Attached a short Summary regarding Predictive Analytics.
Important for Sales.
Link for the Summary (I´m not allowed to upload a pdf document):
Attached a short Summary regarding Predictive Analytics.
Important for Sales.
Link for the Summary (I´m not allowed to upload a pdf document):
Continuing from our earlier blog where I talked about how to access the HANA cloud image on AWS for Predictive Analytics, herewith I am attaching a short 20min video which explains the complete process.
This was probably already addressed by another blog post but I couldn't find it unfortunately, so if you find it’s a duplicate, I’ll withdraw mine.
One of my colleague at SAP asked me this question and I kind of found out that the answer was not so obvious if you haven't played with the new “Auto” algorithm feature for long.
Also I think this could apply to any HANA online scenarios.
So, usually when you use the “Expert Analytic” (former Predictive Analysis), with text files, you were able to add your initial data set, create an “Auto-Classification”, save the model and then add a new data set and finally apply the saved model.
But when working with HANA online, “Expert Analytic” allows you to only work with one data set. In other words, you cannot add a new data set in the “Prepare” room.
So how do I apply a model I build with my training data on a new data set?
The answer is not far from what the “Automated Analytic” module is doing when using it in a production environment. You will first need to export the model, then apply it to your new dataset.
Next question is how do I export my model?
But let's start from the beginning, after launching the Expert Analytic, create a new “Document” and select "Connect to SAP HANA One"
Next is to enter your HANA connection details then hit “Connect”:
Then, select your dataset
The dataset will be analyzed, and the column names and type will be retrieved.
Now you can select the “Predict” room, add your “HANA Auto-Classification” algorithm, configure it, then you can run it ,
Once the run phase is completed, you can then right-click on the “HANA Auto-Classification” node and use the “Save as Model” item.
Once saved, the model will appear on the right side bar under “Models”. Select the saved model, then click on “Export Model”
From the following popup, use the “.spar” file format.
Save it on your desktop for example.
Now, your model has been exported, so we now have to create a new “Document” and select "Connect to SAP HANA One", select your the dataset to be scored. Then, on the right side bar, you can click on the “+” sign, and use the “Import Model” item.
Select the “spar” file previously created
Select the model to import from the list
You will now be able to use it in the "Predict" room to score your new dataset.
Hope this save you some time.
This article was built using SAP Predictive Analytics 2.1 using a HANA instance where the Automated Predictive Analytics (APL) was previously setup.
Any comments, feedback or opinions are very welcome!
Attending SAPPHIRE NOW / ASUG Annual Conference to be held in Orlando, Florida from May 5-7? SAPPHIRENOW is an enormous show and to get the most of your 3 days, we have recommended 12 predictive sessions you should include in . But attending lectures, panels, microforums is not enough. To see our predictive analytics solutions in action, here's 5 demo sessions not to be missed:
Make More Meaningful Business Decisions by Using All Your Big Data
Enable better decisions, improve business results, and support your Big Data initiatives in a simpler manner while minimizing costs by providing complete, accurate, and accessible information from all data sources. Manage and integrate large volumes of data and get real-time response rates regardless of data volume, location, or type.
Transform Your Business with the Internet of Things
Discover how the Internet of Things will transform your existing business operations. See how SAP HANA Cloud Platform supports the IoT by enabling enterprises to process large volumes of data generated by thousands of sensors to allow real-time and predictive decision making that can revolutionize your products and services.
Personalize Customer Relations with Predictive Analytics
Discover how embedded predictive applications have the ability to anticipate, learn continuously, and provide the right context and content at the right time. Watch and learn how you can enhance customer relations with SAP Predictive Analytics software.
Combat Fraud with Predictive Analytics
Find ways to uncover and prevent fraud with a powerful analytic application. Learn how, when combined with predictive analytics, SAP Fraud Management goes beyond detection to actually prevent fraud by spotting the events and conditions preceding fraud and averting its occurrence.
