1. Manuals
  2. Brands
  3. CTS Manuals
  4. Gateway
  5. FWR5-3105SFP-CW-AC-DR Series
  6. Manual

CTS FWR5-3105SFP-CW-AC-DR Series Manual

Triple play gateway
Hide thumbs
Table of Contents

Advertisement

Quick Links

User Guide for Predictive Analytics Cloud Image - Trial Edition
SAP Store – Trial Edition

Advertisement

Table of Contents
loading
Need help?

Need help?

Do you have a question about the FWR5-3105SFP-CW-AC-DR Series and is the answer not in the manual?

Questions and answers

Subscribe to Our Youtube Channel

Related Manuals for CTS FWR5-3105SFP-CW-AC-DR Series

Summary of Contents for CTS FWR5-3105SFP-CW-AC-DR Series

  • Page 1 User Guide for Predictive Analytics Cloud Image - Trial Edition SAP Store – Trial Edition...
  • Page 2 Table of Contents INTRODUCTION ............................3 PREREQUISITES ............................. 3 SYSTEM ACCESS ........................... 3 PREDICITIVE SCENARIOS (FRONT-END COMPONENTS) ..............5 Banking ..............................5 Customer Attrition Analysis ........................5 Consumer Products ..........................10 Brand Sentiment and Sales Analysis .....................10 Demand Data Analysis ...........................12 Product Fulfillment and Optimization ......................14 Finance ..............................18 Company Performance Analysis ......................18...

  • Page 3: Introduction

    1 INTRODUCTION Users learn how to use SAP Predictive Analytics tools in the context of SAP HANA with a few pre-built scenarios in this trial edition for the cloud. Sample data is available so that the users can understand how the tools could be utilized.
  • Page 4 Predictive Analytics VHCALHDBDB master RDSPAUSER password Predictive Analytics VHCALHDBDB RDS_CRM_DS master for Sales&Markeing password USER use cases Connect to Remote Desktop Start Remote Desktop by following the menu Start > All Programs > Accessories > Remote Desktop Connection Now the Remote Desktop is launched. Enter the following information: ...

  • Page 5: Predicitive Scenarios (Front-End Components)

    Now enter the data source name, data source description as vhcalhdbdb and Server:Port as vhcalhdbdb:30015 Click connect Enter user id and password as RDSPAUSER and master password NOTE: Location of LUMs files on the instance 1. Once the instance is created and you have done a remote desktop, you get access to the files on the remote desktop.
  • Page 6 For more information on populating SAP_RDS_PA_BANK.CUST_ATTRITION, see the SAP HANA Deployment for Banking on SAP Predictive Analytics Content Adoption rapid-deployment solution (VD2) configuration guide that is part of this solution. Choose Analyze BUS_PARTNER is the only column with a Key value of 1. This value is generated by SAP Predictive Analytics that identifies this column as the Primary Key of the table On the next screen, enter Attrition as the Target Variable and make BUS_PARTNER the Excluded Variable...
  • Page 7 From Generation Options, select Decision for the Generation Options Leave Apply as the Mode Select where the generated output is stored by making the following entries in the Results Generated by the Model section: a. Select Database b. Browse and populate the dialog box with your SAP HANA instance c.
  • Page 8 c. Select Properties/Column Selection/Features for the independent columns (variables) for analysis. By default, the following are enabled:  Average Tenure  Average Income  Average Investment Amt d. In the Properties/Column Selection/Target Variable, choose the dependent column (variable) for analysis. By default, Attrition is enabled e.
  • Page 9 c. Select Properties/Column Selection/Features and choose the independent columns (variables) for analysis. d. Select: Average Tenure, Average Income, and Average Investment Amt identical to saved model Adjust the HANA Writer Data writer component a. Select Configure Settings b. Specify Schema Name, Table Type, and Table Name as appropriate for your site Choose Run to execute the scenario Choose Yes to switch to the Results view for verifying the execution results.

  • Page 10: Consumer Products

    4.2 Consumer Products For the Consumer products industry, we have pre-built scenarios for 3 use cases such as Brand sentiment and sales analysis, Demand data analysis, Product fulfillment and Optimization. Depending on the use case and the functionality that we are analyzing, we have picked up either the Automated Analytics or the Expert Analytics approach.
  • Page 11 b. For training a model, which is not based on event, use SALES_DATE as predictor variables and exclude the rest of the variables On the next screen, name the Model: a. P1_EVENT: If you applied “PRODUCT 1” filter on PRODUCT_NAME and kept SMC1, SMC2 and HLYDSSN as predictor variables b.

  • Page 12: Demand Data Analysis

    From Generations Options, select Predicted Value Only Use Apply as the Mode To specify where the generated output is stored, enter the following in Results Generated by the Model section: Select Database Browse and enter the SAP HANA instances and logon for the <Domain User> account in the dialog box.
  • Page 13 Select Start Year g. Select Start Periods h. Select Periods to Predict Adjust the HANA Triple Exponential Smoothing Advanced Properties (Optional) a. Select Alpha, Beta, and Gamma Adjust the HANA Writer Data writer component a. Select Configure Settings b. Specify Schema Name, Table Type and Table Name as appropriate for your site. Keep the default configuration whenever possible.

