Predictive Analysis - KXEN is not a Radio Station - ASUG Webcast - Part 1

SAP's Charles Gadalla provided this webcast today.

Figure 1: Source: SAP

On the left of Figure 1, high skill sets are needed to be a data scientist, with a masters in statistics.

On the right side, you have business users

Consumers take output from data scientists and take an action.

In the middle: data analysts/business analysts – do more than basic reporting – segmentation, forecasting, in a more sophisticated manner

Figure 2: Source: SAP

Data scientists on the far right of Figure 2 are already well served.

SAP is interested in group in the middle, including embedding the analytics inside the workflow

Figure 3: Source: SAP

Figure 3 shows a paradox that there is a lot of “big data”.

We are using more data today and decisions are made in a much shorter time scale, with a huge increase in speed of algorithms

Every business is being asked to make decisions faster with more data

Why should I care?

Figure 4: Source: SAP

Figure 4 shows that back in December, SAP released a survey, showing competitive "ROI"

Figure 5: Source: SAP

Figure 5 shows Mobilink going through 900TB call data records for communities – 6M communities from these calls

MONext – decision on fraud transactions in milliseconds

Figure 6: Source: SAP

It was on this slide that Charles said "KXEN doesn't stand for a radio station...it means knowledge extraction engine".  I did not know that.

Figure 7: Source: SAP

Insight from KXEN to view thousands of fields of data; Predictive Analysis was built inside SAP

Charles used as an example if you drink a diet cola on Tuesday at that means you had chips on a Sunday

Another example is to integrate and tell story as Predictive is built on Lumira

Figure 8: Source: SAP

Figure 8 shows data comes in from any of the channels

PAL is on HANA is the implementation on HANA R – maintained by universities and consortium – popular algorithms to use and reuse – execute in memory,

It is based on an open source language

Client tools on top left of Figure 8.

SAP combined Predictive Analysis with Insight in a tool called Insight Modeler

It also includes a line of business application – like Fraud Management, etc.

SAP has RDS solutions using Predictive

They partner with ESRI, SAS

Charles has special speaker from Obama campaign presenting on how the Obama campaign used KXEN to win the 2012 US Presidential election.

Figure 9: Source: SAP

With SAP embedded on HANA, you are not getting the SAS algorithm

You can see the two ways to access HANA in Figure 9

Figure 10: Source: SAP

Three options:

1) Client side – PA/KXEN – Java based and R based predictive  - connect to relational database and CSV

2) Server – Infinite Insight Explorer – connect to database (say Oracle)

a. Factory – model management – how data looked 1-2-3 months

b. Factory scheduling to refresh

c. Infinite Insight Social – trying to detect similar/like-minded people

d. Recommendation engine – buy brown shoes, likelihood to buy belt

3) Third option is HANA – with PAL in memory, connected to R

More to come...

Related:

ASUG Annual Conference has the following SAP Predictive sessions:

Charles is presenting the Predictive Analysis Roadmap and co-presenting "Using Analytics to Help Win the US Presidency".

Join us in May for ASUG Annual Conference   - Pre-Conference SAP BusinessObjects BI4.1 with SAP BW on HANA and ERP Hands-on – Everything You Need in One Day June 2nd

Register at: ASUG Preconference Seminars

Share your Story: Call for Sessions for ASUG at SAP d-code (former TechEd)

Share your knowledge with others and submit a proposal to speak at SAP d-code. Selected proposals will be part of the ASUG and SAP d-code: Partners in Education program, providing attendees with interactive learning experiences with fellow customers.

View the education tracksplanned this year.  If selected, you will receive a complimentary registration for the conference and it will give you valuable professional exposure.

Follow this linkto create a speaker account where you can formally submit your proposal, review important deadlines, and other general information about SAP d-code.

The deadline to submit your abstract is May 25. If you have any questions, please e-mailsapdcodespeaker.info@sap.com