Build a Predictive Application in 10 Minutes
Discover how predictive applications have the ability to anticipate, learn continuously, and provide the right context and right content at the right time. Watch as a predictive application is built using SAP Predictive Analytics software in the cloud in just 10 minutes.
Hope to see your there.
Pierre Leroux, @pileroux
Attending SAPPHIRE NOW / ASUG Annual Conference to be held in Orlando, Florida from May 5-7? Predictive analytics should be on your list of hot topics to check (read why) during these three days. Here are 12 predictive sessions you should include in your schedule:
Tuesday May 5
1. Microforum PT20340: Discover Why Your Business Needs Predictive Analytics Now 11:00-11:45 a.m.
Go beyond “what happened.” Discover the major role that predictive analytics plays in letting your organization respond to change before it happens.
2. Demo Theater GS21990: Take the Guesswork Out of Trade Promotions with Predictive Analytics 1:30-1:50 p.m.
Focus on promotions that are most likely to achieve objectives by making data-driven decisions based on predictive analytics. Understand price and time sensitivity, true net lift, and volume drivers. Simulate promotions, regular business, and customer plans.
3. Lecture BI747: Improving manufacturing processes with SAP HANA Predictive Maintenance at Mohawk Industries 3:00-4:00 p.m.
Learn how Mohawk, the world’s leading flooring manufacturer, uses SAP HANA and predictive analytics in its predictive maintenance program to increase product quality by improving its manufacturing process parameters.
Wednesday May 6
4. Demo Theater PS20796: Determine Propensity to Buy Using Advanced Visualization and Analytics – 12:00-12:20 p.m.
Searching for better ways to learn customer spending habits? Use predictive analytics to identify customer buying behavior and forecast for better sales and planning.
5. Demo Theater IN20709: Benefit from the Convergence of IT and Operations in the Internet of Things 1:30-1:50 p.m.
Take advantage of the Internet of Things and of the new analytical and predictive capabilities that result from the integration of smart data from various devices.
6. Lecture BI121: Deploying Predictive Analytics Solutions – How Lockheed Martin Space Systems Forecast Supply Chain Management Performance 2:30-3:30 p.m.
Learn how Lockheed Martin Space Systems and SAP teamed up to deliver a predictive analytics capability to forecast supplier scheduling performance and better manage and engage with suppliers.
7. Microforum PT20341: Experience the Power of Predictive Personalization 4:00-4:45 p.m.
This discussion centers on how customers today demand a personalized experience in every interaction, through every channel, every time. Transform the customer experience with advanced personalization approaches enabled by predictive analytics.
8. Lecture BI109: Predictive Analytics 2.0 Roadmap 4:15-5:15 p.m.
This session will appeal to anyone interested in predictive analytics from SAP and how this space is evolving. A roadmap will be shown as well as use cases and success stories.
9. Theater Presentation PT21256: Enlighten Customer Services with Real-Time Analytics 5:00-5:20 p.m.
See why rapid global expansion, while good for business, puts pressure on IT to provide easy access to critical data, identify market trends, and react faster to customers’ needs.
Thursday May 7
10.Panel Discussion PT25133: Simplify, Innovate, and Transform Your Business with Analytics and Mobile 9:00-9:30 a.m.
See how companies have harnessed the power of SAP technology to transform the way they serve their customers and employees to maximize performance and innovate business models.
11. Demo Theater PT20332: Combat Fraud with Predictive Analytics 1:00-1:20 p.m.
Learn how, when combined with predictive analytics, SAP Fraud Management goes beyond detection to actually prevent fraud by spotting the events and conditions preceding fraud and averting its occurrence.
12. Demo Theater PT20330: Build a Predictive Application in 10 Minutes 1:30-1:50 p.m
Discover how predictive applications have the ability to anticipate, learn continuously, and provide the right context and right content at the right time. Watch as a predictive application is built using SAP Predictive Analytics in just 10 minutes.
Looking for more? We have over 141 sessions and demos showcasing predictive. View all SAPPHIRE predictive sessions here (check predictive analytics under platform and technology).
