AUTHOR=Sikka Poonam , Nath Abhigyan , Paul Shyam Sundar , Andonissamy Jerome , Mishra Dwijesh Chandra , Rao Atmakuri Ramakrishna , Balhara Ashok Kumar , Chaturvedi Krishna Kumar , Yadav Keerti Kumar , Balhara Sunesh 

TITLE=Inferring Relationship of Blood Metabolic Changes and Average Daily Gain With Feed Conversion Efficiency in Murrah Heifers: Machine Learning Approach

JOURNAL=Frontiers in Veterinary Science

VOLUME=Volume 7 - 2020

YEAR=2020

URL=https://www.frontiersin.org/journals/veterinary-science/articles/10.3389/fvets.2020.00518

DOI=10.3389/fvets.2020.00518

ISSN=2297-1769

ABSTRACT=Machine learning algorithms were employed for predicting the Feed Conversion Efficiency (FCE), using the blood parameters and Average Daily Gain (ADG) as predictor variables in buffalo heifers. It was observed that isotonic regression outperformed over other machine learning algorithms used in study. Further, we achieved the best performance evaluation metrics model with Additive regression as the meta learner and Isotonic regression as the base learner on a 10 fold cross validation leaving one out cross validation test. Further to understand the interactions of blood parameters, ADG with FCE, we created three separate partial least square regression (PLSR) models using all 14 parameters of blood and ADG as independent (explanatory) variables and FCE as the dependent variable, each for all FCE values(i), Higher FCE (negative)values (ii) and Lower FCE (positive) values (iii). PLSR model for the higher FCE values was the best, based on performance evaluation metrics as compared to PLSR models for the lower FCE values and all FCE values based on model evaluation indices. IGF1 and its interactions with the other blood parameters were found to be highly influential for higher FCE measures. Strength of estimated interaction effects of the blood parameter in relation to FCE may facilitate understanding the intricate dynamics of blood parameters for growth.