ANC-201 Practice Questions

Upon reviewing the data model and noticing the high correlation alert between 'Store' and daily

sales quantity, the appropriate action is to verify with the client their expectations regarding the

influence of the Store field on daily sales. Here’s the rationale:

Understanding the Role of 'Store' in the Model: Before making any changes to the model, it's crucial

to understand whether the 'Store' field is expected to be a strong predictor based on the business

context. If the client expects that different stores inherently have different sales volumes due to

factors like location, size, or customer base, this correlation may be both meaningful and desired.

Potential Data Leakage: High correlation warnings can sometimes indicate data leakage, where a

predictor (like 'Store') might inadvertently include information about the outcome variable (daily

sales quantity). It's essential to verify whether this correlation makes sense logically or if it's skewing

the model predictions.

Client Consultation: Consulting with the client helps ensure that any modeling decisions align with

their business knowledge and expectations. It’s about validating the model against real-world

expectations and ensuring it remains a useful tool for decision-making.

By taking these steps, the consultant not only adheres to best practices in data science by validating

model inputs and their implications but also ensures that the model aligns with the client’s business

strategies and operational realities.

:

If a consultant at Cloud Kicks needs to use custom GeoJSON files for dashboard visualization and

cannot upload the file via the CRM Analytics user interface (UI), the recommended action is to use

the API for this purpose. Here’s why this approach is suggested:

Functionality Limitation in UI: Currently, the CRM Analytics UI does not support direct uploads of

GeoJSON files, which necessitates an alternative method.

API Flexibility: The API provides a more flexible route for uploading custom GeoJSON files, allowing

consultants to integrate more complex or larger datasets that are not supported through standard UI

functionalities.

Customization and Control: Using the API also offers greater control over how GeoJSON data is

handled, processed, and utilized within CRM Analytics, catering to more advanced customization

needs.

This method ensures that the consultant can fully utilize CRM Analytics’ capabilities for creating

highly customized geographic visualizations, thereby enhancing the analytical value of the

dashboards.

In the context of a regression model being deployed, the performance metrics used to evaluate its

effectiveness in production typically include:

Root Mean Square Error (RMSE): This metric provides a measure of the average magnitude of the

errors between predicted values by the model and the actual values, giving a sense of how

accurately the model predicts the outcome.

Minimum Square Error: While less commonly referenced as "Minimum Square Error", metrics like

Mean Squared Error (MSE) are often used to quantify the average of the squares of the errors—

essentially, the average squared difference between the estimated values and what is estimated.

These metrics are crucial for assessing the performance of regression models in CRM Analytics, as

they directly reflect the accuracy and reliability of the model’s predictions in real-world applications.

In CRM Analytics, performance issues often arise when large tables or datasets are loaded on a single

dashboard page, especially when the table contains a lot of data, as in the case of the Opportunities

Table. One way to improve performance is to split the dashboard into multiple pages, moving

resource-intensive components (like large tables) to a secondary page. By creating a second page

and relocating the Opportunities Table, the initial dashboard page will load faster, and users can still

access the table by navigating to the second page when needed. This practice ensures better overall

performance and user experience.

Reference: CRM Analytics Dashboard Optimization

:

:

:

In CRM Analytics, the versioning feature described is typically leveraged for Apps. This feature

allows:

Parallel Development: Users can work on changes in a separate version without affecting the live

version being accessed by others.

Controlled Publishing: Once changes are finalized, the user can then promote their version to be the

new live version, ensuring seamless updates without disrupting ongoing usage.

Collaborative Workflows: Facilitates teamwork by allowing multiple users to propose and test

changes in a controlled environment before making those changes live.

This approach ensures that CRM Analytics apps remain dynamic and can evolve over time while

maintaining stability and continuity for end-users.

If the wrong field is selected in the initial setup of an app or dataset, it is important to stop any data

processing activities (like recipe executions) to prevent erroneous data from being loaded into

datasets and dashboards. In this case, stopping the recipe from running in Data Manager is the

correct first step. Once the recipe is stopped, the consultant can update the field selection or make

other necessary corrections before restarting the process.

Reference: The Data Manager section in CRM Analytics outlines how recipes and data flows are

managed, including how to stop or pause recipes.