This blog post will focus on the analytical services available via
SAP API Business Hub. The SAP API Business Hub provides a lot of functionality. The APIs described here all come from
SAP Predictive service - Business Services. You will use the APIs to register and manage your data source. After it has been registered you can use the other features to create robust reports
Analytics Data set APIs
You start with the
Analytics Dataset APIs because it provide a series of features that manage data sets to be used with the predictive service. These features are:
- Register a data set in the application
- At this time the data set must be HANA. It can be on premise, accessed via the cloud connector, or on the SAP Cloud Platform.
- Unregister a data set
- If you are no longer using the data set for reporting, use this feature to remove it.
- Retrieve registered data set information
- This is used to load the data set information
- Retrieve information on a variable of a data set
- This allows for a more granular selection of the data available in the data set. Retrieve a piece, not everything.
- Modify the description of the data set variables
After loading your data set, you can choose which API you would like to consume to generate your analytical dashboard. The following options are available:
- Clustering
- Forecast
- Key Influencers
- Outliers
- Recommendation
- Scoring Equation
- What If
In the space below, I will describe the functionality offered by these APIs. They are all REST services. The details on how to call them can be found by visiting
SAP Predictive service - Business Services.
Clustering APIs
The Clustering service analyzes a data set and segments it into homogeneous clusters.
The service groups similar entities of a data set into clusters. The resulting clustering information is then exported to the SAP HANA database. The clusters IDs can be written to a database table or view.
The end user must specify the numbers of clusters that the service should return, expressed as a range. The service returns the best clustering whose number of clusters is in the range.
The user must also set the name and schema of the table or view where the results are stored. Optionally, they can choose the variables from which the clustering can be defined and set a target variable in case of supervised clustering.
The service returns information on the clusters and stores results into the requested table. It also provides model performance information in case of supervised clustering.
Forecast APIs
The Forecasts service analyzes a dataset containing the successive values of a target indicator over time to predict the next values.
This service:
- Generates forecasts based on patterns detected on the time series
- Provides information on the detected pattern: trends, cycles, fluctuations
- Provides indicators on the reliability of the results
- Enables you to modify the modeling process to improve the results (variables, forecast modeling method)
Analytics Key Influencers APIs
The Key Influencers service analyzes a data set to identify the variables with an influence on a specified target.
This service:
- Identifies the variables with an influence on a specified target ordered by decreasing contribution
- Returns detailed information on the grouped categories for each contributive variable
- Returns the variables excluded from the analysis
- Returns the variables that are correlated with each other
- Provides indicators on the reliability of the results
Outliers APIs
The Outliers service identifies the odd profiles of a data set whose target indicator is significantly different from what is expected.
This service:
- Identifies outliers contained in a data set with regard to a target indicator
- Ranks the outliers to get the oddest on top
- Provides the reasons why an identified outlier is odd
An outlier can either result from a data quality issue to correct or represent a suspicious case to investigate.
Recommendation APIs
The Recommendation APIs provide a set of services that allows you to create a recommendation model and generate recommendations from it.
The services compute the model and its recommendations based on a transaction data set. The data set contains information about user transactions, which consist of customer/purchased item pairs.
Scoring Equation APIs
The Scoring Equation service builds a predictive model from a data set and exports its scoring equation to either an SAP HANA SQL query or a score card in CSV format.
This service:
- Returns the scoring equation of a predictive model
- Provides indicators on the reliability of the results
The scoring equation generates predicted values for each data point of the specified data set. In regression cases, the predicted value corresponds to an estimation of the value of the target indicator. In classification cases, the predicted value corresponds to a score. The more likely a data point is a target, the higher the score is. This score does not have any semantics and can only be used to sort out data points from more likely to less likely to be a target. However, it can be converted into a probability by setting the predictedOutputType parameter to probability.
What If APIs
The What If service simulates a planned action and returns the significant changes that result from it.
This service:
- Provides the list of deviant variables
- Provides the list of deviant categories for each deviant variable
- Provides statistics of the variable on both original and simulation datasets
The simulation consists of changing the weight assigned to a group of values of the variable. The service returns the deviations observed on the series of variables affected by this change and lists the affected categories for each of them. It also compares the frequency of each category before and after the change is applied.
Along with the predictive analytical APIs shown above there is the
SAP Analytics Cloud. You can learn about the features available on the SAP Analytics Cloud by attending open SAP class
Analytics with SAP Cloud Platform.