  • Page 14: Product Fulfillment And Optimization

    Choose OK to switch to the Results view for verifying the execution results. Select available charts icon to display the results in charts. Switch to Visualize panel and Select Components selector to display results in charts. Switch to Compose panel and Select Components selector to display results in storyboards. Product Fulfillment and Optimization In this use case, we are identifying the different clusters of population and their buying trends of products.
  • Page 15 a. Launch Expert Analytics in SAP Predictive Analytics. Open menu File and choose Import to folder and import or if the LUMS file is already imported browse through the Documents list for Consumer_Product_InterQuartile_Analysis.lums or Consumer_Product_InterQuartile_Analysis_DSiM.lums (for SAP Demand Signal Management data) file.
  • Page 16 Select Filter in the analysis panel a. Choose Configure Settings b. Select Row Filter and update the value and Validate For Consumer_Product_Timeseries_Analysis.lums, adjust the R-Triple Exponential Smoothing Algorithm Component a. Choose Configure Settings b. Select Output Mode: Forecast c. Select Period to Predict: 10 d.
  • Page 17 Select Filter in the analysis panel a. Choose Configure Settings b. Select Row Filter and update the value and Validate Adjust the SAP HANA Apriori Algorithm Component a. Choose Configure Settings b. Select Apriori Type: Apriori Lite c. Select Item Column: Product Name d.

  • Page 18: Finance

    4.3 Finance For the Finance LoB, we have pre-built scenarios for 3 use cases such as Company performance analysis, Late payment management, Customer cash collection analysis. Depending on the use case and the functionality that we are analyzing, we have picked up either the Automated Analytics or the Expert Analytics approach. Basically for the Late Payment management use case, we have used the SAP HANA Live views for Finance as the data source and sample data sets are available for the same.

  • Page 19: Customer Cash Collection Analysis

    a. Launch Expert Analytics in SAP Predictive Analytics. Open menu File and choose Import to folder and import or if the LUMS file is already imported browse through the Documents list for Finance_Customer_Late_Payments_train.lums file. b. In the dialog box, enter the SAP HANA server details, your user name, and password. To verify the data, choose Prepare tab to ensure that the data has loaded properly Switch to the Predict panel to view the predictive model.
  • Page 20 REPAIR_DEBT_WITHHELD_1 DEBT_PAID_AFTER_COMPLETION_1 REPAIR_NOTICE_DATE_2 REPAIR_TYPE_2 REPAIR_DEBT_2_WITHHELD DEBT_PAID_AFTER_COMPLETION_2 REPAIR_TYPE_3 REPAIR_DEBT_WITHHELD_3 DEBT_PAID_AFTER_COMPLETION_3 REPAIR_NOTICE_DATE_3 TOTAL_REPAIR_DEBT_OUTSTANDING CONTACTED CONTACTED_BY_EMAIL CONTACTED_BY_HOME_VISIT CONTACTED_BY_LETTER CONTACTED_BY_LARGE_PRINT EMAIL_SUCCESS HOME_VISIT_SUCCESS LETTER_SUCCESS LARGE_PRINT_SUCCESS On the next screen, Summary of Modeling Parameters, select Generate The Model Overview screen then appears View the KI and KR values Go to the Next and view various Display Views.
  • Page 21 REPAIR_NOTICE_DATE_2 REPAIR_TYPE_2 REPAIR_DEBT_2_WITHHELD DEBT_PAID_AFTER_COMPLETION_2 REPAIR_TYPE_3 REPAIR_DEBT_WITHHELD_3 DEBT_PAID_AFTER_COMPLETION_3 REPAIR_NOTICE_DATE_3 TOTAL_REPAIR_DEBT_OUTSTANDING CONTACTED CONTACTED_BY_EMAIL CONTACTED_BY_HOME_VISIT CONTACTED_BY_LETTER CONTACTED_BY_LARGE_PRINT EMAIL_SUCCESS HOME_VISIT_SUCCESS LETTER_SUCCESS LARGE_PRINT_SUCCESS On the next screen, Summary of Modeling Parameters, select Generate Model Overview screen then appears View the KI and KR values Go to the Next and view various Display Views It is important to display Clusters Summary as it is necessary to know which Clusters are "good"...

  • Page 22: Manufacturing

    4.4 Manufacturing For the Manufacturing LoB, we have pre-built scenarios for 4 use cases such as Customer demand and inventory management, Overall equipment effectiveness, Asset breakdown analysis and Maintenance cost analysis. Depending on the use case and the functionality that we are analyzing, we have picked up either the Automated Analytics or the Expert Analytics approach.

  • Page 23: Overall Equipment Effectiveness

    uncertain these values are equal, choose Execute the document icon on the far left-hand side of the screen (PREFERENCES_MFG_SALES_PARAMETER_VALUES) and choose Yes when asked Do you want to switch to the Results view? A matrix of the input table appears. Scroll to find the values for the parameter to ensure that they are equal.

