classification is already acceptable when 50% of the original survey dataset to construct the typology is used for training the NB classifier. For our datasets, the performance of Naïve Bayesian classification was improved when probabilities for observations to belong to multiple types were used, requiring a sample size of 30% of the survey dataset. Based on the results in this paper, we argue that NB classification is a powerful and promising statistical approach to increase the adaptability and usability of farm typologies.

AB - The applicability of statistical typologies that capture farming systems diversity in innovation and development projects would increase if their adaptability would be enhanced, so that newly encountered farms can be classified and used to update the typology. In this paper we propose Naïve Bayesian (NB) classification as a method to allocate farms to types by using only a few variables, thus allowing the addition of new entries to a typology. We show for two example datasets that the performance of NB classification is already acceptable when 50% of the original survey dataset to construct the typology is used for training the NB classifier. For our datasets, the performance of Naïve Bayesian classification was improved when probabilities for observations to belong to multiple types were used, requiring a sample size of 30% of the survey dataset. Based on the results in this paper, we argue that NB classification is a powerful and promising statistical approach to increase the adaptability and usability of farm typologies.

KW - Clustering

KW - Data distributions

KW - Diversity

KW - Farming systems

U2 - 10.1016/j.inpa.2017.05.005

DO - 10.1016/j.inpa.2017.05.005

M3 - Article

VL - 4

SP - 220

EP - 227

JO - Information Processing in Agriculture

JF - Information Processing in Agriculture

SN - 2214-3173

IS - 3

ER -