Artificial intelligence-based opportunity insights
Pega Sales Automation uses decisioning capabilities to provide predictive insights for opportunities.
Opportunity insights are displayed in the opportunity record for each opportunity. The Opportunity insights widget is dynamic and responds to changes, such as stage changes and changes in customer activity or contact growth.
Opportunity insights workflow overview
Pega Sales Automation uses separate strategies for business and individual opportunities. The strategies are used to drive the insights that are displayed as opportunity AI Insights and they are used to take periodic predictor snapshots.
The strategy (B2B or B2C) runs all three model types (move to next stage, opportunity win, and win date), distinguishing them by using labels that are mapped to the issue and group hierarchy. For the opportunity win and move to next stage models, the strategy also evaluates a model without predictors (opportunity win base propensities) to establish a base propensity for benchmarking.
Historical data and adaptive learning
Pega Sales Automation uses self-learning adaptive models to generate opportunity predictions. This approach is based on core decision management capabilities and provides the flexibility to add and remove predictors as your needs change.
- Historical data
- The adaptive model provides a set of key predictors that are drawn from an
analysis of data from actual production environments. Production data was used
to create weekly snapshots for each closed opportunity over a two-year period.
Over 2,000 opportunities were used to create the weekly snapshots and
approximately 75,000 records were used to define the key predictors and train
the adaptive models.
The following tables include the predictors provided in the adaptive model for Pega Sales Automation and Pega Sales Automation for Financial Services:
Pega Sales Automation adaptive model predictors
B2B opportunity B2C opportunity StageDuration StageDuration ActiveDays ActiveDays OpportunitySource OpportunitySource ContactGrowthPast30Vs90Days PrimaryContact - Age ReceivedUnique30Vs90 PrimaryContact - Gender ReceivedTotal30Vs90 PrimaryContact - Marital status SentUnique30Vs90 PrimaryContact - HouseholdMemberRole SentTotal30Vs90 PrimaryContact - ValidPhone AllUnique30Vs90 PrimaryContact - ValidEmail AllTotal30Vs90 CountOfCIsPast30Vs90Days CountOfCIsPast30Vs90Days StageSequence OrgDownloadActivity30Vs90Days SalesType OrgSubscribeActivity30Vs90Days OrgWebsiteActivity30Vs90Days OrganizationIndustry OrganizationRevenue StageSequence SalesType Pega Sales Automation for Financial Services adaptive model predictors
B2B opportunity B2C opportunity ActiveDays ActiveDays AllTotal30Vs90 Age (months or years in business) AllUnique30Vs90 AllTotal30Vs90 AnnualRevenue AllUnique30Vs90 ContactGrowthPast30Vs90Days AnnualIncome CountOfClsPast30Vs90Days ContactGrowthPast30Vs90Days CurrentAssets CountOfClsPast30Vs90Days EstimatedCreditScore CurrentAssets LoanAmount EstimatedCreditScore MonthlyDebtToIncomeRatio LoanAmount MonthsInBusiness MonthlyDebtToIncomeRatio NumberOfEmployees NoOfAccounts OpportunitySource NoOfHouseholdMembers OrganizationIndustry OpportunitySource OrgDownloadActivity30Vs90Days pyPostalCode OrgSubscribeActivity30Vs90Days ReceivedTotal30Vs90 OrgWebsiteActivity30Vs90Days ReceivedUnique30Vs90 PreviousYearGrowth SentTotal30Vs90 pyPostalCode SentUnique30Vs90 ReceivedTotal30Vs90 StageDuration ReceivedUnique30Vs90 StageSequence SentTotal30Vs90 TotalOutstandingDebt SentUnique30Vs90 ValueOfCollateral StageDuration StageSequence TotalOutstandingDebt ValueOfCollateral - Adaptive learning
- The OpportunityInsights job schedule runs daily to execute a data flow that makes a call to a decision strategy. The decision strategy contains all of the adaptive models and runs on all the open opportunities to capture the data that is required by the models. The decision strategy uses the standard Delayed Learning cache.
