Using Augmented Analytics

After completing this lesson, you will be able to:

After completing this lesson, you will be able to:

  • Use the augmented analytics features supported by SAP Analytics Cloud

SAP Analytics Cloud Machine Learning Features

SAP Analytics Cloud - Supported Predictive Features

The figure below shows the predictive features supported by SAP Analytics Cloud for acquired data and live data.

Predictive Forecast

Predictive forecasting uses historical data to predict future possibilities. The more historical data there is, the more accurate the prediction. Predictive forecasting takes different values into account, and also looks at trends, cycles, and fluctuations in your data. This data-driven approach optimizes your planning process as it is based on facts, not feelings.

Watch this video to learn about the Predictive Forecast.

The key features of predictive forecasting are as follows:

  • Easy to use
  • No set-up required
  • Use Smart Predict for more advanced requirement
  • Select from existing algorithms:
    • Automatic

    • Linear regression

    • Triple exponential smoothing

    • Add additional inputs

Time Series Forecasting

The figure Time Series Forecasting shows how smart assist allows you to project possible future outcomes at the click of a button.

Now, let's look at the predictive features supported by SAP Analytics Cloud.

Use Predictive Forecast

Task Flow

In this exercise, you will perform the following tasks:

  • Log on to SAP Analytics Cloud
  • Create a New Model
  • Create a New Story
  • Run a Predictive Forecast

Smart Discovery

Smart data discovery is a next-generation data discovery capability that provides business users or citizen data scientists with insights from advanced analytics.

Running a Smart Discovery on a data set uses artificial intelligence to analyze that data and generate a story consisting of Overview, Key Influencers, Unexpected Values, and Simulation pages.

Key Features of Smart Discovery

  • Auto-generate fully populated, multi-tabbed stories with Overview, Key Influencers, Unexpected Values and Simulation tabs
  • Identify actionable insights powered by Machine Learning 
  • Expose key influencers driving business-critical KPIs
  • Analyze outliers to identify impactful decisions 
  • Predict future outcomes with interactive simulation

Watch this video to learn about Smart Discovery.

The figure Smart Discovery: Core KPIs shows how you can understand the main business drivers behind your core Key Performance Indicators (KPIs).

With dynamic text token in chart footers, you can supplement visualizations with smart textual explanations on the contributors behind your data.

SAP Analytics Cloud runs on SAP HANA, so the core predictive features of SAP HANA are available, which includes the Automated Predictive Library (APL) and the Predictive Analysis Library (PAL).

Smart Insights

Smart Insights allows you to quickly develop a clear understanding of intricate aspects of your business data.

Consider you are interested in analyzing the total annual salary spent in North America (NA). You can see that the company has employees situated in three countries: Belgium, Canada and USA. As the company is spending more in the US, explore who are the top contributors.

Let's run smart insights on annual salary in USA.

How to Run Smart Discovery and Use Smart Insights

In this demonstration, we will run a smart discovery within SAP Analytics Cloud. You will develop an understanding of the purpose of various pages that are created by smart discovery.

Based on the dataset in an existing story, you want to see what factors influence the salary you pay your employees. As you are not familiar with HR data, you want to use smart discovery in SAP Analytics Cloud which automatically creates a story for you.

In this demonstration, we will perform the following tasks:

  • Copy an existing story.
  • Run a smart discovery with acquired data.
  • Explain the differences between the overview, key influencers, unexpected values, and simulation page.
  • Use smart insights to gain intrinsic information about key contributors.

Smart Predict

Smart Predict helps you answer business questions that need predictions or predictive forecasts to plan for future business evolution. It automatically learns from your historical data, and finds the best relationships or patterns of behavior to easily generate predictions for future events, values, and trends. Additionally, you get easy-to-understand Key Performance Indicators (KPIs) and visualizations that help you evaluate the predictions accuracy. You can then leverage those predictions and predictive forecasts with confidence to augment your planning model and stories.

You can create one or several predictive models within a Smart Predict. Each predictive model produces intuitive visualizations of the results making it easy to interpret its findings. Once you have compared the key quality indicators for different models, you choose the one that provides the best answers to your business question, so you can apply this predictive model to new datasources for predictions.

  • Trial tenants do not currently support Smart Predict.
  • Smart Predict is not necessarily available on all existing SAP Analytics Cloud tenants. To verify that Smart Predict is available in your SAP Analytics Cloud system, see: SAP Note - 2661746

Planning models can be used as datasources for Smart Predict. This means you get to add predictive forecasts directly to your planning models. You can easily combine dimensions to split your data into entities, getting forecasts for each entity to improve predictive accuracy and confidence. This is beneficial for large-scale forecasting.

Planning users get access to predictive reports so they can see the quality of the debriefs and KPIs. Experiencing the business-orientated insights firsthand will build confidence for them to use the predictive forecasts.


Smart Predict is explained fully in the SACPR1 training: SAP Analytics Cloud: Predictive Functions.

Smart Predict scenarios are as follows:

  • Classification
  • Regression
  • Time Series

Save progress to your learning plan by logging in or creating an account