  • Page 24: Asset Breakdown Analysis

    you want to switch to the Results view? A matrix of the input table appears. Scroll to find the values for the parameter to ensure that they are equal. Note that for the Explosion values (ID starting with ‘E’) the values of the node below the one being listed in the row is displayed Note that for the Single values (ID starting with ‘S’) the values of the nodes above the one being listed in the row is displayed...
  • Page 25 Select the Prompts tab. Add prompt using data set column from data source. Set ‘Default Value’ from the data set as needed. Prompt Data Set Column Selected_Equipment EQUIPMENT Selected_Class CLASS Selected_Manufacturer ASSETMANUFACTURERNAME Select the Filters tab. Add condition data set column equal to prompt. Keep Only Records option to Match All of the Following.
  • Page 26 Select Next. Save the data manipulation to SAP HANA for use in predictive modeling Attribute Data Manipulation EQUIPMENT DM_MAINTBREAKDOWN_EQUIPMENT CLASS DM_MAINTBREAKDOWN_CLASS MANUFACTURER DM_MAINTBREAKDOWN_MANUFACTURER Repeat these steps to create data manipulation for each attribute. Result: The Data Manipulation is ready for use in predictive model development. Continue to the next section for information on developing a predictive model.
  • Page 27 In the Selecting Variables screen, set BREAKDOWNDATE as the TIME variable and NMBROFACTUALMAINTOBJECTBRKDWNS as the TARGET variable. Exclude the all other variables from the analysis. You can keep the Predictive Analytics selected to Last Training Date or choose your own. Select Next Set Number of Forecasts: to desired number of months, for example 12, for 12 monthly forecast If desired, select Advanced button to set additional parameters.

  • Page 28: Maintenance Cost Analysis

    Data Type: Data Base Folder: HANA ODBC connection File/Table: Attribute Model EQUIPMENT SAP_RDS_PA_MFG.SII_MODEL_BREAKDOWN_EQUIPMENT CLASS SAP_RDS_PA_MFG.SII_MODEL_BREAKDOWN_CLASS MANUFACTURER SAP_RDS_PA_MFG.SII_MODEL_BREAKDOWN_MANUFACTURER Result: A maintenance breakdown time series forecasting analysis using HANA Live maintenance breakdown reports data is saved to SAP HANA. Maintenance Cost Analysis In this use case, we focus on identifying the maintenance costs for assets based on historic data and trends.
  • Page 29 Prompt Data Set Column Selected_ActivityType MAINTENANCEACTIVITYTYPE Selected_Equipment EQUIPMENT Selected_Funclocation FUNCTIONALLOCATION Selected_Manufacturer ASSETMANUFACTURERNAME Selected_OrderType MAINTENANCEORDERTYPE Selected_PlannerGroup MAINTENANCEPLANNERGROUP Select the Filters tab. Choose New condition data set column equal to prompt. Keep Only Records option to Match All of the Following. Prompt Data Set Column Selected_ActivityType MAINTENANCEACTIVITYTYPE...
  • Page 30 Set field Type column to ‘continuous’ Attributes Measures Type columns ACTIVITYTYPE PLNDMAINTCOSTINDISPLAYCRCY_E continuous EQUIPMENT PLNDMAINTCOSTINDISPLAYCRCY_E continuous FUNCLOCATION PLNDMAINTCOSTINDISPLAYCRCY_E continuous MANUFACTURER PLNDMAINTCOSTINDISPLAYCRCY_E continuous ORDERTYPE PLNDMAINTCOSTINDISPLAYCRCY_E continuous PLANNERGROUP PLNDMAINTCOSTINDISPLAYCRCY_E continuous Select Next. Save the data manipulation to SAP HANA for use in predictive modeling Attribute Data Manipulation ACTIVITYTYPE...
  • Page 31 Choose Next to continue. Enter the attribute prompt value to filter the data set, for example ACTIVITYTYPE, EQUIPMENT, FUNCLOCATION, MANUFACTURER, ORDERTYPE, PLANNERGROUP After entering the value, choose OK to begin modeling Choose Analyze and a description for the data set appears. Choose Next when the data description accurately describes the data The data set description was previously completed during the data manipulation steps.
  • Page 32 FUNCLOCATION DM_MAINTCOST_FUNCLOCATION MANUFACTURER DM_MAINTCOST_MANUFACTURER ORDERTYPE DM_MAINTCOST_ORDERTYPE PLANNERGROUP DM_MAINTCOST_PLANNERGROUP Generation Options Generate: choose ‘Only First Forecast Column and the Error Bars’ Results Generated by the Model Data Type: Database Folder: HANA ODBC connection Data: Attribute Model Result ACTIVITYTYPE SAP_RDS_PA_MFG.SII_RESULT_MAINTCOST_ACTIVITYTYPE EQUIPMENT SAP_RDS_PA_MFG.SII_RESULT_MAINTCOST_EQUIPMENT FUNCLOCATION SAP_RDS_PA_MFG.SII_RESULT_MAINTCOST_FUNCLOCATION MANUFACTURER...
  • Page 33 ORDERTYPE SAP_RDS_PA_MFG.SII_MODEL_MAINTCOST_ORDERTYPE PLANNERGROUP SAP_RDS_PA_MFG.SII_MODEL_MAINTCOST_PLANNERGROUP Result: A maintenance costs time series forecasting analysis using HANA Live maintenance costs reports data saved to SAP HANA.