- When an opportunity is closed, the application runs the crmOnOpportunityChange declare trigger. The trigger executes a response strategy from a data flow to fetch the data for relevant decisions and train the applicable models. You can use the same decision strategy at any time to evaluate an opportunity and return propensities.
Opportunity insights architecture
Review the following adaptive models architecture concepts:
- Predictors
- Strategy models
- Data pages
- Data flows
- Strategies
- Adaptive models
Predictors
- Probability to move to next stage
Adaptive models predict the likelihood that an opportunity will move from the current stage to the next stage. Pega Sales Automation uses the average number of all opportunities that have moved from the current stage to the next stage as the base propensity. The difference between the likelihood that an opportunity will move and the base propensity is an indicator of how you are progressing with the opportunity.
- Win probability
Adaptive models predict the likelihood of winning an opportunity. Pega Sales Automation uses the average number of all won opportunities for a given stage as the base propensity. The difference between the likelihood that you will win an opportunity and the base propensity is an indicator of how you are progressing with the opportunity.
- Close date
Adaptive models predict the quarter (for B2B) or the days (0-60, for B2C) when an opportunity is most likely to close. Pega Sales Automation compares the target date range that is set by the sales representative and the predicted closing quarter/days to indicate whether the opportunity close date is earlier than expected, on time, or delayed.
Strategy models
- Opportunity win model
Prediction for this model is: will this opportunity ever be won? The input predictor range should be as complete as possible. B2B and B2C opportunities have different predictors.
- Opportunity win base propensity model
This model does not use predictors. Instead, the model uses an opportunity stage as the context to provide the base propensity of winning an opportunity in the current stage.
- Move to next stage model
Prediction for this model is: will this opportunity ever move to a higher stage? When an opportunity moves from the current stage to the next stage, the application sends a positive, one-response to all opportunities in the Adaptive Decision Manager (ADM) data cache. Pega Sales Automation also takes a snapshot of the previous stage. The response is filtered by using an additional Decision Data Store (DDS) data set. The response strategy for the move to the next stage model filters out the decision results for stages that have already been marked as positive. It then determines whether the current stage is higher than the stage in the snapshot and returns only the decision results for which this is true.
B2B and B2C opportunity have different predictors.
- Move to next stage base propensity model
This model does not use predictors. Instead, the model uses an opportunity stage as the context to provide the base propensity of moving from the current stage to the next stage.
Move to the next stage model 
- Win date model
This data model supports separate models for the following outcomes:
Win date model outcomes
B2B opportunity B2C opportunity Will this opportunity be won in 0-90 days from now? Will this opportunity be won in 0-5 days from now? Will this opportunity be won in 90-180 days from now? Will this opportunity be won in 5-10 days from now? Will this opportunity be won in 180-270 days from now? Will this opportunity be won in 10-15 days from now? Will this opportunity be won in 270-360 days from now? Will this opportunity be won in 15-20 days from now? Will this opportunity be won in 20-25 days from now? Will this opportunity be won in 25-30 days from now? Will this opportunity be won in 30-35 days from now? Will this opportunity be won in 35-40 days from now? Will this opportunity be won in 40-45 days from now? Will this opportunity be won in 45-50 days from now? Will this opportunity be won in 50-55 days from now? Will this opportunity be won in 55-60 days from now? Pega Sales Automation uses propositions (different for B2B and B2C opportunities) in a Decision Data shape to model the date ranges. The propositions have both a minimum and maximum days attribute. If you require more granularity, you can edit the propositions to meet your needs and to create a smoother display for the dashboard widget.
- Win date base propensity model
This model does not use predictors. Instead, the model uses an opportunity stage as the context to provide the base propensity of winning an opportunity in a specified time frame.
Capture response strategy for B2B opportunity 
Capture response strategy for B2C opportunity 
Data pages
Opportunity insights use the D_PredictSAOpportunity data page.
- For Pega Sales Automation, review the
D_PredictSAOpportunity data page.
