11g Release 7 (11.1.7)
Part Number E20373-08
Home
Contents
Book
List
Contact
Us
|
Oracle® Fusion Applications Sales Implementation Guide 11g Release 7 (11.1.7) Part Number E20373-08 |
Home |
Contents |
Book List |
Contact Us |
 Previous |
 Next |
This chapter contains the following:
Define Sales Prediction Configuration
Select Model Entities and Attributes
Oracle Fusion Sales Prediction Engine enables organizations to capture and leverage predictive sales intelligence. Predictive models analyze sales data to evaluate buying patterns. After the evaluation of model results, lead generation can be scheduled to disseminate lead recommendations to users. Each lead recommendation includes win likelihood, average expected revenue, and sales cycle duration.
The key features of Oracle Fusion Sales Prediction Engine include the following:
Application Home Page: The application home page provides sales analysts with a summary of the prediction model results. Additionally, reports on the dashboard provide overviews of model performance and leads adoption.
Predictive Model Learning: Model learning uncovers hidden selling patterns in complex business environments. Salespeople can replicate sales success using historical insight generated through model training.
Rule-based Recommendations: When new products are launched or during initial deployment, historical data is sparse. In such cases, the sales analyst can create customer-, industry-, or product-specific rules to drive the recommendation of new products.
Higher Lead Adoption Rate: By utilizing a combination of data mining, segmentation, prediction and business rules, Sales Prediction Engine ensures that the recommendations have a higher likelihood of being converted to a win.
Analyze Recommendation Performance: Built-in analytical reports verify whether the recommendations are being accepted by the sales organization. If adoption is low, then the predictive models can be fine-tuned by selecting different attributes for model learning or editing the rules. Simulation can then be performed to assess the impact of these new changes before publishing new recommendations.
Usage across CRM Applications: The recommendations generated are integrated with and can be viewed in other CRM applications and features, such as Opportunity Landscape, Customer Center, Territory Management, and Lead Qualification. In Opportunity Landscape, the recommendations can be ranked and qualified as leads after being reviewed. In Customer Center, recommended products display next to a customer, and the rationale for the recommendations is provided in the context of creating a deal for the customer. Territory managers can use the metrics output to set sales targets by territory and assign them to salespeople. The metrics ranking determines whether leads can be qualified in Lead Qualification.
To run the Oracle Fusion Sales Prediction Engine in Oracle Fusion Applications Customer Relationship Management (CRM), perform the following post-installation tasks if you deployed Oracle Business Intelligence Applications and have created the Oracle Business Analytics Warehouse. For information on deploying and setting up Oracle Business Intelligence Applications, refer to the Oracle Fusion Middleware Configuration Guide for Oracle Business Intelligence Applications.
However, if you deployed only Oracle Transactional Business Intelligence, you need not perform these steps to run the Oracle Fusion Sales Prediction Engine.
You can create the Data Warehouse objects using the Sales Predictor Repository Creation Utility (RCU). To run the Sales Predictor RCU , ensure that the Oracle Business Intelligence Application (OBIA) Data Warehouse database and the related schema including database objects such as tables, are available. The Sales Predictor RCU creates Sales Predictor related Data Warehouse database objects such as Oracle Data Mining tables, views, packages, Oracle Real-time Decisions (RTD) Inline Service Processing tables, and the purge package in the existing OBIA schema.
Initiate the Sales Predictor RCU following these instructions.
Access the rcuBIZSPApps.zip file from the following location, and extract its contents to a local directory.
In Windows NT, the location is FAINTEG_BASE/fainteg/shiphome/rcu/nt/rcuBIZSPApps.zip
In Linux, the location is FAINTEG_BASE/fainteg/shiphome/rcu/linux/rcuBIZSPApps.zip
Run the following command pointing to the BIN folder within the local directory:
In Windows NT, use rcu -variables BI_SCHEMA_NAME=<OBIA Schema name>
In Linux, use ./rcu -variables BI_SCHEMA_NAME=<OBIA Schema name>
Note
<OBIA Schema name> refers to the name of the OBIA schema that is used, and is an input parameter for the Sales Predictor RCU.
The Sales Predictor RCU wizard appears.
On the Welcome page, click Next and on the Create Repository page, ensure that the default option Create is selected and click Next.
On the Database Connection Details page, provide the following information and click Next.
Host Name: Name of the server where the database is located.
Port: The database port number.
Service Name: The service name of the database.
Username: SYS. It is the user name associated with an administrative role.
Password: Password used in combination with the user name to access the database.
Role: SYSDBA. It is the role with administrative access rights.
The provided information is processed through a prerequisite check.