  • Page 34: Portfolio & Project Management

    4.5 Portfolio & Project Management For the Portfolio & Project management LoB, we have pre-built scenarios for the use case Project Profitability analysis. Depending on the use case and the functionality that we are analyzing, we have picked up either the Automated Analytics or the Expert Analytics approach.

  • Page 35: Project Profitability Analysis

    Order Backlog" DM_PROJEC Kxen.Connector;Kxen. ConnectorsTable 2015-06-25 10:51:26 "Project T_TOTAL ODBCStore; <HANA Transaction ODBC DSN> Date - Aggregated to Project Level" DM_TS_PRO Kxen.Connector;Kxen. ConnectorsTable 2015-06-25 15:27:08 "Project JECT_TOTAL ODBCStore; <HANA Transaction ODBC DSN> Data - Selected Project Transaction Data for Time Series"...
  • Page 36 DM_PROJECT_SUMMARY Project transaction summary by project, customer, entity, bill-to DM_PROJECT_TOTAL Project transaction total by project, customer. DM_PROJECT_TRANSACTION_ACTIVE_BACKLOG Active project transaction by net backlog. DM_TS_PROJECT_TRANSACTION_PROJECTID Project transaction for time series analysis DM_TS_PROJECT_TOTAL Project transaction total for time series analysis Building the Classification/Regression Model From the home screen of SAP Predictive Analytics, select the Modeler section Select Create a Classification/Regression Model In the Select a Data Source window,...
  • Page 37 Results Generated by the Model Data Type: Text Files Folder: local folder Data: result_class_pref_ind_summary_active_adv.txt Select Apply After reviewing model results, choose Next. Choose Save/Export and choose Save Model Saving the Model Model Name: default Description: description of model Data Type: Text Files Folder: local folder File/Table: md_regression_preference_ind_summary_closed.txt Choose Save...
  • Page 38 In the Applying the Model screen Application Data Set Data Type: Data Base Folder: HANA ODBC connection Data: DM_PROJECT_TOTAL - select CLOSED = 0 Generation Options Generate: choose ‘Advanced Apply Settings’ – select all the options Mode: Apply Results Generated by the Model Data Type: Text Files Folder: local folder Data: result_seg_3_targets _summary_active_adv.txt...
  • Page 39 In the Selecting Variables screen, select EBIT_ON_BACKLOG, ORDER_BACKLOG as the Target Variable. Select PROJECT_ID, CUSTOMERID, BILL_TO_ID, EXECUTE_ENTITY to Excluded Variable. Select Next. Review Summary of Modeling Parameter to set additional setting. Select Generate. Engine runs the Training the Model. Review the Model Overview. In the Using the Model screen, select Display and review the resulting model by viewing Model Overview, Model Graphs, Contributions by Variables, etc.
  • Page 40 Choose Next to continue. Enter Select Project ID prompt values to filter the data set i.e. 3019767 After entering the value, choose OK to begin modeling Choose Analyze and a description for the data set appears. Choose Next when the data description accurately describes the data The data set description was previously completed during the data manipulation steps.
  • Page 41 Result: A regression analysis on order backlog profit forecast is created and saved. Expert Analytics - Visualization The solutions’ preconfigured content is provided in five LUMS format files. The LUMS files are dependent, in that you first generate the results dataset as describe earlier with Automated Analytics predictive modeling. Then you use these results files/tables as an input dataset for the LUMS files.

  • Page 42: Retail

    4.6 Retail For the Retail industry, we have pre-built scenarios for 3 use cases such as Market basket analysis, Customer loyalty programs, Store clustering. Depending on the use case and the functionality that we are analyzing, we have picked up either the Automated Analytics or the Expert Analytics approach. Basically for all 3 use cases, we have used the leading SAP application Customer activity repository as the data source and sample data sets are available for the same.

  • Page 43: Customer Loyalty Programs

    a. Launch Expert Analytics in SAP Predictive Analytics. Open menu File and choose Import to folder and import or if the LUMS file is already imported browse through the Documents list for Retail_Market_Basket_Analysis_CAR.lums file b. In the dialog box, enter the SAP HANA server details, your user name, and password. Verify the data a.
  • Page 44 Adjust the Clustering Customer/Review Period Algorithm Component a. Choose Configure Settings in the Clustering Customer/Review Period component b. Select the independent columns (variables) needed for cluster analysis. By default, Total Sales, Frequency of Visits, and Items Purchased are enabled c. Set Number of Clusters to a desired value. Adjust the Clustering Customers Last Year Algorithm Component a.

