8/9/2020

SAP Analytics Cloud Help

Generated on: 2020-08-09

SAP Analytics Cloud | Q2 2020 (2020.8)

PUBLIC

Original content: [Link]

Warning

This document has been generated from the SAP Help Portal and is an incomplete version of the official SAP product
documentation. The information included in custom documentation may not re ect the arrangement of topics in the SAP Help
Portal, and may be missing important aspects and/or correlations to other topics. For this reason, it is not for productive use.

For more information, please visit the [Link]

[Link] 1/22
8/9/2020

Getting Started
Get started creating your rst story, and customize your SAP Analytics Cloud experience.

Tasks
Logging In for the First Time

Creating Your First Story

Building Your First Model

Customizing Your Home Screen

Editing Your Pro le

Requesting Roles

Collaborating with Others

Getting Started with Planning

Contacting an Admin for Support

Get More Help and SAP Support

Mobile App

Smart Predict – Using Predictive

Scenarios
A Predictive Scenario helps address a business question requiring predictions. It is a workspace, where you create and compare
predictive models to nd the best one to bring the best predictions to address the business question.

The following types of predictive scenarios are available. You choose the one that best ts your business question.

Predictive
scenario Answers this type of business question...

Classi cation What is the likehood that a future event occurs? This event is observed at an individual level (customer, asset, product, ...)
and at a certain horizon (in the year, before the end of week, in the month after a customer contact, ...) .

 Example
Who is likely to buy or not buy your new product? Which client is or isn't a candidate for churn?

Regression What could be the prediction of a business value, taking into account the context of its occurrence?

 Example
What will be the revenue generated by a product line, based on planned transport charges and tax duties?

Time Series What are the future values of a business value over time, at a certain granularity/place?

 Example
How much ice cream will I daily sell over the next 12 months? I have my historical daily sales information, but I'd like to
be able to include other factors such as vacation months, and the seasons.

You can create one or several predictive models within a predictive scenario. Each predictive model produces intuitive
visualizations of the results making it easy to interpret its ndings. Once you have compared the key quality indicators for different

[Link] 2/22
8/9/2020
models, you choose the one that provides the best answers to your business question, so you can apply this predictive model to
new datasets for predictions.

 Restriction
To verify that Smart Predict is available for your region or tenant type, check out the SAP Note 2661746
Information published on SAP site.

Looking for the Best Predictive Model

Once you've added and con gured your rst predictive model, it's time to analyze its performance indicators and add new
predictive models if you want to re ne your results.

This image is interactive. Hover over each area for a description. Click highlighted areas for more information.

Generating Your Predictions

Once you are satis ed with the performance of your predictive model, you can use it to generate your predictions.

This image is interactive. Hover over each area for a description. Click highlighted areas for more information.

Applying a Time Series Predictive Model

Context
You want to create the output dataset containing your predictions and save the forecasting results to a dataset.

Procedure
1. Open the relevant model.

2. Under the icon bar, click the Apply Predictive Model icon.

3. Click the Name eld, and either:

a. Enter a name in the Name eld to create an output dataset, and optionally enter a description.

b. Use the Search eld at the top right of the dialog box to browse where you want to save your output dataset.

c. Browse the folders in the My Files section to save your output dataset in an existing folder.

4. Click OK.

In the predictive model list, the status of your predictive model is updated to <Applied>. You can nd your output dataset
with the predictions under Main Menu Browse Files .

Here are the columns that are added to your output dataset:

Column Name Description

[Link] 3/22
8/9/2020

Column Name Description

Forecast This is the column where you nd the forecasted values for the
signal based on the number of requested forecasts speci ed in
the predictive model settings.

Error Min For each requested forecast at a given horizon H, the predictive
model calculates a con dence interval. The Error Min value is
the lower bound of this con dence interval. It is equal to the
forecasted value – sigma(RMSE)*1.96, where sigma(RMSE)
represents the standard deviation of RMSE between the actual
and forecasted signal value at horizon H. The weighted value of
1.96 corresponds to a con dence level of 95%.

Error Max For each requested forecast at a given horizon H, the predictive
model calculates a con dence interval. The Error Max value is
the upper bound of this con dence interval. It is equal to the
forecasted value + sigma(RMSE)*1.96, where sigma(RMSE)
represents the standard deviation of RMSE between the actual
and forecasted signal value at horizon H. The weighted value of
1.96 corresponds to a con dence level of 95%.

Related Information
Input Datasets
Output Datasets
Datasets - Examples

Applying a Classi cation or Regression

Predictive Model
Context
You want to apply your classi cation or regression predictive model to a new dataset.

Procedure
1. Open the relevant predictive model.

2. Click Apply Predictive Model .

The Apply Model window opens.

3. In the Input Dataset section, select the input dataset. It's the new dataset (application dataset) you want to apply your
predictive model on.

