Machine learning is one of the most important subfields of computer science and can be used to solve a variety of interesting artificial intelligence problems.There are different languages, framework and tools to define the data needed to solve machine learning-based problems.However, there is a great number of very diverse alternatives which makes it difficult the intercommunication, portability and re-usability of the definitions, designs or algorithms that any developer may create.In this paper, we take the first step towards a language and a development environment independent of the underlying technologies, allowing developers to design solutions to solve machine learning-based problems in a simple and fast way, automatically generating code for other technologies.That can be considered a transparent bridge among current technologies.We rely on Model-Driven Engineering approach, focusing on the creation of models to abstract the definition of artifacts from the underlying technologies.