Machine Learning models evolve due to evolution of the input data, the relationtions between predictors and dependent variables or even due to temporal degration of the implementation.
The implications of these phenomenons for machine learning operations requires not just the proper identification, but also the understanding and the adaptation of the systems, adapting risk models, security frameworks and ultimately the software supply chain.
This presentation review the state of the art on these topics, presenting the result of recent research papers and highlighting the elements still to be defined.