Machine Learning Techniques for Egg Production Prediction

Abstract

Predicting egg production in poultry farming is a complex task due to the multitude of influencing factors such as temperature, nutrition, and environmental conditions. This study aims to evaluate the performance of various machine learning models in forecasting egg production using multivariate time series data. The dataset comprises records of the Hy-Line breed, divided into four batches, with attributes including age, maximum and minimum temperature, feed and water consumption, and daily production percentage. The study employs a sliding window technique to capture temporal patterns and evaluates models including Ridge Regression, Random Forest, XGBoost, and MLP. The models were trained on three batches and tested on the fourth, with performance measured using Mean Squared Error (MSE) and Mean Absolute Percentage Error (MAPE). The results indicate that Ridge Regression, with a window size of 7 days, provided the most accurate predictions, achieving an MSE of 19.74 and a MAPE of 3.81%. This study demonstrates the effectiveness of machine learning techniques and the sliding window approach in improving the accuracy of egg production forecasts, offering valuable insights for poultry farm management and optimization.