Though predictive analytics has been around for decades, it’s a technology whose time has come. More and more organizations are turning to predictive analytics to increase their bottom line and competitive advantage. Why now?

With interactive and easy-to-use software becoming more prevalent, predictive analytics is no longer just the domain of mathematicians and statisticians. Business analysts and line-of-business experts are using these technologies as well.

The intent of this blog is to share my understanding and opinion of predictive capabilities and options available within the SAP Ecosystem.  Predictive Analytics in SAP can be leveraged with any of the below tools/applications. It all depends on how the  business adopt the tools.

SAP Analytics Cloud –

It’s a cloud-based SaaS offering from SAP, capable performing of BI, Planning, and Predictive/Augmented Analytics in one place. This tool offers out-of-the-box and business-friendly technology to perform predicative use cases. SAC uses HANA APL libraries (Classification, Regression, and Time-series Forecasting)… Models where you can input the historical data and predict future outcomes. Currently, it supports both flat-file and Live (HANA) connectivity. Live connections use On-prem HANA APL installation, not the SAC APL.

There are currently 3 types of predictive scenarios available in Smart Predict:

• Classification
• Regression
• Time Series

To create and manage predictive scenarios in SAC you need a few different datasets:

• The training dataset contains the historical data your predictive model will learn from. In this dataset, the values for your target variable, which is the column related to your business question, are known.
• The application dataset contains current or new data that you would like to create predictions for. In this dataset, the values for the target variable are unknown.
• The output dataset contains your predictions and any additional columns that you have requested. Once the Model is created, SAC has added advantage of publishing the model to S4 on-prem via Pai connections.

In the course of this blog, I will create a simple Predictive scenario of Insurance Fraud using SAC Smart Predict

SAP HANA –

As everyone knows, HANA is a powerful in-memory database from SAP. Predictive Capabilities in HANA are there for quite a while through Application Framework Libraries (AFL). Below are core predictive components of HANA predictive offerings:

PAL – Algorithmic approach towards machine learning and predictive use cases.  This is more suited for data scientists and IT people which requires SQL coding.

APL – Automated predictive libraries for augmented analytics to train and predict the outcome.

R/ EML Integration – Integrating with external R server for more robust and statistical use cases which requires CRAN algorithms and TensorFlow.

Check out the link for more information on HANA predictive (https://tek-analytics.com/site/blog_inner/28 )

SAP BW – Yes, SAP BW running on HANA has inbuilt Predictive algorithms. It uses Native HANA PAL libraries above using HAP for predictive modeling. This is best suited for industries with extensive in-house BW talent.

SAC Smart predict sample use case

Before we use the functionality, let’s look at the data we have

Data set 1 – Past insurance claims with the flag for fraud (Yes or No)

Data set 2 – Current insurance claims on which we apply the prediction

Step 1 – Create 2 datasets in SAC, Datasets can be Live on HANA tables or Flat files loaded into SAC

Step 2 – Create a Classification based Predictive scenario

Step 3 – Select Input Dataset, target variable and exclude the variables which have no impact on the outcome (Claim ID, Member name)

Step 4 – Train the Data set. After successful Training, SAC provides the output including Predictive power, Predictive confidence and we have an option to run Profit simulation to see where to concentrate

Applying the Model

Once we are comfortable with our Predictive Model, we can apply this to our new data set and see what it predicts

Provide, the new input dataset and Output to be created

The new dataset will be now created with the name provided. The new output dataset has two additional columns created with predictive class and Probability

This Dataset can be in turn used for creating stories for visualizations and also, we can write back to Hana for any additional use cases.

SAP Analytics Cloud is a next-gen cloud-based service offering for all reporting and analytical applications. As promoted by SAP it is the one-stop place for all the BI, Planning and Predictive applications. For years (Decades ????) Business Objects is a premium BI offering from SAP and customers are using it extensively and effectively.  With the new strategic direction of SAP, SAC is going to be a successor for all the reporting and analytical needs. Our customers frequently ask how can we migrate our on-prem BOBJ to SAC? What should be our strategy for cloud migration.

First, let’s see what SAC is and its capabilities are.

SAP analytics cloud is a next-generation all-in-one analytics SaaS solution that combines reporting planning as well as predictive.