Finally, if you arrive early, you can catch the ASUG pre-conference seminar: Hands-On Predictive Modeling and Application Development Using SAP HANA Predictive Analysis Library (PAL) and R
Looking for predictive demos? View my list of 5 demos not to miss at SAPPHIRE Now: 5 #Predictive Demos Not To Miss at #SAPPHIRENOW
Hope to see your there.
Pierre Leroux, @pileroux
Note: This blog post was originally published on SAP Analytics Blog
On a vibrant online community, there is so much activity that you may miss some pieces that were voted in by your peers. Here are the most viewed ones published in Q1 2015; if you did not have the time yet to read them, it’s time to!
#1 Introducing SAP Predictive Analytics 2.0! - by Ashish Morzaria
This blog post introduces our new product SAP Predictive Analytics (combination of SAP Predictive Analysis and SAP InfiniteInsight, and their advanced predictive capabilities), full of tips and delivering the essential: explaining the Why, what it brings to you, what’s new in, how to get started and what’s next!
#2 14 Examples on How to Use Predictive Analytics Solutions - by Pierre Leroux
14 short and fun videos covering a large spectrum of key predictive possibilities on common business cases that can also give you fresh ideas on how to address critical questions whatever your company’s industry!
#3 Basket Analysis with SAP Predictive Analysis and SAP HANA - Part 1 - by Ian Henry
Market Basket Analysis (MBA) is a common predictive use case. It allows to find relationships between purchases when many products are involved. The three part article explains how you can do MBA with SAP Predictive Analytics and SAP HANA.
#4 What is the SAP Automated Predictive Library (APL) for SAP HANA? - by Ashish Morzaria
A detailed, very complete article about (APL) – a major milestone in our efforts to integrate and embed our advanced analytics services everywhere and into everything!
#5 3 Easy Steps to Run Predictive Analytics on Hadoop - by Victor Lu
Automated Analytics (formerly SAP InfiniteInsight) made ‘run predictive analytics on Hadoop’ easy and available to non-Data Scientists. Learn more!
#6 Try SAP Predictive Analytics (a HANA Cloud Image) on AWS - by Venkata Raghu Banda
Rapid Deployment Solutions is a key part of our community. The first sentence of this article will urge you to learn more: “The wait is over! (…) Now SAP Predictive Analytics scenarios can be simulated and run on the AWS cloud in the context of HANA.”
#7 7 #Predictive Sessions You Should Attend @ #BI2015 in Las Vegas - by Pierre Leroux
Yes #BI2015 Las Vegas is over but stay tuned: #BI2015 Nice is coming (June 16-18)! More about the predictive sessions there to come soon!
#8 2015 College Basketball Predictive Analysis - by Charles Gadalla
A predictive and visualization challenge around the federator sport that is basketball? Yes it is! 2015 #VizTheMadness Challenge powered by SAP Lumira & SAP Predictive Analytics
#9 Predictive Analytics 2.0 – What is New - ASUG Webcast - by Tammy Powlas
In case if you missed the ASUG webcast “What’s New in SAP Predictive Analytics 2.0?”, Tammy put together the key takeaways for you. Here!
#10 SAP Predictive Analytics 2.0 30-Day Trial Now Available! - by Ashish Morzaria
The most expected SAP Predictive Analytics 2.0 trial is available, try it now!
There are many predictive resources available on SCN and sap.com/predictive! Here are 3 ways to get engaged:
- Follow the SAP Predictive Analytics community to be informed as soon as there is something new posted or discussed here
- Check the ‘Content’ tab to make discoveries here
- Follow your favorite authors to be informed when they publish a new piece
And don’t forget the tutorials page that is updated on a regular basis and where you find tons of crucial tips!
In 3 weeks ASUG Annual Conference begins, co-located with SAPPHIRENOW. Last year's ASUG SAP Predictive sessions was highlighted by Peter Tanner, who used to work for the Obama campaign. The campaign used SAP predictive tools to as a way to analyze and mine social media, and send targeted e-mails. I am thinking of this today as the 2016 US Presidential campaign kicks into high gear.
