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 1: ...User Guide for Predictive Analytics Cloud Image Trial Edition SAP Store Trial Edition...
Page 2: ...23 Asset Breakdown Analysis 24 Maintenance Cost Analysis 28 4 5 Portfolio Project Management 34 Project Profitability Analysis 35 4 6 Retail 42 Market Basket Opportunities 42 Customer Loyalty Program...
Page 3: ...f the running Error Reference source not found instance The system opens the Instance dialog box with the properties of the solution instance The IP Addresses area displays the access details of the s...
Page 4: ...w the Remote Desktop is launched Enter the following information Computer IP addresses of your personal instance User Administrator Choose Connect Enter the following information Password Master Passw...
Page 5: ...ng the Expert Analytics tool in Predictive Analytics We have built a generic data structure and seeded sample data so that compelling predictive models could be built Most of the fields in the data st...
Page 6: ...l b Specify where you want the model saved SAP HANA database Text file and so on and SAVE Once saved models may be opened and reused The folder location for the saved model is selected when you open a...
Page 7: ...alysis Train 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 B...
Page 8: ...C4 5_3_indep_cols spar f Select Save Predicting Once the model is trained the PREDICT LUMS is used with SAP Predictive Analytics for predictive modeling and the visualizations for the analysis using c...
Page 9: ...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 appropria...
Page 10: ...hen combined with Profile information and made visible via a database view in SAP HANA The data in this view can then be displayed using any tool that can read SAP HANA Automated Analytics Training th...
Page 11: ...ion where you want the model saved SAP HANA Database text file and so on c Choose Save to that location The location of the saved model is entered when using Load a Model for additional predictions If...
Page 12: ...ifferent segments of population in those communities The following section describes configuration for two scenarios The solution preconfigured content is provided in LUMS format files for each scenar...
Page 13: ...Documents list for Customer_Demand_Cluster_Analysis lums or Customer_Demand_Cluster_Analysis_DSiM lums for SAP Demand Signal Management data file b In the dialog box enter the SAP HANA server details...
Page 14: ...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_Cluster_Analysis lums or Consu...
Page 15: ...onsumer_Product_InterQuartile_Analysis_DSiM lums adjust the HANA Inter Quartile Range Test Algorithm Component a Choose Configure Settings b Select Output Mode Show Outliers c Select Features Sales Qu...
Page 16: ...per Year j Select Start Period k Select Start Year l Select Year Values m Select Period Values Choose Run to execute the scenario Choose OK to switch to the Results view for verifying the execution r...
Page 17: ...ype Apriori Lite c Select Item Column Product Name d Select TransactionID Column Transaction ID Choose Run to execute the scenario Choose OK to switch to the Results view for verifying the execution r...
Page 18: ...t 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 Company_Performance_Correlat...
Page 19: ...ecision Tree and save the model Optional Export the model as SAP Predictive Analytics spar file for use with PREDICT LUMS file For configuration purposes only the procedure for the TRAIN LUMS is descr...
Page 20: ...on Insight Portion Predicting Launch SAP Predictive Analytics Choose Automated Analytics Modeler Create a Clustering Model On the Select a Data Source enter the SAP HANA server details your user name...
Page 21: ...way to determine the good clusters is to display the Cluster Profiles and note which ones have a high percentage of 1 The same cluster numbers should be determined 2 3 and 5 5 On the Using the Model s...
Page 22: ...r predictive period Q for Quarter M for Month Start_Year Starting year of the actual data Start_Qtr IF the period is Q the starting quarter of the actual data Start_Mth IF the period is M the starting...
Page 23: ...r of periods years quarters months or weeks for review in the Predictive Analytics Zero_Fill_Missing_Time_Periods N for No Y for yes Note only use if you having missing period data and want to use 0 f...
Page 24: ...BETA DOUBLE Value of the smoothing constant beta 0 1 Asset Breakdown Analysis In this use case we focus on identifying the assets that are likely to break down based on historic facts and mean time b...
Page 25: ...4 right intToString BREAKDOWNDATEYEARMONTH 2 01 Manufacturer attribute needs following expression stringToDate concat concat concat left intToString YEARMONTH 4 right intToString YEARMONTH 2 01 Enter...
Page 26: ...Data Source window Choose Browse and connect to your SAP HANA instance using the Domain User logon Then select the Browse button again to select the data set that will be used for predictive modeling...