Built natively on SAP HANA Cloud Platform (HCP), SAP Analytics Cloud allows data analysts and business decision-makers to visualize, plan and make predictions all from one secure, cloud-based environment. SAP claims this differs from other BI platforms, which often require data to be integrated from various sources and users to jump between different applications when performing tasks, such as creating reports. With all the data sources and analytics functions in one product, Analytics Cloud users can work more efficiently, according to SAP. The key functions are accessed from the same user interface that is designed for ease-of-use for business users.

SAP Business Objects BI suite –

Business Objects is a Premium BI offering from SAP with multiple BI suite of products bundled. This has been a very successful BI tool for most of the SAP customers. Even though SAP announced BI 4.3 and maintenance up to 2027, all new innovations will be added to SAC. The below Image shows the convergence plan for the products.

Let’s look at migration options from BOBJ to SAC. Unfortunately, at this moment there is no direct migration path or tools delivered by SAP. However, they are planning to deliver assessment tools for migration in the future to compare the features supported.  So, how can we start using the latest and greatest cloud offerings while we have thousands of BOBJ reports already deployed.

• Let’s start with an assessment of the bobj system. SAP now changing the licensing model for BOBJ, if you are heavy Web-Intelligence shop and limited other tools, we now have Web-I only licensing so               we start using SAC for visualizations and planning
• Latest BI 4.3 has very tighter integration with SAC which includes easy user onboarding and Web I data model connection
• BOBJ 4.3 will have a new option to deploy Web I report directly to SAP Analytics Hub. This allows end-users transparency in accessing both SAC and BOBJ content
• We already have universe connection available in SAC, so technically all the modeling/ semantics applied at Universe level can be used in SAC
• BI 4.3 will be delivering a new Web I Data model, which essentially enables the user to build SAC stories on On-prem Web I
• SAP Application designer will have all the features and capabilities of Lumira designer and now is the time to start converting (Again, no direct migration tool)

Tek Approach

• Our Rapid Deployment team partners with IT and Business stakeholders and quickly identify the use-cases for On-prem, cloud and hybrid approaches
• Our team will help customer to change the licensing model based on BI product usage for the effective and cost-efficient transition to SAC
• Asses the On-prem BI platform and identify any redundant objects, identify reports which can be easily recreated in SAC
• Configure Live, import connections and Deploy SAP Analytics Hub as reporting gateway for seamless and transparent SAC transition
• Deploy SAC cloud content to Jumpstart the SAP Analytics cloud Journey
• End to end training and enabling the business transition to Guided/Self – service BI using SAC

SAP Analytics Cloud is a new generation cloud-based application that helps you explore your data, perform visualization and analysis, create financial plans, and produce predictive forecasting. you can restrict the folder access from individual user or teams (group of users). In SAP Analytics Cloud the authorization is mainly controlled by SAC role, SAP back-end system (e.g. S/4 HANA) and SAC folder access.

Note: you should have admin authorization to secure folder access in SAP Analytics Cloud.

below are the steps to restrict the folder access from a specific user or team.

Step 1: Log into SAP Analytics Cloud tenant URL with valid credentials

Step 2: Then click on the three horizontal stripe button(Main Menu), on top of the left corner on the home page.

Step 3: Click on Browse>Files

Step 4: Click on the Public folder. Here we doing the restriction settings on subfolders of the Public folder. If you want to put a restriction on another folder of the public folder follow the same steps.

Step 5: Select the folder where you want to put a restriction and then click on the manage button(here we are putting restrictions on subfolders of Rumpke Reporting). 

Step 6: Click on the Sharing Settings which can be available under the Manage button.

Step 7: Here you can set the required restriction on teams or users.

Note: You can share the restricted folder with all users.

Step 8: You need to give access to the required user or team.

There are different types of access available.

View: In view access, the restricted user can read and copy the folder but he can not make any changes.

Edit: In edit access the restricted user can  Update the folder,  create files, create folders and maintain the folder.

Custom: In custom access, we have different options, You need to check the required access you want to provide to users or team.

Full control: In full control access the restricted user can delete the folder and share the folder to different users or teams.

Note: In SAP Analytics Cloud, you can create new roles to different users (follow the below steps for new roles creation)

Creating a New Role

In the Main Menu Go to Security>Roles

In Security/Role page Click on + Create a new role Option under Custom roles

Enter the details of new role which you want to create and click on create button

The new role will be added under the custom roles.

After selecting the appropriate access Then click on  Add Users and Teams button. Here you can see the available list of users or teams.