4. In the Output Dataset section, give a name to your output dataset and select a place to save it.

5. In the Output Columns section, you select the additional columns you want to have in your output dataset:

Input dataset variables: select which variables from the dataset used to run the training that should be part of the
output dataset.

 Restriction
The application process does not take into account any column of the application dataset that doesn't belong to
the training dataset.

[Link] 4/22
8/9/2020
Contextual Information: This is the information about your predictive model you want to have in the output
dataset.

Information Description Comments

Apply Date It's the start date of the predictive model application. The type of the column is TIMESTAMP.

Train Date It's the start date of the predictive model training. The type of the column is TIMESTAMP.

Statistics: select the statistics regarding the variables you want to export:

Statistic Description

Assigned Bin When selected, indiviuals in the application population are assigned to referent
quantiles de ned on the validation population.

Assigned bins explained: The validation population during training is spread out in
quantiles (bins), each de ned by a range of scores, to serve as references (assigned
bins) to an application population. When a predictive model is applied, each individual
in the application population is allocated to an assigned bin based on its predicted
score. As each assigned bin represents 10% of the training population, if the population
structure is unchanged, this % value should remain stable on the application
population. If this is not the case, it doesn’t mean that the predictive model is no longer
accurate, rather that the structure of the population has changed. For example there
are more or less potential churners now, than in the past. The accuracy of the
predictions should be monitored to back up the decisions.

 Note
The number of the bin is set to 10 and isn't customizable.

See the section How does Smart Predict Create Assigned Bins? for information on
using assigned bins.

Outlier Indicator For each row in the application dataset, the Outlier Indicator is 1 if the row is an outlier
with respect to the target, otherwise 0.

An observation is considered an outlier when the prediction error is greater than 3

times the average prediction error found on similar observations.

Predictions: select the predictions to include in the output table:

Prediction Description

Predicted Category For each row in the application dataset, the Predicted Category is the target variable
category determined by the predictive model.
Classi cation predictive models
(nominal target with 2 values The percentage of predicted target variable categories found in the application dataset
only) corresponds to the Contacted Population percentage that is set by default when
entering the Confusion Matrix.

Any change done by the user in the Confusion Matrix does not affect the Predicted
Category in the output dataset.

An alternate way could be to generate the Prediction Probability (instead of the

Predicted Category) and set a decision threshold on the value of the probability based
on the business requirements.

[Link] 5/22
8/9/2020

Prediction Description

Prediction Probability For each row in the application dataset, the Prediction Probability is the probability
that the Predicted Category is the target variable value.
Classi cation predictive models
(nominal target with 2 values
only)

Predicted Value For each row in the application dataset, the Predicted Value is the value predicted for
the target variable.
Regression predictive models
(continuous target)

 Note
If you do not select any statistics or predictions, only the target variable and the key variable(s) are included.

6. Click Apply.

The status of your predictive model is updated to <Applied> and you can nd your output dataset with the predictions
under Main Menu Browse Files . You can then access to your results directly by opening the output dataset or depending
on your business needs, consume the output dataset in a BI story.

Related Information
Input Datasets
Output Datasets
Datasets - Examples

How does Smart Predict Create Assigned

Bins?
While applying a classi cation or regression predictive model to an input dataset, you can require to get the statistics information
on Assigned bins. But what are Assigned bins and how should they be leveraged?

During the training step, Smart Predict uses past observations compiled in a training dataset to create a predictive model.

For a classi cation predictive model: Smart Predict associates to each observation (customer, product, etc…) a probability
that an event (target) occurs. Then it uses this probability to group the list of observations, ranged in decreasing order from
the most probable to the least probable in 10 bins (or groups). Each bin represents 10% of those observations and in each
bin, the observations have the same level of probability.

For a regression predictive model: Smart Predict associates to each observation a predicted value. Based on this value, it
groups the list of observations ranged from the highest to the lowest predicted value in 10 bins (or groups). Each bin
represents 10% of those observations and in each bin, the observations have the same value or range of values.

During the application step, Smart Predict refers to the bins de ned in the training step to assign the current observations from
the input dataset to the relevant bin. It compares each value obtained by the predictive model with the limits of each Assigned bin
de ned in the training step. Then it assigns each observation to the relevant bin.

Why use Assigned Bins in a Classi cation

Predictive Model?
[Link] 6/22
8/9/2020

 Example
Let's take the following example: you want to know if customers will buy your new product "P". You train your predictive model
using an input dataset containing past observed observations for 1,000 customers. As a result, Smart Predict has ranged your
observations as follows:

Bin number Number of customers in the bin Average probability to buy "P"

1 10 customers (= 10% of the dataset) 20%

2 10 customers (= 10% of the dataset) 18%

3 10 customers (= 10% of the dataset) 15%

4 10 customers (= 10% of the dataset) 13%

5 10 customers (= 10% of the dataset) 11%

6 10 customers (= 10% of the dataset) 8%

7 10 customers (= 10% of the dataset) 7%

8 10 customers (= 10% of the dataset) 4%

9 10 customers (= 10% of the dataset) 3%

10 10 customers (= 10% of the dataset) 1%

Then, you use your predictive model to get predictions on a new set of customers. Let's say your input dataset contains
observations on 700 customers.