Page 27: ...bles Statistical Reports After reviewing the model results choose Save Export and select Apply Model In the Applying the Model screen Application Data Set Data Type Data Base Folder HANA ODBC connecti...
Page 28: ...NT FUNCLOCATION MANUFACTURER ORDERTYPE and PLANNERGROUP attributes In the Define New Data Manipulation window select your SAP HANA instance and connect using the HANA Domain User account via the Brows...
Page 29: ...oup MAINTENANCEPLANNERGROUP Select the New button and select the Expression Editor Add expression stringToDate concat concat concat left intToString POSTINGDATEYEARMONTH 4 right intToString POSTINGDAT...
Page 30: ...DM_MAINTCOST_MANUFACTURER ORDERTYPE DM_MAINTCOST_ORDERTYPE PLANNERGROUP DM_MAINTCOST_PLANNERGROUP Repeat these steps to create data manipulation for each attribute Predicting From the home screen of...
Page 31: ...OUP MAINTENANCEPLANNERGROUP MAINTENANCEPLANNERGROUPNAME 1 In the Selecting Variables screen set POSTINGDATE as the TIME variable and PLNDMAINTCOSTINDISPLAYCRCY_E as the TARGET variable Exclude the all...
Page 32: ...LT_MAINTCOST_FUNCLOCATION MANUFACTURER SAP_RDS_PA_MFG SII_RESULT_MAINTCOST_MANUFACTURER ORDERTYPE SAP_RDS_PA_MFG SII_RESULT_MAINTCOST_ORDERTYPE PLANNERGROUP SAP_RDS_PA_MFG SII_RESULT_MAINTCOST_PLANNER...
Page 33: ..._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 da...
Page 34: ...sion CreationDate Comment DM_PROJEC T_TRANSAC TION Kxen Connector Kxen ODBCStore HANA ODBC DSN 3 ConnectorsTable 1 2015 06 01 12 55 11 Project Transaction s Data DM_PROJEC T_TRANSAC TION_ACTIV E Kxen...
Page 35: ...ample c MDR_PPM Select OK Project Profitability Analysis In this use case we focus on identifying what projects profitable to be picked up and how they can increase or contribute to the bottom line re...
Page 36: ...t Closed Project prompt value to filter the data set i e Closed 1 After entering the value choose OK to begin modeling Choose Analyze and a description for the data set appears Choose Next when the da...
Page 37: ...appear at the top of the list of options Choose DM_PROJECT_TOTAL Choose Next to continue Enter the Select Closed Project prompt value to filter the data set i e Closed 1 After entering the value choo...
Page 38: ...klog 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 Choose Use a File or a Database Tabl...
Page 39: ...ults Generated by the Model Data Type Text Files Folder local folder Data result_regr_orderbacklog_active_key txt Select Apply After reviewing model results choose Next Choose Save Export and choose S...
Page 40: ...the Using the Model screen select Display and review the resulting model by viewing Model Overview View Forecasts Regressions Contributions by Variables and so on After reviewing the model results ch...
Page 41: ...ts list in SAP Predictive Analytics Expert Analytics b In the dialog box enter the SAP HANA server details your user name and password LUMS file Input Dataset PPM_Project_Insight_Analysis lums result_...
Page 42: ...A server details your user name and password Verify the data Choose Prepare panel to ensure that the data has loaded properly Switch to the Predict panel to view the predictive model Adjust the Time P...
Page 43: ...component a Choose Configure Settings in the Apriori Across all stores component b Change the Support level to an appropriate value c Change the Confidence level to an appropriate value Run the algor...
Page 44: ...the scenario Choose Yes to switch to the Results view for verifying the execution results For SAP Customer Activity Repository installation Select the LUMS for Customer Loyalty a Launch Expert Analyt...
Page 45: ...already imported browse through the Documents list for Retail_Store_Clustering lums file b In the dialog box enter the SAP HANA server details your user name and password Verify the data a Choose Pre...
Page 46: ...HANA K Means Algorithm Component a Choose Configure Settings in HANA K Means component b Set Number of Clusters to a desired value c Select the Features columns variables needed for cluster analysis d...
Page 47: ...y The following section describes the configuration of a local metadata repository file to re use pre built SAP Predictive Analytics metadata in the building of predictive models Editing the Metadata...
Page 48: ...nter a desired value The number of clusters must be less than number of transactions Typically the number of K is usually between 3 and 10 Adjust the HANA K Means Net Value and Incoming Returns Algori...