  • Page 45: Store Clustering

    Adjust the HANA K-Means Algorithm Component a. Choose Configure Settings in the HANA K-Means component b. Select the independent columns (variables) needed for cluster analysis. By default, Total Sales, Frequency of Visits, and Items Purchased are enabled c. Set Number of Clusters to a desired value. Adjust the HANA Anomaly Detection Algorithm Component a.
  • Page 46 Verify the data a. Choose Prepare panel to ensure that the data has loaded properly Switch to the Predict panel to view the predictive model. Adjust the HANA K-Means Algorithm Component a. Choose Configure Settings in HANA K-Means component b. Set Number of Clusters to a desired value. c.

  • Page 47: Sales & Marketing

    4.7 Sales & Marketing For the Sales & Marketing LoB, we have pre-built scenarios for 5 use cases such as Customer Segmentation, Market segmentation, Market campaign success, Product recommendation, Pipeline and revenue forecasting. Depending on the use case and the functionality that we are analyzing, we have picked up either the Automated Analytics or the Expert Analytics approach.

  • Page 48: Customer Segmentation

    Data Type: Text Files Folder: <location where metadata repository files are stored>, for example c:\MDR_S&M. Select OK Customer Segmentation In this use case we focus on the customer buying pattern and cluster them accordingly. Expert Analytics Using Logistics Information System tables (ERP) as the data source Select the LUMS file for Customer Segmentation.

  • Page 49: Market Segmentation

    c. Choose Number of Clusters and enter a desired value. Run the algorithm Choose Run to execute the scenario Choose OK to switch to the Results view to verify the execution results. Market Segmentation In this use case we focus on the different distribution and marketing channels and cluster accordingly to identify the business revenues.

  • Page 50: Market Campaign Success

    b. Select the Features and Category Columns needed for cluster analysis. c. Choose Number of Clusters and enter a desired value. Run the algorithm Choose Run to execute the scenario Choose OK to switch to the Results view to verify the execution results Market Campaign Success In this use case, we identify what particular marketing campaigns are successful and how to position, on what cluster of the customers.

  • Page 51: Product Recommendation

    Product Recommendation In this use case, we focus on identifying what products could be recommended to a particular customer based on similar buying trends and other historic facts. Automated Analytics Building the Rules Launch SAP Predictive Analytics From the home screen Choose the Modeler Section a.
  • Page 52 (Observe the Rules) (Sort on Lift and observe) Save a. Into the same directory as the spreadsheets b. File Name: RULES_FROM_II.txt Statistical Reports a. Observe the calculations Result: The Rules are now ready to be loaded into SAP Hana for subsequent queries. Loading Product Recommendation Rules into SAP HANA Launch Excel a.

  • Page 53: Pipeline And Revenue Forecasting

    Pipeline and Revenue Forecasting In this use case, we focus on how the pipeline could affect the sales revenues in the upcoming weeks, months and quarters. Automated Analytics Manipulating the Data Launch SAP Predictive Analytics Choose the Data Manager section Select Load an existing Data Manipulation In the Load existing Data Manipulation window, select your SAP HANA instance and connect using the <Domain User>...
  • Page 54 The data set description was previously completed during the data manipulation steps. You will not need to change anything in this window Validate Key, Order and Value columns definitions TIMEPERIOD column: Order = 1, Key = 1, Type = continuous. Choose Next to Selecting Variables screen In the Selecting Variables screen, set TIMEPERIOD as the TIME variable and NETAMOUNTINDISPLAYCURRENCY.as the Target variable.
  • Page 55 After reviewing model results, save this model to the SAP HANA schema SAP_RDS_PA_CRM Saving the Model Model Name: default Description: description of model Data Type: Data Base Folder: HANA ODBC connection File/Table: Scenario Model Sales Forecast Aggregated SAP_RDS_PA_CRM.SII_MODEL_SALES_AGGREGATED Sales Forecast by Sales SAP_RDS_PA_CRM.SII_MODEL_SALES_SALESORG_MONTHLY Organization Sales Forecast by Material...

  • Page 56: Telco

    4.8 Telco For the Telco industry, we have pre-built scenarios for 4 use cases such as Churn modeling and offer recommendation, Post-paid analysis, Rotational churn and Multi-SIM detection. Depending on the use case and the functionality that we are analyzing, we have picked up either the Automated Analytics or the Expert Analytics approach.
  • Page 57 or;Kxen.ODBC 16:57:48 Multi-SIM Store;<HANA Indicator " ODBC DSN> MultiSIMClassifiedC Kxen.Connect ConnectorsTabl 2015-01-21 "DM Multi- ustomerNeighbor or;Kxen.ODBC 16:58:09 Store;<HANA candidate ODBC DSN> first circle neighbors" SubscriptionHandset Kxen.Connect ConnectorsTabl 2015-01-21 "DM Filtered or;Kxen.ODBC 16:58:19 Subscription Store;<HANA Handset ODBC DSN> Filtered" SubscriptionHandset Kxen.Connect ConnectorsTabl 2015-01-21 "DM...
  • Page 58 Store;<HANA Usage SIM ODBC DSN> information" SubscriptionUsageS Kxen.Connect ConnectorsTabl 2015-01-21 "DM egment or;Kxen.ODBC 17:00:00 Customer Store;<HANA Subscription ODBC DSN> Usage Segment" EntitySubscription Kxen.Entity;Kx ConnectorsTabl 2015-01-21 EntitySubscri en.ODBCStore 17:00:59 ption ;<HANA ODBC DSN>;SAP_R DS_PA_TELC O.SUBSCRIPT ION;SUBS_ID EntitySubscriptionPo Kxen.TimeSta ConnectorsTabl 2015-01-21 "Default pulation mpedPopulatio 17:01:09...