Smart Predict will give you the following result in the output dataset:

Bin number Number of customers in the bin Estimation of the probability to buy "P"

1 200 customers (~ 29% of the dataset) 20%

2 100 customers (~ 14%) 18%

3 43 customers (~ 6%) 15%

4 27 customers (~ 4%) 13%

5 80 customers (~ 11%) 11%

6 45 customers (~ 6%) 8%

7 50 customers (~ 7%) 7%

8 35 customers (~ 5%) 4%

9 32 customers (~ 5%) 3%

10 88 customers (~13%) 1%

You can use Assigned Bins for two purposes:

Use for assigned bins Description Example

[Link] 7/22
8/9/2020

Use for assigned bins Description Example

Simulating/Estimating the number of At the training step, Smart Predict has

 Example
positives cases. assigned each observation to a bin (one bin
equals 10% of the dataset), which Let's have a look at our example above.
corresponds to a probability to be a positive
At the training step, you know the actual
case.
number of positive targets by bins as you
Smart Predict associates to each customer train your predictive model on known data.
his/her probability to buy the product P and
At the application step, you don't know
check if this probability makes the customer
that. But once the predictive model is
belongs to bin 1, 2, 3, etc. by referring to the
applied, you know for each customer of the
bins de ned in the training step. As each bin is
input dataset to which bin it belongs to. You
associated to an average percentage of
can therefore estimate the total of
positive cases, you can easily estimate the
customers who would buy "P".
number of positive cases.

 Note
It can happen that the distribution of the
observations is not similar (10% of
observations in each bin). It's not because
the structure of the population has
changed that the predictive model is not
relevant anymore (see next point).

Monitoring the population structure Dividing the dataset into bins means that each
 Example
bin should contain +/-10% of the
observations. However, if this changes, then it Having a look back at the example above,
indicates that your population is changing. For you can see that the distribution per bins in
example, there could be an effect that the output dataset is not similar as in the
advertising on social media sites might training dataset. For example, for bin 1, we
in uence and attract more young customers, have 200 customers, which correspond to
rather than other age groups. It doesn't mean 28% of the dataset. It could simply be
that the predictive model is not efficient because you have more "young" customers
anymore. But it may be an alert to check this but with the same behavior in terms of
performance with more recent past data (than buying habits.
the ones used to train the model).

Monitoring the predictive model Once the predictive model has been applied, it
performance. is easier to analyze the classi cation
performance by bins, rather than interpreting
the performance curve. Use the classi cation
rate (see The Metrics) calculated at the
training step associated with each bin, and
detect any variation of this rate when applying
your predictive model.

Why use Assigned Bins in a Regression

Predictive Model?
 Example
In the following example, you want to predict the deal values for the next quarter. Your dataset contains observations on 3,000
customers.

As a result, Smart Predict has ranged your observations as follows:

[Link] 8/22
8/9/2020

Bin Number Number of customers per bin Description

1 300 customers (= 10% of the dataset) Predicted values between 90,001 and
100,000 $

2 300 customers (= 10% of the dataset) Predicted values between 80,001 and
90,000 $

3 300 customers (= 10% of the dataset) Predicted values between 70,001 and
80,000 $

4 300 customers (= 10% of the dataset) Predicted values between 60,001 and
70,000 $

5 300 customers (= 10% of the dataset) Predicted values between 50,001 and
60,000 $

6 300 customers (= 10% of the dataset) Predicted values between 40,001 and
50,000 $

7 300 customers (= 10% of the dataset) Predicted values between 30,001 and
40,000 $

8 300 customers (= 10% of the dataset) Predicted values between 20,001 and
30,000 $

9 300 customers (= 10% of the dataset) Predicted values between 10,001 and
20,000 $

10 300 customers (= 10% of the dataset) Predicted values between 0 and 10,000 $

Then, you use your predictive model to get predictions on a new set of customers. Let's say your input dataset contains
observations on 800 customers.