Step 9: select users or teams by clicking on Add Users or Teams Option

Select the users or teams and click ok button

Step 10: Folder security settings based on the folder structure and team structure. Folder restriction along with the role assigned to the users/team, you can control the access in the SAC application. Then click on the Share button.

• Administrators can now restrict who can create files and folders within dedicated subfolders of the Public folder. These users still won’t be able to create files and folders directly within the Public folder itself.
• Administrators can audit changes made to files’ sharing settings

These include:

1. The name of the object whose permissions were changed
2. The permissions that were granted/revoked and to which specific user/team
3. The user who made the change
4. The timestamp of the change

Note: The Activities log is now updated to show details for any changes that are made to the Sharing Settings of files stored under Browse > Files.   
                            

Stories

• You can now add or delete comments without saving your story.
• When data labels in your bar charts overlap, you can now prioritize the bars in visualization to show the front bar’s data labels only, making it easier to view your information.

• You can now use Search to Insight to search within live BW and S/4 HANA data models. You can choose a model and search for insights and can also create charts.

Planning

• In the calendar, you can now see if processes are related to each other or if they just happen to start at the same time. Also, in the Gantt view, you can now see the time values changing when you drag and drop a process.

• You can now set up a context for a Calendar task, defining all the relevant information for the task such as the Model, primary or Driving dimension, and assignees and reviewers.

• When you copy an aggregated account with calculated subaccounts, you can now see additional targets highlighted so you can paste the account value and its underlying records.

Analytics Designer

• As an application designer, you can now add geo map widgets to your analytic application and allow your application users to create stories from the widgets. Currently, geo map widgets don’t support data source-related APIs. Support for this is planned for future waves.

• Analytics Designer introduces a concept of names for widgets and other application entities to ease the handling effort at design time.

If you as an application designer want to rename some entity, various references to it must be adapted (mainly scripts, dynamic texts, and calculated measures). Previously, you had to do this work manually.

The new automatic refactoring automates this process as much as possible.

• You can now add a Search to Insight object to the scripting area and design its open dialog by defining the source of the questions to be asked. You can also specify whether the dialog is in simple mode or advanced mode and if you want to enable Clean History and Auto Search. Simple Dialog Mode, Advanced Dialog Mode are shown below.

• You can now use the BPC Planning Sequence widget to run planning sequences for BPC live data connection models. This way, the application user can run a planning sequence, which can contain one or more planning functions, as defined in the BPC system.

In the modern digital world customers with information at fingertips, making informed decisions to buy or lease a car.

Manufacturers can now connect with customers directly, transform the traditional selling practices by offering customized incentive programs. Using advanced analytics manufacturers can get deeper insights into customer sentiments and influencing factors for closing a deal with the customer

With this dynamically changing ownership models and competitive incentives landscapes, manufactures and dealers need more tools to manage incentive programs and budgets to dynamically modify programs by gaining insights into customer’s preferences to win deals.

Incentive Planning and Trade Promotion management process consists of activities aimed at successful automobile sales which can benefit from improved budgetary controls. Sales promotions and program activity, dealer incentives, promotional campaigns, and many other programs are accurately planned, budgeted, executed and audited for efficacy using our flexible and easy to customize Incentives / Trade Program Management solution.
 

Our flexible solution offers:

• Planning Budgets – total allocation of dollars
• Reconciliation – detailed breakout of budgets
• Programs – Add and manage initiatives
• Reports and Publications – chargebacks from distributors and vendors against the program 

Plan and Analyze Promotion Budgets:

 

Create templates and established budget plans templates. Plan Budget Allocations, Analyze program effectiveness, measure progress and ensure accurate execution which can be tracked by:

Model / VIN / Product

Regions / Zones / Market

Dealer / Zip/ Distributor

Program / Affiliations / Fleet
 

Planning & Management Workflows:
 
Create or Change programs, conduct what-if financial analysis, measure and review budget impacts. Review and track changes and manage approvals.:

Planning Workflow

Financial Workflow

Program Changes

Audit Trail and Compliance

Incentives Planning and Management through a set of standard and ad hoc business processes with workflow and analytics

Connect all process steps (activities) and decision events, such as program planning, new incentive model analysis, approval 

Trigger process approvals, notifications and communication workflows where the execution of one task results in automatic initiation of other processes
 

Seamless Data and System Integration

Add new data sets, integrate budgets from existing ERP system, connect other CRM systems, including external financial

Establish two-way integration with data feeds.