  • Page 59: Churn Modeling And Offer Recommendation

    In the Data Manager window, validate each explorer objects Data Manipulation, Entity, Time-stamped Population and Analytical Record by open and saving it. Result: The Metadata repository objects are ready for use in predictive model development. Continue to the next section for information on developing a predictive model. Churn Modeling and Offer Recommendation In this use case, we identify who are the pre-paid customers likely to churn and how we can retain them by providing competitive retention offers.
  • Page 60 After defining the aggregation periods, define the End Date for the aggregation. We recommend developing a Prompt/Argument called Last_DateTime to represent the end of your aggregation period. Using Last_DateTime allows the data set to be continuously used for scoring purposes Select the Filters and Pivot Settings tab to create your aggregates for multiple types of events In the Pivot section, select the Search (binocular icon) then from the whole data set to get the category occurrences in the data...
  • Page 61 Select Next If desired, unselect Enable Auto-Selection Choose Generate to build your customer churn model with SAP Predictive Analytics After reviewing model results, save this model as SII_CHURN_MODEL to the SAP HANA schema SAP_RDS_PA_TELCO Result: A customer churn model built using customer demographic and usage data saved to SAP HANA that can be deployed on current customer data.
  • Page 62 Result: A social network model is saved in SAP HANA for future applications and a table with social network analysis results for each of our existing customers. The following step adds this social network data to the previous data manipulation. Manipulating the Data for Customer Churn Analysis a Social Network This section will outline the steps needed to add the social network data to our existing data manipulation.
  • Page 63 In the Application Data Set section, Browse to your SAP HANA instance and logon as <Domain User> Select DM_CHURN_CUSTOMERS_SOCIAL as your application data set  We will be using more recent aggregates on our current customers to assess their likelihood of churn Choose Advanced Apply Settings to configure the variables to be used in your model result In the General Outputs section, select Copy Variables...

  • Page 64: Post-Paid Analysis

    Start SAP Predictive Analytics and select Expert Analytics Logon with credentials provided to you. Select the LUMS file for Telco Churn Post-Analysis a. Either double-click Telco_Churn_Postanalysis.lums file and import, or select the file in the Documents, after the file is imported. b.

  • Page 65: Rotational Churn Detection

    Results Generated by the Model Data Type: Data Base Folder: <HANA connection> Data: SAP_RDS_PA_TELCO. SII_RESULT_POSTPAID_REGRESSION Choose Apply to continue.  Also, in this step (13) different decision cuts can be used in order to maximize profit, etc. Choose Apply Model and use following setting in Applying the Model screen: Application Data Set Data Type: Data Base Folder: <HANA connection>...
  • Page 66 DM_TELCO_LIST_OF CHURNERS List of SUBSCRIPTIONCHURNED Churners DM_TELCO_LIST_OFNEWCOMERS List of SUBSCRIPTION Newcomers DM_TELCO_CALL_LIST_OF CHURNERS Call List of SUBSCRIPTIONCHURNED Churners & SUBSCRIPTIONUSAGE DM_TELCO_CALL_LIST_OF_NEWCOMERS Call List of SUBSCRIPTION and Newcomers SUBSCRIPTIONUSAGE  The SUBSCRIPTIONCHURNED table contains the list of churned subscribers.  The SUBSCRIPTION table contains current subscribers including newly activated subscribers. ...
  • Page 67 Target Node: B_NUMBER Date Column: EVT_DATE Links Type: Directed Use a Weight Column: USG_DURATION Choose Next In the Post-Processings screen, allow Community Detection and Mega-hub detection Choose Node Pairing page and select + to add. In the Pairing Definition screen, enter the parameters as follows: a.