The Analytics widgets in the opportunity run in the context of the D_PredictSAOpportunity data page. This data page has the SAPredictOpportunity activity as a data source, which runs the SAPredictOpportunity data flow. The data flow fetches the precalculated predictors using a data set. The data flow sets the predictors on opportunity case and uses the EvaluateOpportunity strategy of B2B/B2C opportunity to predict the propensity to move to the next stage, to win an opportunity, and to predict the close date quarter.
- For Pega Sales Automation for Financial Services, review the
D_PredictSAOpportunity data page.
This data page populates the propensity for an Opportunity case. Analytics widgets of the opportunity insights run in the context of the D_PredictSAOpportunity data page. This data page has the SAPredictOpportunity activity as a data source, which runs the PopulatePredictors activity. The PopulatePredictors activity replaces the following activities: GetContactGrothRatio, GetEmailActivityRatio, GetTrendsDataRatio, and GetCIRatio, which are available in the Pega Sales Automation application. When there are multiple products specified, the PopulatePredictors activity iterates all of the products propensity, but displays the least propensity model. This workflow is applicable only for the credit and debit product types.
Data flows
- StoreOpportunitySnapshots
The solution uses the StoreOpportunitySnapshots data flow during the initial training of the models by using the business opportunity data that is fetched from the internal production data. This data flow converts each record from the PegaCRM-Data-SFA-Predictors class into opportunity objects and then routes them to the EvaluateOpportunity strategy. In the data flow, the mode for the EvaluateOpportunity strategy is set to Make decision and store data for later response capture.
- TrainFromHistory
The input for TrainFromHistory comes from the RD OpportunityStages, which fetches one record per business opportunity from the predictors’ data table, sorted by maximum stage. This data flow calls the OpportunityClosed and MovedToNextStage data flows.
- StoreIndvOpportunitySnapshots
- The solution uses the StoreOpportunitySnapshots data flow during the initial training of the models by using the individual opportunity data that is fetched from the internal production data. This data flow converts each record from the PegaCRM-Data-SFA-Predictors class into opportunity objects and then routes them to the EvaluateOpportunity strategy. In the data flow, the mode for the EvaluateOpportunity strategy is set to Make decision and store data for later response capture.
- TrainIndvOppFromHistory
- The input for TrainFromHistory comes from the RD OpportunityStages, which fetches one record per individual opportunity from the predictors data table, sorted by maximum stage. This data flow calls the OpportunityClosed and MovedToNextStage data flows.
- OpportunityClosed
The OpportunityClosed data flow calls the CloseOpportunity strategy, which captures responses for decisions in the past period.
- MovedToNextStage
The MoveToNextStage data flow calls the HandleNextStageResponses strategy, which is the core strategy for training the PredictNextStageModels adaptive model. The available responses depend on whether an opportunity moves up or down from the current stage.
- SnapshotOneOpportunity
The SnapshotOneOpportunity data flow reuses the EvaluateOpportunity strategy, which is used to train the model during bulk processing. This data flow runs on a daily basis and captures all predictors for the opportunity each time it runs.
- SAPredictOpportunity
The SAPredictOpportunity data flow reuses the EvaluateOpportunity strategy to get the analytic results for the opportunity.
To view the details for each data flow, perform the following steps:
- In the navigation pane of Dev Studio, click .
- To open the data flow record, click a data flow name.
Strategies
The following are the opportunity insights strategies:
- EvaluateOpportunity
- HandleNextStageResponses
To view the details of each strategy, perform the following steps:
- In the navigation pane of Dev Studio, click .
- To open a strategy record, click a strategy name.
Adaptive models
Each adaptive model has predictors, context, and outcomes that you must configure before you can train the models to predict outcome propensities based on your use cases. Base propensity models do not have any predictors, but they have the OpportunityStage property in their context so you can train different models for each stage.
Outcome propensities are configured for the following models:
- PredictiveMoveNextStage
- BaseWinModel
- PredictWin
- PredictCloseDate
To view the details of each model, perform the following steps:
- In the navigation pane of Dev Studio, click .
- To open a model record, click a model name.
Previous topic Voice AI model training Next topic Artificial intelligence-based sales coach