Smart Predict will give you the following result in the output dataset:

Bin number Number of customers per bin Description

1 110 customers (~ 14% of the dataset) Predicted values between 90,001 and
100,000 $

2 100 customers (~ 13% of the dataset) Predicted values between 80,001 and
90,000 $

3 95 customers (~ 12% of the dataset) Predicted values between 70,001 and

80,000 $

4 85 customers (~ 11% of the dataset) Predicted values between 60,001 and

70,000 $

5 80 customers (~ 10% of the dataset) Predicted values between 50,001 and

60,000 $

6 85 customers (~ 11% of the dataset) Predicted values between 40,001 and

50,000 $

7 75 customers (~ 9% of the dataset) Predicted values between 30,001 and

40,000 $

8 60 customers (~ 7.5% of the dataset) Predicted values between 20,001 and

30,000 $

9 60 customers (~ 7.5% of the dataset) Predicted values between 10,001 and

20,000 $

[Link] 9/22
8/9/2020

Bin number Number of customers per bin Description

10 40 customers (~ 5% of the dataset) Predicted values between 0 and 10,000 $

You can use Assigned Bins to monitor the population structure: As each bin should contain +/-10% of the observations, if these
gures increase or decrease for one or several bins, it indicates that your population is changing and you might need to retrain
your predictive model with more recent data. For example, having a look back at the example above, you can see that the
distribution per bins is quite similar in the output dataset as in the training dataset. However, we could have different results. For
example, for bin 1, we could have 300 customers, which correspond to 37.5% of the dataset.

Consuming Your Predictive Outputs in SAP

Analytics Cloud
Once the predictions are generated, an output dataset is created. You can augment your SAP Analytics Cloud stories or models
using the data available in this output dataset. The process might differ depending on the type of dataset (acquired or live) you
used to generate the output dataset and the insights you want to reuse in SAP Analytics Cloud.

This image is interactive. Hover over each area for a description. Click highlighted areas for more information.

Related Information
Consuming Your Acquired Output Dataset Generated by a Classi cation or Regression Predictive Scenario
Consuming Your Acquired Output Dataset Generated by a Time Series Predictive Scenario
Consuming Your Acquired Output Dataset in a Story
Consuming Your Live Output Dataset in an SAP Analytics Cloud Model
Consuming Your Output Dataset in a Planning Model

Consuming Your Acquired Output Dataset in

a Story
You can consume your acquired output dataset either directly in a story, or in a story via an SAP Analytics Cloud model.
Depending on the type of model, you need to keep different elements in your output dataset to consume it.

Consuming the predictions stored in an acquired dataset

When you apply your predictive model on an acquired application dataset, an output dataset containing your predictions is
created. This output dataset can be consumed in a story using some features available in SAP Analytics Cloud.

 Note
If you want to consume your output dataset in a story or via an SAP Analytics Cloud model in SAP Analytics Cloud, only the
rst 100 columns will be taken into account.

 Note
You need to keep speci c information in your output dataset in order to consume it in a story. The type of information you
need, depends on the predictive scenario type. For more information, refer to the related links.

[Link] 10/22
8/9/2020

You can consume your output dataset:

Directly in a story:

 Note
When you upload the output dataset in a story, it implicitly becomes an "embedded" model.

In a story via a SAP Analytics Cloud model:

 Note
The SAP Analytics Cloud model can be shared with other users.

Related Information
Consuming Your Acquired Output Dataset Generated by a Classi cation or Regression Predictive Scenario
Consuming Your Acquired Output Dataset Generated by a Time Series Predictive Scenario

Consuming Your Acquired Output Dataset

Generated by a Classi cation or Regression
Predictive Scenario
Depending on how you want to consume your Classi cation or Regression Predictive Scenario, you need to keep different
information in your output dataset.

Consuming your output dataset in a story

To consume your output dataset in a story, you need to keep some information:

The application dataset variables, if these variables are not available from another source.

The predictions

The key variable(s)

 Note
If you have speci ed the key variable(s) during the training of your predictive model, it is automatically added.

You can then consume the output dataset directly in a story.

 Note
When you upload the output dataset in a story, it implicitly becomes an "embedded" model.

For more information, refer to the related link Blending Data.

Combining existing data with the generated predictions and consuming them in a
story

[Link] 11/22
8/9/2020
To combine existing data with your predictions, you need to keep the following information in your output dataset:

The predictions

The key variable(s)

 Note
If you have speci ed the key variable(s) during the training of your predictive model, it is automatically added.

Thanks to the key variable(s), you can blend the predictions with other data sources, in the context of a story.

For more information, refer to the related link Blending Data.

Importing the output dataset in SAP Analytics Cloud models

You can rst use the output dataset to create a SAC model and then consume it in a story.

 Note
You will then be able to easily share this model with other users.

For more information, refer to the related link Creating a New Model and Model preferences.

To do so:

1. Create a model (from the main menu Create Model ).

2. Select Get data from a datasource.

3. From the proposed list, select Dataset and browse up to your output dataset.

Related Information
Creating a New Story
Creating a New Model
Model Preferences
Blending Data

Consuming Your Acquired Output Dataset

Generated by a Time Series Predictive
Scenario
Depending on how you want to consume your Times Series Predictive Scenario, you need to keep different information in your
output dataset.

Consuming your output dataset in a story

To consume your output dataset in a story, you need to keep at least the forecasts.

