Skip to main content

Analyzing simulation results using Scenario Planner

4 Tasks

5 mins

Visible to: All users
Beginner Pega Customer Decision Hub 8.6 English
Verify the version tags to ensure you are consuming the intended content or, complete the latest version.

Scenario

U+ Bank is currently cross-selling on the web by showing various credit cards to its customers.

The bank wants to boost two credit card actions by applying a business weight. The bank wants to understand the opportunity cost or gain in using levers to adjust AI prioritization.

Use the following credentials to log in to the exercise system:

Role

User name

Password

Decisioning Analyst

CDHAnalyst

rules

Your assignment consists of the following tasks:

Task 1: Prepare data set for simulation run

Run the PrepareSampledCustomers_REF data flow to prepare the data set for the simulation run.

Note: The Sampled Customers is not available in a persisted store. To initialize the customer data, first, run the PrepareSampledCustomers_REF data flow. 

If you already initiated the customer data as part of a previous challenge, you do not need  perform Task 2.

Task 2: Add business weight to actions

Add a business weight to Standard card and Rewards card actions to manually nudge the offers.

Action

Business Weight

Standard card

20%

Rewards card

40%

Task 3: Create and execute an arbitration audience simulation

Create and execute an audience simulation. Use the Sampled Customers data set as the audience and engagement policy and arbitration as the simulation scope.

Task 4: Analyze the simulation results in Scenario Planner

Analyze the audience simulation with the arbitration in scenario planner to understand the effects of adding business weight to the actions. Answer the following questions.

  1. What is the effect of applying the business levers? Is there an indication of an opportunity cost or opportunity gain?
  2. How does the application of business levers affect the percentage of accepts?
  3. Which actions are traded off if the business levers are applied and what is the volume?
    • How many times is the Rewards card sent or presented to customers before and after applying business levers?
  4. How many customers are likely to accept the Premier Rewards card when the business levers are not applied?
  5. Which scenario is more profitable for the business?

You must initiate your own Pega instance to complete this Challenge.

Initialization may take up to 5 minutes so please be patient.

Challenge Walkthrough

Detailed Tasks

1 Prepare data set for simulation run

  1. Log in as Decisioning Analyst with username CDHAnalyst and password rules.
  2. In the navigation pane of Pega Customer Decision Hub, click Data > Data Flows.
    Data flows
  3. Search for and then open the PrepareSampledCustomers_REF data flow to prepare the data set used for simulations. This data is based on a Monte Carlo dataset, which is generated.
  4. Click Actions > Run to initialize the customer data.
    Run a data flow
  5. Click Submit to submit the customer data.
  6. Click Start to populate the customer data.
    Note: Notice that the prospect data is populated once the test run is complete.
  7. Close the data flow Test run window.

2 Add business weight to actions

  1. In Next Best Action Designer, click the Engagement policy tab.
  2. Click CreditCards.
    open group in engagement policy tab
  3. In the Offers section, click Standard card to open the card offer details.
  4. In the upper right, click Check out to check out the group-level conditions.
  5. In the Next-Best-Action configuration section, in the Business weight field, enter 20.
    Action Business weight
  6. Click Check-in to save the changes.
  7. Close the action to return to the Engagement policy tab.
  8. In the Offers section, click Rewards card to open the card offer details.
  9. In the upper right, click Check out to check out the group-level conditions.
  10. In the Next-Best-Action configuration section, in the Business weight field, enter 40.
    Add business weight to action
  11. Click Check-in to save the changes.
  12. Close the action to return to the Engagement policy tab.

3 Create and execute an arbitration audience simulation

  1. Click Actions > Audience Simulations.
    Open Audience simulation menu
  2. Click Create simulation to create a new audience simulation.
  3. In the Create simulation dialog box, configure the following information.
    1. Audience: SampledCustomers
    2. Next-Best-Action scope: Engagement policies and arbitration
      Note: The Include a second-pass simulation without business levers (for Scenario Planner) check box enables you to compare the simulation results to analyze the effectiveness of assigning an increased business weight to specific actions.
    3. Name: Arbitration_levers
      Audience simulation with arbitration
  4. Click Run to execute the simulation.
  5. Inspect how the customers are filtered at the Next Best Action Designer level for every engagement policy condition.

4 Analyze the simulation results in Scenario Planner

Question: What is the effect of applying the business levers? Is there an indication of an opportunity cost or opportunity gain?
  1. In the navigation pane of Pega Customer Decision Hub, click Discovery > Scenario Planner.
    Scenario planner menu
  2. In the Scenario Planner window, enter or select the following information:
    Scenario planner single simulation scope
    1. ScopeSales/Credit cards
    2. SimulationArbitration_levers (S-#####)
  3. Click Apply.
  4. Inspect the results.
    Single simulation in scenario planner
    Note: The Monte Carlo data set generates a mock data set. As a result, different simulation runs have different results.
    Note: In this example, the Scenario Planner projected value capture for the simulation with levers is $ 11.82K, and the projected value capture of the simulation without levers is $11.92K. In this example, there is an opportunity cost involved as there is a difference of $96.63K.
Question: How does the application of business levers affect the percentage of accepts?
  1. In the Scenario Planner window, as the Comparison simulation listselect (S-#####) With no levers.
    Scenario planner scope
  2. Click Apply.
  3. In the Projected responses (next run/presentation) tile, click the Graph icon to view the difference in the percentage of accepts.
    Difference in projected responses
    Note: In this example, the projected response is 33% for the simulation with levers and 34% for the simulation without levers. That is, the projected responses are more when the business does not apply business levers.
Question: Which actions are traded off if the business levers are applied and what is the volume?
  1. Scroll down to view the Projected reach per action.
    Projected reach per action
    Note: In this example, you can see the 41 additional Premier rewards card and 35 additional Rewards card offers are presented in green. The 26 fewer Rewards plus and 50 fewer Standard cards are in red.
    Question: How many times is the Rewards card is sent or presented to customers before and after applying business levers?
    Projected response of an action
    Note: The Rewards card is sent or presented 92 times when the business levers are applied. 
  2. Click the (S-#####) With no levers tab to view the results of the simulation without business levers.
    Scenario planner tabs for simulations
  3. Scroll down to view the Projected reach per action. 
    Per action projected reach without levers
    Note: Rewards card is sent or presented 57 times when the business levers are not applied, 35 times fewer than the scenario with business levers.
    Question: How many customers are likely to accept the Premier Rewards card when the business levers are not applied?
    Note: Projected response is the number of expected accepts per card. 120 customers are likely to accept the Premier Rewards card when the business levers are not applied. That is, 5 fewer acceptances than the scenario with business levers.
    Projected responses per action in comparison mode
    Note: When the adaptive model of an action does not have enough data projection to predict, the system indicates that there is insufficient evidence.
    Insufficient evidence in scenario planner
Question: Which scenario is more profitable for the business?
  1. Inspect the Projected value capture tile and note the opportunity gain indicated in green.
    Projected value capture with opportunity gain
  2. Inspect the Projected responses tile and note the increase in projected responses indicated in green.
    Increased Projected response
    Note: In this example, the scenario without levers is more profitable as the projected value capture is higher by $96.63.


Available in the following mission:

If you are having problems with your training, please review the Pega Academy Support FAQs.

Did you find this content helpful?

Want to help us improve this content?

We'd prefer it if you saw us at our best.

Pega Academy has detected you are using a browser which may prevent you from experiencing the site as intended. To improve your experience, please update your browser.

Close Deprecation Notice