IoT Big Data – Predictive Analytics and SAP Solution


What is predictive Analytics (PA)? PA is the understanding of the factor influencing the past to determine what could happen next and even what could be done to positively influence future outcomes.

According to Machina Research, the emergence of “millions and millions” of connected devices has seen big data analytics shift its focus towards forward-looking data insights, and away from historical data patterns.

Algorithmically, predictive analytics analyzes historical data to find trends and patterns to understand relationships between elements. By understanding these relationships, companies can make better decisions.

What is the evolution and maturity of analytics capabilities? Analytics started as analyzing the past and responding to it (descriptive analytics). With IoT the goal is to analyze the information in real time, study patterns, predict best course of action and act on it (predictive and prescriptive analytics). See diagram below.




SAP Predictive Analytics (PA) is a solution with the purpose to create, deploy, and maintain thousands of predictive models to anticipate future behavior or outcome, and guide better, more profitable decision-making across the digital enterprise.

SAP PA is a single platform that enables everyone to benefit from an automated predictive solution that encompasses the full predictive lifecycle, from model creation to validation and deployment, without sacrificing speed, power, or scalability.


SAP PA Functional Capabilities
  • Automated analytics

Allows business analysts and data scientists to use an automated technique to build sophisticated predictive models that can be embedded in business processes – in days, not weeks or months.

  • Expert analytics

Builds predictive models with a powerful drag-and-drop interface, and allows users to use their own R1 scripts.

  • Model management

Provides end-to-end model management, maintains peak performance for thousands of predictive models, and schedules updates as needed.

  • Data Manager

Data Manager provides a framework to facilitate automated data preparation. Users can define a broad set of reusable components, which can be applied to automatically create modeling data sets.

  • Predictive scoring

Get individual variable contributions for every predictive model. Simulates, and scores of a specific business question – in real time. Generates predictive scoring for a wide variety of target systems and directly embeds the results.

  • Social and recommendation

Runs powerful networks and links analysis to understand the connections and relationships between your customers – and discover which customers have a strong social influence. This capability can help you better manage churn, risk, and fraud.

  • Advanced Visualization

Advanced Visualization provides an intuitive way to explore your data. Transform the results of applied predictive modeling into stunning, advanced visualizations that reveal actionable insights.


SAP PA Technical Capabilities
  • Predictive automation

Supports both SAP and non-SAP environments.

  • Big Data analytics

Automates the building of predictive models based on data stored in Hadoop (it is an open source, Java-based programming framework that supports the processing and storage of extremely large data sets in a distributed computing environment). Does data manipulation, model training, and retraining directly on Hadoop data using the Spark engine.

  • Automated predictive library

Uses the application’s automated analytics engine and data mining capabilities on your data stored in SAP HANA.

  • R integration

Leverages tight integration with R to enable a large number of algorithms and custom R scripts for analyzing your data.





Business and strategic decisions are being augmented with highly operational and predictive / prescriptive analytics, shifting the ground from ‘look at what happened’ to ‘what may happen’ and how best to address those potential scenarios.

1 – R is a software environment for statistical computing and graphics.



>>>>>  <<<<<


Your opinion and feedback are important to me


One thought on “IoT Big Data – Predictive Analytics and SAP Solution”

  1. Pingback: IoT Big Data – IoT Analytics Solution, Pentaho • The Internet of Things

Leave a Comment

Your email address will not be published. Required fields are marked *