 Note

[Link] 12/22
8/9/2020
The date and signal are selected automatically.

You can then consume the output dataset directly in a story.

 Note
When you upload the output dataset in a story, it implicitly becomes an "embedded" model.

For more information, refer to the related link Creating a new story.

Combining existing data with the generated predictions and consuming them in a
story
To combine existing data with your predictions, you need to keep the forecasts in your output dataset.

 Note
The date and signal are selected automatically.

Thanks to the date variable, you can blend the predictions with other data sources, in the context of a story.

For more information, refer to Blending Data.

Importing the output dataset in SAP Analytics Cloud models

You can rst use the output dataset to create a model and then consume it in a story.

To do so:

1. Create a model (from the main menu Create Model ).

2. Select Get data from a datasource.

3. From the proposed list, select Dataset and browse up to your output dataset.

 Note
You will then be able to easily share this model with other users.

For more information, refer to the related link Creating a New Model and Model preferences.

Related Information
Creating a New Story
Creating a New Model
Model Preferences
Blending Data

Consuming Your Live Output Dataset in an

SAP Analytics Cloud Model
You have generated the predictions in a live dataset and you now want to consume the predictions in SAP Analytics Cloud.
[Link] 13/22
8/9/2020

Context
Live datasets cannot be consumed in SAP Analytics Cloud as they are. To be able to consume your predictions, you need the help
of an IT administrator and to go through some additional steps.

Here is an overview of the full process you have to follow while working with live datasets (see related links for more information):

 Caution
As of Google Chrome version 80, you need to con gure your SAP on-premise data source to issue cookies with
SameSite=None; Secure attributes. If the SameSite attribute is not set, cookies issued by your SAP data source system
will no longer work with SAP Analytics Cloud. Refer to SameSite Cookie Con guration for Live Data Connections for more
information.

 Restriction
Your IT administrator user has to create calculation views before you can consume the output tables containing your
predictions. For more information, see Creating Calculation Views to Consume Live Output Datasets.

Procedure
1. In the main menu of SAP Analytics Cloud, select Create Model .

2. Select Get data from a datasource

3. Click on Live Data Connection under Connect to live data area.

4. In the Create Model From Live Data Connection window, enter the following information:

System Type: SAP HANA

Connection: Select the previously created data connection (to this SAP HANA system)

Data Source: Enter rst 3 letters of the calculation view created by your SAP HANA technical user.

You can then create a story using this model as a source.

Related Information
Creating Calculation Views to Consume Live Output Datasets
Setting up Live SAP HANA Data Access for Smart Predict

Consuming Your Output Dataset in a

Planning Model
Context
You can now leverage your predictive outputs in your planning process by copying them into your master planning model.

 Note
Watch the end-to-end work ow here Information published on SAP site or click a step in the graphic below:

This image is interactive. Hover over each area for a description. Click highlighted areas for more information.

[Link] 14/22
8/9/2020

Procedure
1. Create a new planning model that contains the predictive outputs produced by Smart Predict:

a. From the main menu, select Model Create .

b. Select Get Data From a Datasource and under Acquire Data, select Dataset. Then, browse up to your output
dataset.

c. Under Model Options, select Enable Planning .

d. Save your planning model.

2. Create a Data Action to copy your outputs to your master planning model:

a. Go to Create Process Data Action . See Creating a Data Action for more information.

b. Enter a name and description for your data action.

c. Select the original planning model as default model (= the model you’ve just created). And Save.

d. Click Add cross model copy action. For more information, refer to Adding a Cross-Model Copy Step .

e. Select a target model (your master planning model as an example).

 Note
You might need to ensure that the end date of your master planning model includes the last date of your
forecasts period. For example, if the master planning model end date is 2018 and the forecasts go up to 2021,
then the master planning model end date must be extended accordingly. You can update this end date in the
Model Preference under Planning & Time Range.

f. Do the mapping by setting up the lters: In the master planning model, you have measures (member of the Account
dimension) that you need to match with the predictions.

 Example
For example, if you have requested predictions to forecast your total revenue for the next 3 years, Category
could be Budget; Member could be the dates you want to copy over future dates. If you use the segmented by
option available in Smart Predict for time series predictive models, then you can keep the segmentation: it
appears under Source Dimension and you can simply use drag and drop it. Taking back the example, let's say
you used the segmented by option on the column State, then you can drag and drop this source dimension to
the column State of your master planning model. For more information about segmentation, please check
Understanding Variable Roles.

g. Under Source Member Without Target, select the columns from the output datasets that you need to match with
your current model information. For example, the column containing the predictions is called "Forecast" in a time
series predictive model output dataset. If you were looking for a forecast of a total revenue, you will need to match
"Forecast" with the column from your master planning model which contains the total revenue gures.

 Note
Mapping is only possible if target member values exist in the account dimension in the target planning model.

h. Save your Data Action.

