Map > Problem Definition > Data Preparation > Data Exploration > Modeling > Evaluation > Deployment

Problem Definition

First, it is required to start with "a question" and understand and define the objectives clearly. Next, we should do an extensive search to see if there is an existing answer for our question. Then, if we do not find an answer for our question we do research and based on the objectives we design an experiment and decide about the best possible data science solution. Moreover, we should clearly define our "success criteria" to judge whether an objective has successfully been achieved. Finally, we should have a plan about the deployment of our solution and consider the major roadblocks such reproducibility of the outcomes.
Discovery and development of genomic biomarkers from discovery to application