  • Page 68: Multi-Sim Detection

    Folder: <HANA connection> Data: SAP_RDS_PA_TELCO.SII_RESULTS_ROTATIONALCHURN After applying the model, return to the previous screen and save the social model to the repository. Result: A social network analysis Node Pairing result will provide list of phone numbers and subscribers that are similar. ...
  • Page 69 Data Type: Data Base Folder: <HANA connection> Data: SAP_RDS_PA_TELCO.SII_MULTISIM_SEGMENT Choose Apply to continue. Move to Save/Export and choose Save Model to the repository Result: Predictive Analytics Cluster Model is built using Subscription data. Cluster segmentation has been generated and result written to HANA for use in Classification modeling. Continue to the next section for information on classification model.
  • Page 70 Result: A classification model built using usage data saved to SAP HANA that can be deployed on current customer data. After reviewing the model results, the next step is using social network analysis to improve the model’s predictive power. Multi-SIM Social Network Analysis Neighbor The following section describes how the Social Network Analysis capabilities of SAP Predictive Analytics are used with Telco score data info to Identify multi-SIM pairs of customers.
  • Page 71 The following section describes how the Social Network Analysis capabilities of SAP Predictive Analytics are used with Telco score data info to Identify multi-SIM pairs of customer. From SAP Predictive Analytics, select the Social section Select Create a Social Network Analysis In the What Type of Graph dialog box, select Build a Social Graph From a Data Set Connect to your SAP HANA instance and logon as <Domain User>...
  • Page 72 Folder: <HANA connection> Data: SAP_RDS_PA_TELCO.SII_MULTISIM_NEIGHBOR Choose Apply to save run the model and save the results to HANA. Change Generate: Node Pairing Mode Data: SAP_RDS_PA_TELCO.SII_MULTISIM_NODEPAIR Choose Apply to save run the model and save the results to HANA. After applying the model, return to the previous screen and save the social model to the repository. Result: A social network analysis Node Pairing result will provide Multi-SIM candidate list.

  • Page 73: Hana Models (Optional Back-End Components)

    5 HANA MODELS (OPTIONAL BACK-END COMPONENTS) Note: (This section 5 is NOT NEEDED – Optional, You need this section to be done only if you want to create a separate user for your exercises. You can do this section and create users for each of the line of businesses or industry flavors.) SAP HANA delivery unit is installed.
  • Page 74 e) If missing, right click in SAP HANA Systems window and add your system with user account SYSTEM and master password Creating Solution Data Schema and System Roles a) To complete the solution data model implementation, the following SQL statements must be executed using SQL Editor Window opened under SYSTEM account in SAP HANA Studio by right-clicking on the SYSTEM account and selecting SQL Console.
  • Page 75 b) You can copy the SQL instructions from Appendix section (the electronic version of this document), then paste them directly into the SQL Editor. Depending on the line of business or industry, you copy the respective instructions from the section – appendix and copy them in the SQL Editor.
  • Page 76 c) The output window of the SQL Editor notifies when the command is successfully completed. d) Corresponding SAP_RDS_PA_<DOMAIN> schema is created under catalog area of SAP HANA developer studio, and must be visible to SYSTEM account catalog area. For eg., SAP_RDS_PA_CRM e) Note that some of these objects may have already been set up in your environment.
  • Page 77 Creating Operational and Administrative Roles In this section, you create operational and administrative roles for users of this solution. The functional roles must be created for specific operational purposes. The designated roles are assigned different operational and access permissions that we recommend. Functional Roles required for operating and administering this solution: ...
  • Page 78 Replace <user name> and <initial password> with your values: Refer to step c (Create a password). CREATE USER <user name> PASSWORD <initial password> ; GRANT RDS_<DOMAIN>_PA_ADMIN TO <user name>; GRANT RDS_<DOMAIN>_PA_BI_ADMIN TO <user name> WITH ADMIN OPTION; GRANT RDS_<DOMAIN>_PA_ADMIN TO <user name> WITH ADMIN OPTION; ...
  • Page 79  The initial password established for business user has a change password requirement at first logon. Refer to section Establish Permanent password.  Verify the role creation by opening a SQL Window using the business user account. SAP_RDS_PA_<DOMAIN> schema is visible in catalog area of the business user SAP_ERP_V4 schema is visible in catalog area of the business user for Sales &...
  • Page 80  Select Add Additional User and provide username and the initial password  You are prompted to Enter a new password, which is the permanent password e) Verify data  For each user, open all tables, one after the other, in schema SAP_RDS_PA_<DOMAIN> of the Catalog area, right click each table and do a data preview.
  • Page 81  For each user you previously created set the Session Client to 488 for ECC scenarios.

  • Page 82: Open Source R Including Installation (Optional)