For sure please consider adding the following ASUG Predictive Analysis sessions to your agenda, selected by ASUG Volunteers:
|CODE||SESSION NAME||SESSION DESCRIPTION|
|BI109||Predictive Analytics 2.0: Roadmap, what's new and what's next||This session will appeal to anyone interested in Predictive Analytics from SAP and how this space is evolving. A roadmap will be shown, as well as use cases and success stories. At the end of this session, you should have a good idea of how to make your business smarter with SAP.|
|BI1521||Deploying Predictive Analytics Solutions – How Lockheed Martin Space Systems Uses Predictive Analytics to Forecast Supply Chain Management Performance||Learn how Lockheed Martin Space Systems and SAP Data Science teamed up to deliver a predictive analytics capability to forecast supplier scheduling performance using R, SAP HANA, SAP Data Services, SAP Enterprise Resource Planning and SAP ABAP Acceleration to help Lockheed Martin better manage and engage with its suppliers.|
|BI747||Improving manufacturing processes with SAP HANA Predictive Maintenance at Mohawk Industries||Learn how Mohawk, the world's leading flooring manufacturer, uses SAP HANA and predictive analytics in the "Predictive Maintenance" program to increase product quality by improving its manufacturing process parameters, including many millions of sensor data readings. Also learn about SAP's related customer co-innovation program.|
The Lockheed session above is not to be missed; they share their experiences with the SAP Data Science team.
But there's more to come. Starting very soon, ASUG will have call for speakers for SAP Analytics & BusinessObjects Conference in Austin, Texas August 31-September 2nd. Next week, April 20th, call for speakers for ASUG sessions at SAP TechEd Las Vegas (October 19-23) start.
If you can't make the face to face events, ASUG has the following webcasts planned related to Predictive Analytics:
So take advantage of your ASUG membership to help you predict the future.
Only 28 days before SAPPHIRE NOW / ASUG Annual Conference held in Orlando, FL on May 5-7. Here are 5 reasons why you should put Predictive Analytics at the top of your list of hot topics to check out during these 3 days:
1. Stay on the Analytics Cutting Edge – Predictive analytics have been around for a while but we are currently in an era where predictive is blended with big data, Internet of Things, in-memory platform, business apps, web store, etc. Learn about the latest in making predictive pervasive.
2. Hear Real Case Examples – More and more government agencies and businesses – big and small, are using predictive analytics to take advantage of their data. Come and hear firsthand how they use predictive analytics just like Lockheed Martin Space Systems does to forecast supply chain management performance.
3. Exchange Best Practices – Witness case studies, hear real-life experiences and discover how best to implement predictive analytics – just like the world's leading flooring manufacturer did to increase product quality by improving its manufacturing process parameters.
4. Network with your Peers. Through face-to-face interactions with executives, industry experts, peers, and SAP partners, you’ll be able to leverage a diverse skillset unmatched at any other event this year and keep growing your network long after SAPPHIRE NOW is over.
5. Come back home with fresh ideas and takeaways on how predictive analytics, once the exclusive domain of Data Scientists, can now be applied to your work and used by all.
View my list of top 12 predictive sessions you must attend at SAPPHIRE Now: 12 Must See #Predictive Sessions At #SAPPHIRENOW
View my list of 5 demos not to miss at SAPPHIRE Now: 5 #Predictive Demos Not To Miss at #SAPPHIRENOW
Looking for more? We have over 141 sessions and demos showcasing predictive. View all SAPPHIRE predictive sessions here (check predictive analytics under platform and technology). View all SAPPHIRE predictive sessions here (check Predictive Analytics under Platform and Technology).
Got questions about our predictive analytics presence at SAPPHIRE? Contact me at @pileroux.
The SAP Predictive Analytics team look forward to seeing you in Orlando!