On the confirmation dialog box, click OK.
On the Select Components page, select the Oracle Application Components, and click Next.
On the confirmation dialog box, click OK.
On the Schema Passwords page, ensure that the Use same passwords for all schemas option is selected. Selecting this option provides the password used with the existing OBIA Schema Name.
Enter the password again to confirm it, and click Next.
On the Map Tablespaces page, click Next and on the confirmation box that subsequently appears, click OK.
On the Summary page, review the database information provided until this point. If necessary, click Back to change details in the previous pages.
Click Create to create the Data Warehouse objects. The Completion Summary page confirms the successful creation of the objects.
The Data Warehouse requires a Java Naming and Directory Interface (JNDI) data source connection named DWDS that points to the Online Analytical Processing (OLAP) database residing on Oracle BI server. To create the data source using the RTD WebLogic Server console, follow these instructions.
In the WebLogic Server console, open Services - JDBC - Data Sources and click New.
On the JDBC Data Source Properties page, provide the following details and click Next.
Name: Fusion_OLAP_DS
JNDI Name: DWDS
Database Type: Oracle
Database Driver: Oracle Driver (Thin) for Instance connections
On the Transaction Options page, ensure that the default property Supports Global Transactions is selected, and click Next.
On the Connection Properties page, provide the following values, and click Next.
Database Name: The Unique System ID (SID) of the database
Host Name: The name of the computer that hosts the database
Port: The port number of the database
Database User Name: User credential to access the database
Password: The password used in combination with the Database User Name to access the database
On the Test Database Connections page, review the details provided until this point, test the connectivity to the database, and click Next.
Select the Oracle BI Server where you want to make the data source available, and click Finish.
To enable connectivity to Data Warehouse, you must set the value for the profile option.
Note
You can set the value for this profile option using Applications Core Setup, if you have roles allowing access to do so. The Application Implementation Administrator abstract role provides the necessary access.
Sign in to the Oracle Fusion Applications Core Setup.
Under the Tasks menu on the left side of the page, click Manage Administrator Profile Values. The Manage Administrator Profile Values tab appears.
In the Profile Option Code field, enter ZCA_WAREHOUSE_ENABLED_BI and click Search. The profile option appears in the search results.
In the Profile Values region, select the result item associated with the searched profile option, and under the Profile Value column, set the value to Yes.
Click Save.
The Sales Predictor Inline Service within RTD uses the profile option to point to the Data Warehouse tables.
You can point RTD to the Data Warehouse in one of the following ways:
Restart the RTD application server. The Sales Predictor Inline Service is reloaded and points to the Data Warehouse.
Manually redeploy the Sales Predictor Inline Service if restarting the RTD application server does not work. Before you manually redeploy, ensure that the following prerequisites are met:
You have roles allowing access to deploy the Sales Predictor Inline Service.
Java Development Kit (JDK) 1.6 or higher version is available and running on the same server
You must have access to the command line tool zip file rtd-deploytool-11.1.1.zip. The zip file resides within the RTD client zip file (rtd_client_11.1.1.3.0.zip), which is available in the BI_MW_HOME/Oracle_BI1/clients/rtd directory.
To manually redeploy the Sales Predictor Inline Service, follow these instructions.
Extract the contents of the file rtd_client_11.1.1.3.0.zip to a local directory.
In the local directory, go to the folder ./client/CommandLineDeploy, locate rtd-deploytool-11.1.1.zip and extract its contents to a folder.
In that folder, locate ./OracleBI/RTD/deploytool folder and within that folder, open a command prompt terminal.
Note
Ensure that the JDK classpath is set for the command prompt terminal.
Run the command: java -jar deploytool.jar -deploy -server <Server Host> -port <Port>
-terminateSessions true <Full path of Directory/ Zip File>.
When prompted, provide the user name and password to connect to the RTD server.
The message Deploymentstateid: id. Deployed SPE_ILS.zip to server port in state: Development appears indicating completeness of deployment of the Sales Predictor Inline Service.
The Oracle Fusion Sales Prediction Engine can also use data from the following Data Warehouse entity tables to make more accurate predictions:
Assets
Service Agreements
Orders
Also, it is necessary to load either Assets or Orders tables into the corresponding Data Warehouse table. Once the data in the Data Warehouse entity tables are ready, you can go to the Schedule Predictive Model Training page to run the model training process.
For more information on OBIA, see Oracle Fusion Middleware Configuration Guide for Oracle Business Intelligence Applications.
The Oracle Fusion Sales Prediction Engine provides configuration parameters that you can edit to influence how the application works. These configuration parameters control how recommendations are generated and displayed in other applications.