    6 OPEN SOURCE R INCLUDING INSTALLATION (OPTIONAL) If you want to use the Open source R algorithms, you need to install this component. Follow these steps: a) Choose File / Install and Configure R b) Choose Install R to install, continue confirming prompts until installation begins. 7 SECURITY ASPECTS For more information about security vulnerabilities, see this community...
  • Page 83 GRANT CREATE ANY, ALTER, DROP, EXECUTE, SELECT, INSERT, UPDATE, DELETE, INDEX ON SCHEMA SAP_RDS_PA_CRM TO _SYS_REPO WITH GRANT OPTION; -- Establish referenced tables for DU onboarding CREATE column table SAP_RDS_PA_CRM.SALESORG_ANALYSIS_PDATA_T ("ID" INT,"TYPENAME" VARCHAR(100),"DIRECTION" VARCHAR(100)); --- PAL Content Admin CREATE ROLE RDS_PA_CONTENT_ADMIN; GRANT IMPORT, EXPORT, CONTENT_ADMIN, MODELING to RDS_PA_CONTENT_ADMIN WITH ADMIN OPTION;...
  • Page 84 GRANT SAP_ERP_V4_SELECT_USER TO RDS_CRM_PA_BI_ADMIN WITH ADMIN OPTION; GRANT RDS_PA_PAL_ADMIN TO RDS_CRM_PA_BI_ADMIN WITH ADMIN OPTION;...
  • Page 85 b) Manufacturing (Line of Business) CREATE SCHEMA SAP_RDS_PA_MFG; GRANT CREATE ANY, ALTER, DROP, EXECUTE, SELECT, INSERT, UPDATE, DELETE, INDEX ON SCHEMA SAP_RDS_PA_MFG TO _SYS_REPO WITH GRANT OPTION; --- PA Content CREATE ROLE RDS_PA_CONTENT_ADMIN; GRANT IMPORT, EXPORT, CONTENT_ADMIN, MODELING to RDS_PA_CONTENT_ADMIN WITH ADMIN OPTION;...
  • Page 86 CREATE ROLE RDS_MFG_PAL_PARAMETER_CONTROLLER; GRANT SELECT, UPDATE, DELETE ON SCHEMA SAP_RDS_PA_MFG TO RDS_MFG_PAL_PARAMETER_CONTROLLER WITH GRANT OPTION; -- BI Admin Role CREATE ROLE RDS_MFG_PA_BI_ADMIN; GRANT RDS_PA_CONTENT_ADMIN to RDS_MFG_PA_BI_ADMIN WITH ADMIN OPTION; GRANT RDS_PA_PAL_ADMIN TO RDS_MFG_PA_BI_ADMIN WITH ADMIN OPTION; GRANT RDS_MFG_PA_SELECT_USER TO RDS_MFG_PA_BI_ADMIN WITH ADMIN OPTION; GRANT RDS_SAP_ERP_PA_SELECT_USER TO RDS_MFG_PA_BI_ADMIN WITH ADMIN OPTION;...
  • Page 87 GRANT <HANA_LIVE_SCHEMA>_POWER_USER TO RDS_FIN_PA_ADMIN with ADMIN OPTION; GRANT RDS_FIN_PA_BI_ADMIN TO RDS_FIN_PA_ADMIN WITH ADMIN OPTION; GRANT SELECT ON SCHEMA SAP_RDS_PA_FIN TO _SYS_REPO WITH GRANT OPTION; GRANT <HANA_LIVE_SCHEMA>_SELECT_USER TO _SYS_REPO with ADMIN OPTION; d) Portfolio & Project Management (Line of Business) CREATE SCHEMA SAP_RDS_PA_PPM;...
  • Page 88 --PA Content Admin CREATE ROLE RDS_PA_CONTENT_ADMIN; GRANT IMPORT, EXPORT, CONTENT_ADMIN, MODELING RDS_PA_CONTENT_ADMIN WITH ADMIN OPTION; --PA Pal Admin CREATE ROLE RDS_PA_PAL_ADMIN; -- Grant afl execute to PAL Admin GRANT AFL__SYS_AFL_AFLPAL_EXECUTE RDS_PA_PAL_ADMIN WITH ADMIN OPTION; GRANT AFL__SYS_AFL_AFLBFL_EXECUTE RDS_PA_PAL_ADMIN WITH ADMIN OPTION; GRANT CREATE R SCRIPT RDS_PA_PAL_ADMIN...
  • Page 89 -- Role for setting up SAP HANA content modeling CREATE ROLE RDS_CPG_PA_BI_ADMIN; GRANT RDS_PA_CONTENT_ADMIN to RDS_CPG_PA_BI_ADMIN WITH ADMIN OPTION; GRANT SELECT ON SCHEMA <CPG_DOMAIN> TO RDS_CPG_PA_BI_ADMIN WITH GRANT OPTION; GRANT SELECT ON SCHEMA <DSIM_DOMAIN> TO RDS_CPG_PA_BI_ADMIN WITH GRANT -- Role for setting up algorithm using PA tool CREATE ROLE RDS_CPG_PA_ADMIN;...
  • Page 90 GRANT SAP_CAR_SELECT_USER TO RDS_RETAIL_PA_BI_ADMIN WITH ADMIN OPTION; GRANT RDS_PA_PAL_ADMIN TO RDS_RETAIL_PA_BI_ADMIN WITH ADMIN OPTION; h) Telco (Industry) CREATE SCHEMA SAP_RDS_PA_TELCO; GRANT CREATE ANY, ALTER, DROP, EXECUTE, SELECT, INSERT, UPDATE, DELETE, INDEX ON SCHEMA SAP_RDS_PA_TELCO TO _SYS_REPO WITH GRANT OPTION; --PA Content Admin CREATE ROLE RDS_PA_CONTENT_ADMIN;...

Table of Contents