Task 2 Part D
Contents
User Guide
Machine Learning
Validation
Solution Summary
Data Summary
Visualizations
Part D of the documentation explains the technical details of your project and
should target the computer science subject matter experts. Hence, of the
documentation, part D is most valued and scrutinized by the evaluators. Of
part D, the User Guide, Machine Learning, and Validation sections are the most
important. As such, we recommend completing these sections first. Follow the
Task 2 Template.
User Guide
The evaluator might go here first. Following your instructions, they will verify
your app functions as intended and simultaneously gain context of its purpose
through demonstration.
Include an enumerated (steps 1, 2, 3, etc.) guide on how to execute and use
your application. The evaluator will play the “client” role and follow your
instructions as provided. So you should include instructions for downloading
and installing any necessary software or libraries (they’ll have most of these
, installed anyway). Your application will be considered “user-friendly” if the
evaluator successfully executes and uses your application on a Windows 10
machine following your instructions.
Provide examples. Examples not only make the instructions easier to
follow (hence easier to pass) but also demonstrate how the app solves the
organizational need. When applicable provide sample input or input
which can be copied and pasted.
Provide visual aides. Screenshots or even a Panotpo video would all be
great ways in aiding the evaluator’s understanding of your project.
Test. Create a new environment or borrow a friend’s computer, follow
your instructions verbatim, and verify that everything works as expected.
It’s easy to overlook small details.
Machine Learning
This section should describe the development of your ML application justifying
and explaining decisions made in the process. Explain the what, how, and why
of the machine learning model and its application.
What? Outline what your product does and then explain in detail what
machine learning does in solving the proposed problem. Describe the
algorithms, libraries, and other tools used to develop the machine
learning model. Consider including an example of your model’s output.
How? Outline your application’s implementation plan and then explain in
detail how the machine learning portion was developed (or trained) and
improved.
Contents
User Guide
Machine Learning
Validation
Solution Summary
Data Summary
Visualizations
Part D of the documentation explains the technical details of your project and
should target the computer science subject matter experts. Hence, of the
documentation, part D is most valued and scrutinized by the evaluators. Of
part D, the User Guide, Machine Learning, and Validation sections are the most
important. As such, we recommend completing these sections first. Follow the
Task 2 Template.
User Guide
The evaluator might go here first. Following your instructions, they will verify
your app functions as intended and simultaneously gain context of its purpose
through demonstration.
Include an enumerated (steps 1, 2, 3, etc.) guide on how to execute and use
your application. The evaluator will play the “client” role and follow your
instructions as provided. So you should include instructions for downloading
and installing any necessary software or libraries (they’ll have most of these
, installed anyway). Your application will be considered “user-friendly” if the
evaluator successfully executes and uses your application on a Windows 10
machine following your instructions.
Provide examples. Examples not only make the instructions easier to
follow (hence easier to pass) but also demonstrate how the app solves the
organizational need. When applicable provide sample input or input
which can be copied and pasted.
Provide visual aides. Screenshots or even a Panotpo video would all be
great ways in aiding the evaluator’s understanding of your project.
Test. Create a new environment or borrow a friend’s computer, follow
your instructions verbatim, and verify that everything works as expected.
It’s easy to overlook small details.
Machine Learning
This section should describe the development of your ML application justifying
and explaining decisions made in the process. Explain the what, how, and why
of the machine learning model and its application.
What? Outline what your product does and then explain in detail what
machine learning does in solving the proposed problem. Describe the
algorithms, libraries, and other tools used to develop the machine
learning model. Consider including an example of your model’s output.
How? Outline your application’s implementation plan and then explain in
detail how the machine learning portion was developed (or trained) and
improved.