Learn to use the latest versions of SAP HANA tools to leverage R and PAL algorithms in your application. Attend the ASUG/SAPPHIRE hands-on pre-conference session to create predictive models, flowgraphs and applications. We will also teach you how to easily use predictive models with our text analysis capabilities in HANA. This will allow you to get real insights and make predictions from crowd-sourced or other unstructured content.
Join Christoph Morgen and me in Orlando on May 4th. Click here to learn more and/or register. In the session we will cover SAP HANA Predictive Analysis Library, Application Function Modeler and integration with R.
Here is a short example video of a flowgraph being created in in SAP HANA.
I hope to see you there!
Continuing from our earlier blog where I talked about the new HANA cloud image (hosted on AWS) that was available to test a few predictive analytics scenarios, I would now like to take a few minutes to discuss about how to make the basic set-up work easily. There are a few things you need to make sure are available before you set out to try and test the predictive scenarios in the 15 day free trial.
As you know the trial edition is available in the SAP Store. Users access the trial landscape from their laptop through a remote desktop connection. The system landscape is hosted by Amazon Web Services and accessible via the SAP Cloud Appliance Library (SAP CAL). You will need to create an Amazon Web Services account and a SAP CAL account if you do not yet have one. And then before starting the exercises given on the trial cloud image, you need to create your personal system landscape (instance) in the SAP Cloud Appliance Library (SAP CAL). Then you can activate and suspend the instance as you wish.
There is a hosting cost associated with using Amazon Web Services and it is approximately 2 U.S. dollars per hour, while the landscape is active plus approximately 4 U.S. dollars per week as static IP addresses are used. We estimate that you will need the system for 8 to 16 hours. Cost is calculated based on active time within the landscape. Please make sure you suspend the landscape after you have finished using it (e.g. between exercises), otherwise you continue to incur costs. Terminate your landscape after you are done with all exercises or with your trial evaluation.
We wish you fun with exploring the Trial! PLEASE PROCEED AND READ THE INSTRUCTIONS BELOW TO CONTINUE: 3 Simple Steps
1. Firstly create an AWS account, if you don't have one.
Creating an Amazon Web Services Account and getting your security credentials (if not yet available)
Create an Amazon Web Services (AWS) account by following the instructions.
Go back to amazon home page http://aws.amazon.com Select "My account/ console" and "Security Credentials" in the drop down list.
Continue to create your security credentials
Go to Access Keys, click the button Create New Access Key. You will get asked to download your access key file with your security credentials and secret access key. Store your keys locally.
Alternative: If you want to allow other users to access resources in your
account, use the Identity and Access Management (IAM) console to create
credentials and assign permissions for each user. Please follow the instructions here.
2. Secondly create a SAP Cloud Appliance Library (SAP CAL) account (if not yet available)
Go to http://scn.sap.com/welcome , click on Join us (at the top of the page) and create a SAP CAL user.
3. Thirdly now create your instance in the SAP Cloud Appliance Library (SAP CAL) (only applicable once)
Go to SAP Store and click on Demo Now to access the system and create and instance.
(We recommend to use Internet Explorer or Chrome. Experience shows there are issues with some other browsers like Firefox.)
Accept the Terms and Conditions.
Enter your Access Key and Secure Key(security credentials from Amazon Web Services) if needed or when asked!
Choose a password for your instance e.g. "Welcome1" and this becomes the master password.
Instance is created within approximately 30 minutes. A green icon appears next to the name of your instance when the instance is activated.
Do not forget to suspend the instance after you have finished using it (e.g. between exercises), otherwise you continue to
These are the 3 simple steps in getting you access the HANA Cloud image on AWS for Predictive Analytics in the SAP Store.
If there was one cross-vendor event for analytics that opens your eyes as to “what’s out there”, it is likely the Gartner BI and Analytics Summit that just wrapped up in Las Vegas this week. Many customers come to this conference to understand their strategic options with their existing vendor, as well as what the new “up and comers” are up to. As an employee of one of the vendors, it is also a chance to see if the industry is going in the same direction we are.
