Determination of factors affecting dairy cattle: a case study of Ardahan province using data mining algorithms

Koksal Karadas,Avni Birinci

doi:10.1590/rbz4820170263

Abstract

ABSTRACT This study was conducted to compare predictive performances of different data-mining algorithms for determining factors influencing the average daily milk yield at dairy cattle enterprises of Ardahan province, located in the Eastern Anatolia region of Turkey. The algorithms employed in the present study were Classification and Regression Tree (CART), Chi-Square Automatic Interaction Detector (CHAID), Exhaustive Chi-Square Automatic Interaction Detector (Exhaustive CHAID), Multivariate Adaptive Regression Splines (MARS), and Multilayer Perceptron (MLP). The MARS algorithm outperformed the other algorithms in the study. Visual results of CART revealed that the culture-breed cows with a lactation length greater than 237.500 days had the highest milk yield (10.64 kg/day). Culture-breed cows calving earlier than the 4th month gave the highest yield of approximately 10 kg/day in the regression tree of CHAID. The Exhaustive CHAID results were almost the same as the structure of the CHAID. The use of MARS may provide an opportunity to detect factors affecting milk production (breed, feed supply, type of milking, mastitis control, cow year group, and lactation length) and their interactions. Moreover, the MARS algorithm may be useful in making an accurate decision about increasing milk yield per cow.

Highlights

A sufficient and balanced diet is very important for a healthy lifestyle to maintain growth and development and combat diseases
Definitions of the variables used in the study and their abbreviations are as follows: Average milk yield per cow (AMYPC) is a continuous target variable; breed is a nominal input variable; and year group (Y = 1, 2, 3, and 4) is an ordinal input variable
Interaction effects were not included in General Linear Model (GLM) as a result of the great number of the subgroups obtained by main effects

Summary

Introduction

A sufficient and balanced diet is very important for a healthy lifestyle to maintain growth and development and combat diseases. In this scenario, with its considerable vitamin C and iron contents, milk is an important source of macro- and micronutrients (Black et al, 2002). Turkey holds 2.05% of the world cattle population (5,609,240 heads) and produces 2.59% of all cow milk (16,998,850 tons) in the world (FAO, 2016). The world average cow milk yield is 2,394 kg, while the average yield in Europe and Turkey is 5,834 and 3,030 kg, respectively. The average milk yield in Turkey is above the world average, it is far below that of Europe. The Eastern Anatolia region of Turkey has a great potential for dairy farming, where it has pasture and grassland area relative to other regions in the country; the milk yield of that region is lower than any other region of the country

Methods

Results

Discussion

Conclusion