3. Create or Open an existing story that includes the master planning data. For more information, you can refer to Stories.

4. Run the Data Action Trigger in order for the output data to be copied into the master planning model. For more
information, refer to Running a Data Action in a Story

[Link] 15/22
8/9/2020

Publishing a Predictive Model to a PAi

Application
Context
You can publish a predictive model to a Predictive Analytics Integrator (PAi) application as a new predictive scenario, or as a
predictive model within a scenario.

 Note
You can nd more information Predictive Analytics Integrator at [Link]

 Restriction
You can only publish to a PAi Application predictive models that have been trained on acquired datasets. It is not possible to
publish predictive models trained with a live dataset.

Before you can publish to PAi, check the following pre-requisites with your SAP Analytics Cloud administrator:

The PAi connection is available in SAP Analytics Cloud.

You have the application role of Predictive Admin assigned to your user pro le.

Procedure
1. From the main menu, select Browse Predictive Scenarios .

2. Click a predictive scenario in the list.

The debrief page for the predictive model appears showing its statistics and KPIs.

3. Expand the Predictive Models pane at the bottom of the page.

The trained predictive models for the predictive scenario are listed.

 Note
Only a trained predictive model can be published to PAi. It is published to the PAi application as a model speci cation
either as a new predictive scenario, or as a model within a predictive scenario.

4. Click the predictive model version that you want to publish to your PAi application.

5. Click the Publish icon in the toolbar menu for the page.

The Publish to PAi Application box opens.

6. Depending on whether you want to publish the predictive model as a new predictive scenario or a model in a predictive
scenario, enter information for the following elds:

Field Actions

PAi Connection Select a PAi connection. If your connection doesn't appear in the list, see the SAP Analytics
Cloud administrator to make it available. Creating a PAi connection in SAP Analytics Cloud is
described here: SAP Analytics Cloud Connection to PAi for SAP S/4HANA Cloud

PAi Predictive Scenario Browse to the relevant catalog, and either select a predictive scenario to receive the model, or
select New Predictive Scenario to create a new one.

[Link] 16/22
8/9/2020

Field Actions

New Predictive Scenario

Click to create a new predictive scenario with the published predictive model.

Add a predictive scenario name. The name must comply with Namespace rules in
S/4HANA:

S/4HANA Cloud: YY1_

S/4HANA on Premise: Begins with Z or Y

The name of a Predictive Scenario must be all uppercase, and have a maximum of 20
characters.

Add a description to your scenario.

Model: Name Name the predictive model.

Model: Description Add a description.

7. Click Publish.

The publishing progress is indicated by messages in the Status column for the predictive model. The status messages are
described here: Predictive Model Publishing Status Messages.

Predictive Model Publishing Status

Messages
When you publish a predictive model to a PAi application, the following status levels can be displayed that indicate the publishing
progress:

Status Description

Publish Pending Publishing hasn't started, but it is in a queue, and will start as soon as possible.

Publishing Publishing is in progress.

Published The predictive model has been published successfully without warnings or errors.

Publish Failed Publishing couldn't be completed. Click the status icon for more information.

Published with The predictive model has been published, but with one or more issues. Click the status icon for more information.
Warning

Smart Predict Quick Start Guide

Short tour guide around Smart Predict with the Help topics accessible from the application interface.

These topics are accessed directly from the Smart Predict application. We've grouped them together as sort of a short tour guide
around the application interface. You'll be able to create a predictive scenario, as well as add and train a new predictive model
without having any particular knowledge of Predictive Analytics. However, to get the most out of your new predictive scenarios, we
suggest that you take a bit of time to browse about the more in depth topics available in this guide as well.

This section is one we will be developing and adding content to with each release of SAP Analytics Cloud, so you'll get more links,
improved content, and navigation with each updated version.

[Link] 17/22
8/9/2020

View Available Predictive Scenarios

The Browse/Predictive Scenarios page shows the predictive scenarios available to your user pro le.

Click a predictive scenario to access its performance indicators and reports.

Click + to create a new predictive scenario.

If you've arrived here and aren't sure what a predictive scenario is, take a bit of time to read about them in Related Information
before carrying on.

 Restriction
Smart Predict is not available in all regions or for all tenant types.

For more information, refer to the SAP Note 2661746 Information published on SAP site.

Related Information
Create a New Predictive Scenario
Creating a Predictive Scenario

Create a New Predictive Scenario

As you're creating a new predictive scenario, you need to choose one that is relevant to the type of predictive insights you are
looking for. Read the descriptions and examples to help you decide which one is best for you.

Click a predictive scenario type to start creating one.

If you'd like more information to help you choose your predictive scenario, then go to our playlist on YouTube
Information published on non-SAP site. You'll nd worked examples showing how to create and use predictive scenarios.

What happens next?