So what are the “Big Takeaways” that are guiding the industry in 2015 and beyond?
Francis Ford Coppola Is One Cool Guy
Okay, this one isn't guiding the industry, but it definitely had an impact on the audience: We heard the legendary film director, producer, screenwriter, and wine maker Francis Ford Coppola give his humorous and extremely insightful views on almost any topic the audience could come up with - from his experiences in film making and wine production to predictive technologies, Big Data, and even when to consider instinct and passion versus algorithms and raw data. This was clearly the highlight of the conference.
Big Data Is Watching Us
If you have a pulse, you likely have heard about this thing called “Big Data” and it knows the answer to everything you could ask (hint: the answer isn’t “42”). As an abstract concept, the vast Volume of data from a Variety of places at high Velocity with varying levels of Veracity (quality of data) sounds great, but few organizations really know how to get there or what to do when they reach “Big Data Nirvana”.
The attendees of the Gartner conference may have been unwittingly part of a Big Data project themselves. A colleague of mine was surprised to find that the Gartner website knew which sessions he attended – and which he didn’t. It turns out that each attendee’s name badge had a tiny RFID tag that was only visible if you held it up to the light.
To track the movement of each person, above the door of each session room, and even littered in the hallways were RFID readers placed like ordinary furniture.
YES, Gartner knows when I reached a session, when I left, whether I attended the keynote, how long I was on the exhibit floor, even if I attended the evening reception. Add to that the “booth scans” when I talk to someone or whenever they give me a cute toy, and Gartner knows which booth I went to, when, and a has pretty good idea of the percentage of my total time spent at that booth.
They can also quite easily cluster people based on the common sessions each goes to and determine trends based on actual intent and action rather than those sometimes annoying surveys. They can fine-tune the conference in close to real-time and even market my interest patterns back to the vendors of the sessions I attended.
Big Data’s “Veracity” Is a Killer
The fatal flaw in this story is that while the Gartner website accurately placed me at the show floor (I was booth staff) and even caught the one session I was pulled into that I didn’t register for, it also listed me in the keynote and a couple random sessions in one afternoon – I call it a 3/6 score. Helpfully the Gartner session review site allows me to add sessions I actually went to and signal which ones I was erroneously placed at - and if I fill out the reviews, I might even win a prize! Oh wait, did I just help them improve the data quality for information they can use for better analysis on me? Yup. That was sneaky – but also very smart.
As any data scientist will tell you, preparing and cleansing the data is definitely the largest burden on finding any useful information in Big Data – “Veracity” issues included. But let’s say I play along and “Enter the draw for a prize” by filling out my surveys to help Gartner cleanse their data on me: Gartner still has a huge job to do – the raw data is not enough. For example:
Predictive Analytics is The Core of Any Big Data Strategy
Data Scientists are in such high demand because as the data has more “Velocity”, “Volume”, “Variety”, and “Veracity” issues, a human simply cannot glean insights using visualization and instinct alone. We turn to algorithmic analysis which has proven to be far better at finding patterns than any size army of humans with the latest BI tools. These highly trained people are also highly paid because they can easily justify their value: The ROI of even a 10% improvement could be worth millions of dollars.
Every vendor at the Gartner conference had a big data story and no vendor can do a thing without some form of “predictive” or “advanced” analytics – after all, isn’t the point of collecting all this data to discover insights that can be used to improve outcomes (by “predicting a better outcome if certain actions are taken”)?
One of the key takeaways from the Gartner conference is that Big Data is only as good as the insights you can gain from it. Big Data hasn’t quite exhausted it’s “buzzword value” yet, but it is clear more vendors and customers are realizing it’s the analytics on top of it that really rings the bells. It’s really too bad that those million-dollar insights require such specialized knowledge!
The Future of Predictive Is Invisible
There are some universal truths that exist in this world: It is unrealistic to train a majority of the population in Data Science. Data Science cannot be “dumbed down” too far without losing its intrinsic analytical value. And most importantly: Trying to fundamentally change how a person works has a lower chance of success than learning ancient Latin overnight – from a book - in the dark.
