Database Reference
In-Depth Information
Figure 12.11
Example of a model description for a data science project
Mentioning the scope of the data used is critical. The purpose is to illustrate
thoroughness and exude confidence that the team used an approach that
accurately portrays its problem and is as free from bias as possible. A key trait of
a good data scientist is the ability to be skeptical of one's own work. This is an
opportunity to view the work and the deliverable critically and consider how the
audience will receive the work. Try to ensure it is an unbiased view of the project
and the results.
Assuming that the model will meet the agreed-upon SLAs, mention that the model
will meet the SLAs based on the performance of the model within the testing
or staging environment. For instance, one may want to indicate that the model
processed 500,000 records in 5 minutes to give stakeholders an idea of the speed
of the model during run time. Analysts will want to understand the details of
the model, including the decisions made in constructing the model and the scope
of the data extracts for testing and training. Be prepared to explain the team's
thought process on this, as well as the speed of running the model within the test
environment.
12.2.6 Key Points Supported with Data
The next step is to identify key points based on insights and observations resulting
from the data and model scoring results. Find ways to illustrate the key points with
charts and visualization techniques, using simpler charts for sponsors and more
technical data visualization for analysts and data scientists.