Keep your existing Financial tools for budgets and integrate with new incentive management solution automatically.

Add new programs and import from existing CRM systems and managed metadata.

Track & Manage Spending

Manage incentive payments to dealers and partners. Track and manage program expenditures, reconcile financial and maintain accurate reporting across,

Leverage the TEK Incentives & Promotion Management tool to gain full visibility and maximum control on your budgets and effective incentive programs.

Create Targeted Incentive Programs with Advanced Analytics, AI and Machine Learning

Create customized and targeted incentive plans by gaining insights into customer preferences, social trends, tailored promotional programs:

With access to open data, social media and APIs take a  giant  step from conventional incentive planning by deploying

• Prescriptive analytics driven approach
• AI in measuring customer trends and sentiments
• Digital Incentive Campaigns

 Thank you,
Bharat Sunkari.

DataFlow Object

Right-click on Data Flow Object

When creating the Dataflow object a transport request opens up.

Afterwards add a new or existing Datasource by drag and drop to the Details:

Double click on the entered Datasource leads to the following properties:

Select a Source System and if you want a copy from an existing or a proposal from an ODP connection

By clicking on the „NEXT“ button the Dataflow is shown – now it is possible to add any other object to the dataflow.

In this example an ADSO was added and filled with three InfoObjects

Now you created a persistent ADSO.

Activate the newly created ADSO. Create a connection between the newly created ADSO and the previously created Datasource

Now you’ll see a transformation and DTP creation is possible based on the connection.

Right-click on the transformation symbol and select “Create Transformation … “

Now you are able to create a transformation – Target and Source are filled automatically:

Here you are able to define all settings for the transformation as well as connect to the fields from the previous ADSO

In addition, if infoObjects are available in the source – they are automatically connected. Don’t forget to activate!

Same for the creation of the DTP. All DTP properties can be selected. You can see/select/change all the properties already known in BW.

Same process for the composite provider – drag and drop the composite provider, assign a name and create a connection to the ADSO.

It is also possible to add a comment for the specific selections within the dataflow. Click the one you want to comment on – go to the properties section and add documentation.

Conclusion

As you could experience, the Dataflow object is an easy way to model your intended dataflow. You can see all the different stages on one side in one place and do not have to click yourselves through your modelled dataflow, which can be difficult and time-consuming with two different tools either the Eclipse modelling tool and the SAP GUI.

Although it is a simple way to create a complete dataflow it does not replace process chains for loading data as it is moreover a graphical view of your model. For loading the data into your model you also need to create a process chain.

Finally I’ve put together some hints which will make your work easier:

• Create Persistent Objects of ADSO, InfoSources, HCPR directly out of DataFlow Maintenance Screen
• You can use Templates eg. Datasource or Infosource as templates and more.
• When you have a SourceObject like an Infosource and a Target object like an ADSO, first create the connection in between before persisting the ADSO, then all fields/InfoObjects of the source are automatically taken into account for the DataModel of the Target.
• Execution of DTP’s is possible
• if you want to use DTP Monitor you have to execute the DTP in the DTP Maintenance Screen, from here the InPlace GUI is being called.

Tek-Analytics scheduling engine brings scheduling capabilities to SAC stories and models. You can use Scheduling engine to burst the reports in PDF, Excel formats and the destinations can be email client, File system or SFTP.

 It is a lightweight on-premise installation with easy to maintain GUI interface. Administrators can choose the Models, Stories to be busted with Recurrence schedule.  Stories can be published to third-party vendors by email or SFTP. 

Formats supported – PDF, Excel, CSV

Destinations – Email Client, File System, SFTP

Out of passion with CDS modelling, this is one interesting thing I did for a customer to create a planning enabled CDS view

First, create Custom CDS / Custom Analytical query using Fiori App.

Launch ABAP eclipse and add the ATP local package to eclipse. In this case, the package is TEST_YY_KEY_USER_LOCAL_APP package.

Copy the entire code from the CDS view generated by App

Create a new CDS view and paste the code, Change the names in the code as required

Declare Planning annotations .

This will save a lot of time in defining the query/CDS view from scratch.

The CDS view will be available as any other CDS view in BI tools. But since the origin for the new CDS view is ADT, you cannot develop new Analytical queries on this using the app.