You'll add a predictive model.

 Restriction
Smart Predict features are not available in all regions or for all tenant types.

For more information, refer to the SAP Note 2661746 Information published on SAP site.

De ne Settings and Train a Classi cation or

Regression Predictive Model
You enter values for certain parameters in the Settings tab. These are used to train a predictive model. Training is a process that
takes these values and uses SAP machine learning algorithms to explore relationships in your dataset to come up with the best
combinations.

Enter values for the following settings:

General: Type a descriptive text for the predictive model.

[Link] 18/22
8/9/2020
Input Dataset: Click the Name box and browse to a dataset that contains the historical data you want to use to train the
predictive model. This dataset must already be available to the SAP Analytics Cloud.

Variable Roles: Click the Target box and select the variable that you want to predict values for.

Candidate In uencer: Variables that explain the target variable values. Certain may have too much in uence on a target
variable, and so can cloud the effect of other variables that are related to your business question. Click the Excluded
Variables box and select the variables that you don't want to be taken into account when the predictive model is trained.

Train: Click to start training the predictive model with your settings. The button is over to the left of the central pane. There
is also a Train Predictive Model icon in the toolbar.

What's next?

The training produces performance indicators that you will use to evaluate the results. This is called debrie ng the predictive
model.

De ne Settings and Train a Time Series

Predictive Model
You enter values for certain parameters in the Settings tab. These are used to train a predictive model. Training is a process that
takes these values and uses SAP machine learning algorithms to explore relationships in your dataset to come up with the best
combinations.

Enter values for the following settings:

General: Type a descriptive text for the predictive model.

Input Dataset: Click the Name box and browse to a dataset that contains the historical data you want to use to train the
predictive model. This dataset must already be available to the SAP Analytics Cloud.

Variable Roles / Signal Variable: Click the box and select the variable that you want to predict values for.

Variable Roles / Date Variable: Click the box and select the date variable used for the date dimension in your dataset.

 Note
Date format must be in one of the supported format:

YYYY-MM-DD

YYYY/MM/DD

YYYY/MM-DD

YYYY-MM/DD

YYYYMMDD

YYYY-MM-DD hh:mm:ss

where YYYY stands for the year, MM stands for the month, DD stands for the day of the month, hh stands for the hour,
mm stands for the minutes, and ss stands for seconds.

Variable Roles / Segmented By: Allows you to split a population into separate parts or segments based on values for one
or more selected nominative columns. A predictive model is generated for each segment. For example, it might be more
relevant to have KPIs on both stores and products. If this type of prediction is useful for you, then click the box, and select
up to ve columns for values that you want to segment by.

[Link] 19/22
8/9/2020
In uencer Variables: Variables that explain the target variable values, some may have too much in uence on a target
variable, and so can cloud the effect of other variables that are related to your business question. Click the Excluded
Variables box and select the variables that you don't want to be taken into account when the predictive model is trained.

Train: Click to start training the predictive model with your settings. The button is over to the left of the central pane. There
is also a Train Predictive Model icon in the toolbar.

What's next?

The training produces performance indicators that you will use to evaluate the results. This is called debrie ng the predictive
model.

Debrie ng Classi cation Predictive Model

Results
A predictive model produces performance indicators and reports as a result of a successful training. Here is a short summary of
the different components that you can use to debrief your results so you can verify the accuracy of your predictive model.

Predictive Power: your main measure of predictive model accuracy. The closer its value is to 100%, the more con dent you
can be when you apply the predictive model to obtain predictions. You can improve this measure by adding more variables.

Prediction Con dence: your predictive model's ability to achieve the same degree of accuracy when you apply it to a new
dataset that has the same characteristics as the training dataset. If it's greater than or equal to 95%, you can consider it a
robust predictive model. If it's less than 95%, then you need to improve it, for example, add new rows to your dataset.

Does the target value appear in sufficient quantity in the different datasets? Get an overview of the frequency in each
dataset of each target class (positive or negative) that belongs to the target variable. For more information, refer to Target
Statistics.

Which in uencers have the highest impact on the target? Check how the top ve in uencers impact on the target. For
more information, refer to In uencer Contributions.

Which group of categories has the most in uence on the target? In In uencer Contributions, you can analyze the
in uence of different categories of an in uencer on the target. For more information, refer to Category In uence, Grouped
Category In uence and Grouped Category Statistics.

Confusion Matrix: Only way to assess the model performance in detail, using standard metrics such as speci city. Thanks
to the Confusion Matrix you can quicky see the actual correctly detected cases and the false detected cases.

Pro t Simulation tab and estimate the expected pro t, based on costs and pro ts associated with the predicted positive
and actual positive targets.

For more information, refer to Confusion Matrix, The Pro t Simulation.