Page 49: ...ANA K Means Product Dist Chnl Segments component b Select the Features and Category Columns needed for cluster analysis c Choose Number of Clusters and enter a desired value Adjust the HANA K Means In...
Page 50: ...of Clusters to a desired value Adjust the R MONMLP Neural Network Algorithm Component if needed a Select Configure Settings in each of the Cluster Customers Survey components b Select the Features nee...
Page 51: ...enerated When that occurs set the following value KxIndex Key to 0 Next to Events Data Source screen enter Data Type Text Files Folder input files location Events TRANSACTIONS csv Next to Data Descrip...
Page 52: ...1 Start Line 3 Choose Target Table Existing Find SAP_RDS_PA_CRM RULES_FROM_II Choose Next To the right of Proposed Table Structure select Map 1 to 1 Or if using the existing table drag the Source Colu...
Page 53: ...GRP_MONTH LY Building the Predictive Model From the home screen of SAP Predictive Analytics select the Modeler section Select Create a Time Series Analysis In the Select a Data Source window Choose Br...
Page 54: ...ewing Model Overview View Forecast View Signal Components Regressions Contributions by Variables and Statistical Reports After reviewing the model results choose Save Export and select Apply Model In...
Page 55: ...NA ODBC connection File Table Scenario Model Sales Forecast Aggregated SAP_RDS_PA_CRM SII_MODEL_SALES_AGGREGATED Sales Forecast by Sales Organization SAP_RDS_PA_CRM SII_MODEL_SALES_SALESORG_MONTHLY Sa...
Page 56: ...a pre built metadata repository The Pre Paid Churn Analysis Churn modeling and offer recommendation is based on new configuration which includes the building of the metadata objects and the models SA...
Page 57: ...r Kxen ODBC Store HANA ODBC DSN 3 ConnectorsTabl e 1 2015 01 21 16 58 56 DM Subscription Usage Off Network A Call Data SubscriptionUsageO ffNetAInternational Kxen Connect or Kxen ODBC Store HANA ODBC...
Page 58: ...t or Kxen ODBC Store HANA ODBC DSN 3 ConnectorsTabl e 1 2015 01 21 17 01 33 Call List of Newcomers DM_TELCO_LIST_ OF_NEWCOMERS Kxen Connect or Kxen ODBC Store HANA ODBC DSN 3 ConnectorsTabl e 1 2015 0...
Page 59: ...R_ID Select the Source Field from the target table on the right that we will be using to join the data sets CUSTOMER_ID Select the OK button at the bottom of the screen to confirm the data set merge w...
Page 60: ...Churn This section describes how to use the data manipulation created above to build a predictive model for customer churn based on customer history Using customer demographics and details about thei...
Page 61: ...Node RECD Date Column TIME Links Type Directed Use a weight column DURATION End Date Enter the end date using the format YYYY DD MM Choose Next Allow Community Detection and Mega hub detection in the...
Page 62: ...P Predictive Analytics select the Modeler section Select Create a Classification Regression Model In the Select a Data Source window choose Browse to select your SAP HANA instance using the logon Doma...
Page 63: ...ble SII_FINAL_MODEL_OUT Choose Apply A prompt appears for your data manipulation You are creating your aggregates using recent customer data to get predicted values for churn likelihood over the next...
Page 64: ...alysis In this use case we focus on build churn models and identify the post paid customers likely to leave Automated Analytics Launch SAP Predictive Analytics Choose the Modeler section Select Create...
Page 65: ...ill in cost matrix in order to maximize profit and click next Save the model to the repository Result A post paid churn model is saved in SAP HANA for future applications and a table with analysis res...
Page 66: ...ption as Database and Events as DM DM_TELCO_CALL_LIST_OF_CHURNERS Choose Next When prompted enter the Start Event Date and End Event Date This corresponds to the period for the churners that have chur...
Page 67: ...Choose Generate to construct the social graph To verify and to analyze the model generated click on Nodes Display a Choose Graph Social_Network_Comparison_Ratio and choose a phone number and choose di...
Page 68: ...eate a Clustering Model In the Select a Data Source window choose Use Explorer option Select your SAP HANA instance and connect using the Domain User account via the Browse button Specify the data set...
Page 69: ...rd_MultiSIM and Time stamped Population EntitySubscriptionPopulation Choose Next Enter training cut off date to Analytical Data Set Reference Date prompt screen Choose Analyze to read description from...
