Key causes of failures No good state of the end goal of a project. The desired outcome that is hoped to be achieved by completing the project.  Poor-quality data can lead to wrong conclusions and unreliable results due to lack of research, not properly assessing the data available. Lack of communication. Data science projects are complex and require collaboration between data scientists, engineers, and stakeholders. Results can lead to misunderstandings and incorrect assumptions being made.  Poor Modeling: If the wrong model is chosen or the model is not fine-tuned properly, the project may not yield the desired results.  How cognitive task analysis can ensure success of data sciences projects Identify what the problem project is intended to solve and create ...