You may be looking at a machine learning or neural network type of predictive analysis? Assuming so, there is a good free paper on this at https://www.sciencedirect.com/science/article/pii/0167691189900315
You may also want to redesign this as a nonlinear model using a programming method in R or maybe a math programming model like integer or goal programming using Tableau oemr Excel, see ideas in
Strang, K.D. (2013). Planning for hurricane Isaac using probability theory in a linear programming model. International Journal of Risk and Contingency Management, 2(1), 51-65. IGI
Strang, K.D. (2013). Risk management research design ideologies, strategies, methods and techniques. International Journal of Risk and Contingency Management, 2(2), 1-26. IGI
Strang, K.D. (2013, January 8).Examples of how to research & share crisis management knowledge. International Disaster Research Conference, New Orleans. IDCE
Strang, K.D. (2012). Logistic planning with nonlinear goal programming models in spreadsheets. International Journal of Logistics, 2(4), 1-24. IGI
Strang, K.D. (2012). Man versus math: Behaviorist exploration of post-crisis non-banking asset management. Journal of Asset Management, 13(5), 348-367. Palgrave
Strang, K.D. (2012). Applied financial nonlinear programming models for decision making. International Journal of Applied Decision Sciences, 5(4), 52-69. Inderscience
Feedback linearization is a powerful techniques for analysis and design of nonlinear systems. The central idea of this approach is to algebraically transform the nonlinear system dynamics into a fully or partially linearized system so that the feedback control techniques could be applied. In the study of dynamical systems, linearization is a method for assessing the local stability of an equilibrium point of a system of nonlinear differential equations or discrete dynamical systems. This method is used in fields such as engineering, physics, economics, and ecology.
Using control authority to transform nonlinear models into linear ones is called Feedback Linearization and it looks the same with system linearization with feedback.