Can I see any errors in my predictive model? Is my predictive model producing accurate predictions? Use a large panel
of performance curves in the Performance Curves tab, to compare your predictive model to a random model and a
hypothetical perfect predictive model:

Determine the percentage of the population to contact to reach a speci c percentage of the actual positive target with The
Detected Target Curve.

Check how much better your predictive model is than the random predictive model with The Lift Curve.

Check how well your predictive model discriminates, in terms of the compromise between sensitivity and speci city with
The Sensitivity Curve (ROC).

Check the values for [1-Sensitivity] or for Speci city against the population with The Lorenz Curves.

[Link] 20/22
8/9/2020
Understand how positive and negative targets are distributed in your predictive model with The Density Curves.

Related Information
Consuming Your Predictive Outputs in SAP Analytics Cloud
Applying a Classi cation or Regression Predictive Model
Publishing a Predictive Model to a PAi Application

Debrie ng Regression Predictive Model

Results
A predictive model produces performance indicators and reports as a result of a successful training. Here is a short summary of
the different components that you can use to debrief your results so you can verify the accuracy of your predictive model.

The Prediction Con dence indicates the capacity of your predictive model to achieve the same degree of accuracy when
you apply it to a new dataset, which has the same characteristics as the training dataset. If the Prediction Con dence is
greater than or equal to 95%, it is considered as a good score. If it is less than 95%, then you must improve your predictive
model, adding new rows to your dataset, for example.

Root Mean Squared Error (RMSE) measures the average difference between values predicted by your predictive model
and the actual values. The smaller the RMSE value, the more accurate the predictive model is.

How does the target value appear in the different datasets? Get some descriptive statistics on the target value per
dataset. For more information, refer to Target Statistics.

Which in uencers have the highest impact on the target? Check how the top ve in uencers impact on the target. For
more information, refer to In uencer Contributions.

Which group of categories has the most in uence on the target? In In uencer Contributions, you can analyze the
in uence of different categories of an in uencer on the target: If the in uence value is positive, we are more likely to get
"minority value". If the in uence value is negative we are less likely to get "minority value". For more information, refer to
Category In uence, Grouped Category In uence and Grouped Category Statistics.

Can I see any errors in my predictive model? Is my predictive model producing accurate predictions? Compare the
prediction accuracy of your predictive model to a perfect predictive model using a graph and detect the model errors very
quickly. For more information, refer to Predicted vs. Actual.

Related Information
Consuming Your Predictive Outputs in SAP Analytics Cloud
Applying a Classi cation or Regression Predictive Model
Publishing a Predictive Model to a PAi Application

Debrie ng Time Series Predictive Model

Results
A predictive model produces performance indicators and reports as a result of a successful training. Here is a short summary of
the different components that you can use to debrief your results so you can verify the accuracy of your predictive model.

Is the main performance indicator high enough to consider my predictive model robust and accurate? Check the quality
of your model performance over the Horizon-Wide MAPE. It evaluates the "error" made when using the predictive model to
estimate future values of the signal, where zero indicates a perfect model. The lower the Horizon-Wide MAPE, the better
your predictive model performance. For more information, refer to Horizon-Wide MAPE.
[Link] 21/22
8/9/2020
What predicted values are provided by the predictive model? Analyze the predicted values for the predictive model over a
set of known data called the validation partition. Check if there are outliers in the forecasts and detect anomalies on the
signal. For more information, refer to The Forecasts, The Signal Outliers and The Signal Anomalies

How accurate is my predictive model? Use the Signal vs. Forecast graph to visualize the predicted values (forecast) and
actual values (signal) for the input dataset. You can then quickly see how accurate your predictive model is, what are the
outliers, the zone of possible errors. For more information, refer to The Forecast vs. Actual Graph and The Signal Outliers.

What are the past data that most in uences the signal? Identify whether the signal is in uenced by the recent past or far
past in the case of an autoregressive component. The lags are numbered with negative integers representing their distance
in the past from the forecast. Lag -1 is the point in the past just before the forecast. Lag -5 is ve points in the past. The
higher the absolute value, the further the point is in the past. For more information, refer to The Lagged Predictors
Contribution

Related Information
Consuming Your Predictive Outputs in SAP Analytics Cloud
Applying a Time Series Predictive Model
Publishing a Predictive Model to a PAi Application

Keeping Informed With The Status Panel

You can keep informed about what happened during the modeling process once it's complete by checking out the Status panel.

At the top of the Settings panel, click to access information on the predictive model, and any errors that occurred during the
generation or apply actions:

View Displays

Summary Once your predictive model has been trained, you can access basic
information on your model, for example, the initial number of
variables, and the number of variables kept to train the model.

Message The area where you can access the error messages. For example, if
the training failed, you can get some information on what went
wrong.

Detailed Logs Logs that display the details of each step of the process. In case of a
problem, it allows you to provide SAP support professionals with
information.

Related Information
Status of a Predictive Model

[Link] 22/22