A Markov model for optimal feeding and marketing decisions in production units of growing pigs

Reza Pourmoayed, Lars Relund Nielsen & Anders Ringgaard Kristensen


65th Annual Meeting of the European Federation of Animal Science


In the pig production system, feeding is the most important factor that has a direct influence on the quality of the meat and the costs of the production unit. Another important element is the timing of slaughter (the marketing decision) that refers to a sequence of culling decisions until the production unit is emptied. In the production system, the economic optimizations of feeding and marketing decisions are interrelated and there is a need for a simultaneous analysis. In this study a stochastic optimization model is developed at pen level. In the model the state of the system is updated using a Bayesian approach based on on-line data obtained from a set of sensors in the pen. More precisely, two statistical models are used to update estimates of live weight and growth rate on a weekly basis. The proposed models are tested based on the data from a Danish farm to show the model may be used as decision support in finding optimal feeding and marketing decisions.