In this investigation, a software architecture model is proposed to handle multiple Machine Learning algorithmic strategies to generate predictions over the stock market .The proposal were design under the Design Research in Information Systems as the methodological framework and resulted in several software UML artifacts such as dynamic and structural models. As part of the analysis, a functional prototype was implemented and the architecture was validated. As a result, the prototype fulfilled the adaptability requirement and some performance issues were acknowledged along with some opportunities for improvements and future work.