From walking the show floor at Gartner, it’s clear that momentum is shifting from:
“Use Hadoop, connect via Spark, and fire up analytic solution X, using predictive technology Y, and deploy (magically) in your environment”
“Here’s an application that helps the business analyst understand their world in an environment they are used to and either automates or abstracts the nitty gritty out – with an escape hatch so that more proficient users and Data Scientists don’t feel boxed in”.
(The second one is way better right?)
The net effect is that “predictive technologies” become more embeddable, there is more logic at the application layer, and the demands on the Data Scientist are reduced. It means that cool technology like “R”, “InfiniteInsight”, and “APL” become more embeddable and consumable in *other* solutions rather than being the basis for a standalone tool. The solutions that invisibly embed predictive technologies into their applications will have a distinct edge, and it is all of us non-Data Scientists that benefit.
My View On How SAP Is Positioned
my take on SAP’s position?
In some areas we are light years ahead – the KXEN libraries required to add automated predictive analysis to any application are around 15 MB and are already embedded in many applications inside and outside SAP. We recently announced the Automated Predictive Library (APL) for SAP HANA that brings those same capabilities natively inside HANA. In Predictive Analytics 2.0, you can automatically create predictive models and export them to database vendor-specific SQL, C++ or Java code, or even an “awk” script if that’s your thing. (Try SAP PA 2.0 HERE)
There are other areas that we’re still working on but will put us ahead when we release our next generation “SAP Predictive Analytics 3.0” product. Automated model comparison, consumption and embedding of complex “R”-based models, and a new Fiori-inspired user experience that is specifically designed to meet the needs of data scientists while still being accessible by sophisticated business analysts are just a few things that we’re working on right now.
I’m pretty excited about the future of SAP Predictive Analytics because we've got patented, class leading technology for embedding into all of those applications that need to embed predictive while we will still be developing, improving, and outpacing with our data scientist and data analyst product.
One look at the Gartner BI Summit and it is obvious that as the “Big Data Hype” calms down a bit and more people start asking “Well, how can I *really* use Big Data in real life?”, the true darlings of the tech world may not be those who can store the most data, but those who can bring the best Big Data insights to the most people.
For SAP and users of SAP Predictive Analytics, the future does indeed look bright.
Disclaimer: This article is expressing my own personal views and may not reflect the views of SAP, its products, its partners, or its competitors (but I'm sure all of them would agree the future is bright too).
Market Basket Analysis (MBA) is interesting as a standalone activity, but where is gets more compelling is when you can really find trends, identify unknown relationships, and discover new business opportunities. Using MBA for both Cross-Sell and Up-Sell is very common and we are all familiar with Amazon who do this very well at the bottom of almost every page. MBA can be used to optimise store layouts, and website designs so that your customers can easily find those items that are frequently bought together. On your website having multiple layouts should be easy, having these change automatically depending on day, time, etc should also be easy. This can be done on a either temporary or permanently basis, perhaps you discover a totally different set of baskets being sold Monday to Thursday as opposed to the weekend period, to maximise this opportunity warrants a different user experience. MBA can also be used to identify Driver Items, or PreRules as we call it, which is the initial item that causes the subsequent items to be sold in the same basket. Another use of MBA is to help classify the basket or shopping trip as a whole, what was the reason that person went shopping? It still may not be black and white but MBA can help get some insight with this classification process.
I've already shown how to doBasket Analysis with SAP Predictive Analysis and SAP HANA - Part 1 and how can easy you use Apriori or Association Rules is to perform Association Analysis using SAP Predictive Analytics (PA 2.0), and with SAP HANA. Visualising the results is also quick and easy using Lumira or Expert Analytics as shown here Basket Analysis with SAP Predictive Analysis and SAP HANA - Part 2: Visualisation of Results. By doing so we can transform the time that it takes to perform this from hours to a few seconds or minutes if we want to look across a larger data set.
