Mark Temple-Raston , Decision Machine, USA

Scientific Machine Learning is built on the science-of-counting, is deductively solvable, and well-suited to business and human applications that naturally count. From the Gibbs formalism, Scientific Machine Learning produces unique and exact scientific measurements that define the state of the time-series. Timeseries itself defines a geometric structure tailor made for prediction, optimization and decision making. Inventory management decisions will demonstrate Scientific Machine Learning without introducing models or model bias.

Machine Learning, Supply Chain Management, Prediction, Optimization, Interaction, Information Theory, Decision Theory