Lesson: Advanced Analytics With SAP HANA: Graph Modeling

You might also like

Download as pdf or txt
Download as pdf or txt
You are on page 1of 1

Lesson: Advanced Analytics with SAP HANA

techniques. This is because the choice of which algorithm to use must be made by the
developer. So it is important that the developer initially understands the differences between
the algorithms used for data preparation, scoring, and prediction. But they must also know
how to fine-tune the algorithms to reach to desired outcome. For example, a developer would
need to decide when to use the time series algorithm for double exponential smoothing
versus triple exponential smoothing and then how to adjust the parameters to consider trend
or to eliminate outliers. Developers who work with SAP HANA PAL are typically already
working in predictive analysis projects or have a reasonable understanding of the topic.

Automated Predictive Library (APL)


The Automated Predictive Library (APL) is not shipped with SAP HANA but belongs to the
product SAP Predictive Analytics . For customers who use this product they can run their
models in SAP HANA and that is why it is mentioned here. APL is aimed at business users who
do not have (or desire to have) detailed knowledge of the algorithms and the maths behind
the models. The selection of algorithms for data preparations, scoring, and predictions is
completely automated (hence the name). All the business user has to do is to provide the
data and APL finds the best data preparation and predictive models.

External Machine Learning Library (EML)


SAP HANA provides access to external libraries of machine learning models. Google
TensorFlow was the first library to integrate with SAP HANA and today provides access to a
large library of deep machine learning models. Examples of deep machine learning could
include voice recognition, handwriting recognition, image recognition, and more. The machine
learning models are created in the TensorFlow framework and a TensorFlow client is installed
in SAP HANA to create the connection to the TensorFlow server. SAP HANA sends the source
data, such as an image, to the TensorFlow server where it is processed (either in training
mode, testing, or production mode) and the result is passed back to SAP HANA.
Google Tensorflow has become a very popular and a vastly growing framework open sourced
by Google for machine learning data flows and its recent integration with SAP HANA is
essential for the support of the growing applications for IoT.

R
R is an open source programming language used to develop statistical models. The R library
contains thousands of freely accessible algorithms that can be used or adapted to provide
custom predictive and data preparation capabilities. SAP HANA connects to an R server
where the data is processed and the results are passed back to SAP HANA. R language is
becoming increasingly popular among Data Scientists as the standardized language for
statistical computing.

Graph Modeling
Graphs are used to model data that is best represented using a network. Examples include
supply chain networks, transportation networks, utility networks, and social networks. The
basic idea behind graph modeling is that it allows a modeler to define a series of entities
(nodes) and link them with lines (edges) to create a network. This network represents how
each node relates to all other nodes.

© Copyright. All rights reserved. 85

You might also like