One of the topics most frequently overlooked in contemporary machine learning (ML) and data mining (DM) literature, along with those of variable design and data processing, is the scoring process. This is because the majority of inexperienced analysts have been led to believe that the model-building process ends with the obtaining of the final model. However, even excellent models can ultimately be discarded if they are unable to be successfully deployed and executed on a recurring basis. It is unfortunate that I have observed on numerous occasions throughout my professional career that models that were developed with significant effort and resources have ultimately been discarded due to a lack of understanding of the scoring process. It is easy to understand that the loss of all the work invested in the construction of a model would be a significant tragedy. It is therefore crucial to have a plan in place to move forward with the model in question, should it be accepted for production. However, it is imperative to first comprehend the intricacies of the scoring process.