The configuration parameters are listed in the following table.
|
Configuration Parameter |
Default Value |
Description |
|---|---|---|
|
displayModelBasedRecommendations |
True |
When this is set to True, model-based recommendations are displayed in consuming applications. |
|
eligibilityMinEligibleNum |
0 |
Sets the minimum threshold for number of recommendations eligible for each customer. If eligible recommendations are lesser than the threshold defined here, Sales Prediction Engine requests more recommendations from InLine Service (ILS). This parameter applies only when leads are not eligible. |
|
eligibilityNumRecommendationsILS |
50 |
Indicates the number of recommendations to request from ILS when the number of eligible recommendations is lesser than eligibilityMinEligibleNum. This parameter applies only to the Order Capture eligibility rules. |
|
enableAvgWinRateRecommendations |
True |
When set to True, recommendations based on average win rates are displayed in consuming applications. This parameter applies only to the Order Capture eligibility rules. |
|
enableEligibilityRules |
True |
When set to True, marks leads in the staging table. Indicates whether to apply Order Capture eligibility rules. When set to False, it disables the parameters eligibilityMinEligibleNum and eligibilityNumRecommendationsILS. |
|
leadSalesChannel |
Null |
The selected value is updated in the SALES_CHANNEL in the lead staging table for leads customization. During implementation, you can customize the ILS with new values. |
|
leadSourceCode |
Null |
The selected value is updated in the SOURCE_CODE in the lead staging table for leads customization. During implementation, you can customize the ILS with new values. |
|
numberOfTopDrivers |
3 |
Defines the number of top drivers to return for each recommended product. The values can range from 0-5. |
Oracle Fusion Sales Prediction Engine leverages the power of predictive analytical models to identify patterns and correlation of data for the purpose of identifying what products to consider positioning next to your customers. The application leverages multiple mathematical models in order to formulate the likelihood a given customer will purchase a specific product, the estimated revenue which can be expected, and the duration of the estimated sales effort.
After the statistical model generates against the historical sales data based on the selected entities and attributes, summary and detail reports show critical insights as to what customers buy and can be used to predict the right products for the right customers. You can then use these insights to refine the process of generating leads based on what the customers are more likely to buy. Moreover, the same model can be used to predict the win likelihood of current opportunity revenue based on analysis of similar opportunities in the past. Also, product domain or market experts can write prediction rules to recommend products based on a set of rules conditions, utilizing all available customer profile attributes as well as other metrics.
The statistical analysis will identify which data has an influence in determining a likelihood to buy. After the statistical model generates against the historical sales data based on the selected entities and attributes, summary and detail reports show critical insights as to what customers buy and can be used to predict the right products for the right customers. As such, the decision regarding the selection of entities and attributes is critical. While the selection of certain entities and attributes may seem logical based on the awareness of sales behavior (customers in certain industries have a stronger affinity for certain products, for example), where there is uncertainty, the statistical model analysis will provide the necessary insight into whether patterns and correlation emerge. As such, as much available data as possible should be leveraged for the purpose of evaluation. Some factors which weight into the decision include the availability and accuracy of the data.
While selecting attributes, you must not select similar attributes for model training. For example, Annual Revenue and Annual Revenue Category. Your customer's annual revenue might range from 250,000 dollars to 50 million dollars. However, for efficient management, you decide to target only five customer types based on the Annual Revenue Category such as, Nano (250,000 dollars to 1 million dollars), Small (1-5 million dollars), and so on. The Annual Revenue Category uses Annual Revenue for this classification. Therefore, you must use either Annual Revenue or Annual Revenue Category but not both as they are redundant. Similar duplicate attributes could manifest in multiple areas such as Number of Employees and Company Size, Location and Zip Code, and so on.
Additionally, the application allows for the inclusion of expert insight from product management and sales and marketing operations. These expert insights can be captured via prediction rules. The same data made available to and leveraged by the predictive model, is also available for rule authoring.
Your company sells a service that appeals mostly to larger companies, and another service that targets smaller customers. If a customer purchased one of your product packages, then the customer already has all service needs covered by the package. You want to know, given a product recommendation, if credit score, asset, and customer size are important predictors when it comes to recommending this particular product.
You select the following entities and attributes:
Customer Profile
Annual Revenue
Credit Score
Customer Size Code
Past Purchased Products or Services
Assets and Service Contracts
These entities and associated attributes entail the data available to the enterprise which the predictive models can evaluate for identifying correlation, and which you can use to create prediction rules. Over time, you can further refine the selections based on availability of data and the cost to integrate that data for evaluation.