Page 70: ...arameters as follows Graph Name Multi SIM Candidate Graph Creation Type Contact Source Node a_number Target Node b_number Date Column evt_date Links Type Directed Choose Next Choose Next and skip Add...
Page 71: ...cted and select Clone to create copy of first graph In the Graph Settings section enter the parameters as follows Graph Name second graph Graph Creation Type Contact Source Node a_number Target Node b...
Page 72: ...rk analysis Node Pairing result will provide Multi SIM candidate list A social network analysis Neighbors provide list of Multi SIM candidate and their matched pairs You can analyze details of each mo...
Page 73: ...stry flavors SAP HANA delivery unit is installed In this unit users configure Solution Schema and Roles in SAP HANA Studio Setting up Schema Mapping a Start SAP HANA Studio by following the menu Start...
Page 74: ...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...
Page 75: ...ppendix 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...
Page 76: ...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 be...
Page 77: ...lysis Library PAL In the creation of the operational and administrative roles please replace the DOMAIN with the following For Sales Marketing LoB CRM For Manufacturing LoB MFG For Finance LoB FIN For...
Page 78: ...of that user name for sales and marketing manufacturing related scenarios b Creating a Business User Role The Business User role is a consumer of information provided by the Data Scientist For some s...
Page 79: ...ble in catalog area of the business user o SAP_ERP_V4 schema is visible in catalog area of the business user for Sales Marketing Manufacturing scenairos c Create a password Create an alphanumeric pass...
Page 80: ...assword 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 f Set session client Logged in wit...
Page 81: ...For each user you previously created set the Session Client to 488 for ECC scenarios...
Page 82: ...SECURITY ASPECTS For more information about security vulnerabilities see this community page 8 APPENDIX 8 1 Further Documentation You can find a lot of additional information below SAP SCN Rapid depl...
Page 83: ...to RDS_CRM_PA_POWER_USER WITH GRANT OPTION GRANT RDS_CRM_PA_POWER_USER TO _SYS_REPO WITH ADMIN OPTION CREATE ROLE RDS_CRM_PA_SELECT_USER GRANT SELECT ON SCHEMA SAP_RDS_PA_CRM TO RDS_CRM_PA_SELECT_USE...
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: ...DMIN with ADMIN OPTION GRANT RDS_SAP_ERP_PA_SELECT_USER TO _SYS_REPO with ADMIN OPTION Note this is tied to the HANA Live Schema and have to append _SELECT USER and grant to admin role GRANT SAP_ECC_P...
Page 86: ...PAL_ADMIN Grant afl execute to PAL Admin GRANT AFL__SYS_AFL_AFLPAL_EXECUTE TO RDS_PA_PAL_ADMIN WITH ADMIN OPTION GRANT AFL__SYS_AFL_AFLBFL_EXECUTE TO RDS_PA_PAL_ADMIN WITH ADMIN OPTION GRANT CREATE R...
Page 87: ...O RDS_PA_PAL_ADMIN WITH ADMIN OPTION GRANT CREATE R SCRIPT TO RDS_PA_PAL_ADMIN WITH ADMIN OPTION Role for setting up algorithm using PA tool CREATE ROLE RDS_PA_DATA_ADMIN GRANT DATA ADMIN to RDS_PA_DA...
Page 88: ...RDS_PA_PAL_ADMIN TO RDS_BANK_PA_ADMIN WITH ADMIN OPTION GRANT RDS_PA_DATA_ADMIN TO RDS_BANK_PA_ADMIN WITH ADMIN OPTION GRANT RDS_BANK_PA_BI_ADMIN TO RDS_BANK_PA_ADMIN WITH ADMIN OPTION GRANT SELECT O...
Page 89: ...ROLE RDS_PA_PAL_ADMIN Grant afl execute to PAL Admin GRANT AFL__SYS_AFL_AFLPAL_EXECUTE TO RDS_PA_PAL_ADMIN WITH ADMIN OPTION GRANT AFL__SYS_AFL_AFLBFL_EXECUTE TO RDS_PA_PAL_ADMIN WITH ADMIN OPTION GR...
Page 90: ...ADMIN OPTION GRANT AFL__SYS_AFL_AFLBFL_EXECUTE TO RDS_PA_PAL_ADMIN WITH ADMIN OPTION GRANT CREATE R SCRIPT TO RDS_PA_PAL_ADMIN WITH ADMIN OPTION Role for setting up algorithm using PA tool CREATE ROL...