One of the advantages to basket analysis is that it is so easy to perform, you just require 2 columns of data, so some of the usual data hurdles are removed. As there's only 2 input columns, the TRANSACTION and ITEM it really can be done by anyone.
One of this disadvantages to basket analysis is that is so easy, the algorithms typically do not support additional fields, so it can be more challenging to capitalise on your findings. For example the output data does not show you which underlying transactions were used to generate a particular rule so you can't easily attribute revenue, margin, discount, profit, promotional amount, time, location to the rules that have been generated. This does not mean it can't be done, it just means that you don't get it "for free" with the analysis.
There's 3 further techniques that I've incorporated into the Basket Analysis process.
1. Filtering the input data set for targeted analysis, perhaps you want to look at just one or two product categories, or you want to look only at weekend sales, a promotion or a time of day. This is the easiest to achieve, some of these selections can be easily applied, others may take a small amount of data modelling. By filtering the dataset we therefore reduce the data volume and increase the speed of executing analysis and further reduce the time it takes to just a few seconds.
2. Apply simple data modelling to the output data set. While the results of basket analysis are only truly valid at the level they are performed at, for example if you were analysing SKUs the rules created would also hold true with the parent members of the Product hierarchy, but the support, confidence and lift values could only be used as an indication as to the values of the underlying base products. The easiest way to build an interesting model with the output dataset is to either use the PreRule or use Apriori Lite, which restricts the PostRule to a single item.
3. Manipulating the input data set, this is also easy to do, and is perhaps the most powerful, but also the most computationally expensive, but as we can run basket analysis end to end in just 20 seconds or 180 seconds for almost 100 million records, this is not such a problem anymore. For example if we wish to split the day into 5 bands, perhaps covering Morning, Lunchtime, Afternoon, Evening, Late Night, we can perform Basket Analysis across these. This can now do this in a single execution of the predictive process. Be aware having 5 time bands will take more processing than before. How about if we wanted to do this a a store level and we had 200+ stores, previously the time taken to do this would have been prohibitive, making this impossible, but by using the combination of SAP HANA and PA 2.0 this now easily achievable.
When we manipulate the input dataset what we can do is append the time period or store to the input data record, now we will retain this information throughout the analysis process. The input data now contains 3 pieces of information the Store, Item and Transaction. We can then use output dates within a HANA Calculation View to join the store with the store hierarchy and we're able to slice and dice the data looking for the best/worst performing stores. We can look at regional variations, compare the different store types and identify those that respond best to campaigns and those that require individual treatment due to the baskets being sold. Thanks go to Ran Bittmann for advising me here.
The agility of SAP HANA is one of the key differentiators here. All 3 of the above enhancements were achieved quickly, easily and graphically with HANA Modelling. Because the HANA models are purely views they don't store data so require no further storage and no additional steps and no batch jobs to be executed when you want to re-run the Basket Analysis.
First, another poll:
The poll above shows that the biggest barrier to adopting Predictive Analytics (per 43%) is cost.
SAP's Charles Gadalla provided this part of the session.
Predictive Analytics 2.0 combines both Predictive Analysis 1.x and SAP InfiniteInsight as shown above
Predictive Analytics 2.0 offers BW offline support (including the BEx Query), a recommendation engine in one component, APL for HANA SPS9 – sister library to the PAL library – on AFL of HANA
Charles said to look for wide datasets – lots of fields, variables
It uses "Smart BI" with the "light bulb" in Lumira which comes from KXEN
It supports Big data
In the green boxes, under future direction, there will be a unified UI with one seamless experience, supporting massive analytics and huge datasets
APL offer auto algorithms to optimize
Skyrock is aompany in France with 2x increase in acceptance rate using predictions and personalized recommendations
Q: What are some key use cases?
A: Churn, loyalty, freemium to premium
Q: Roadmap talked about Hadoop – what is integration with Hadoop?
A: Work closely with distributions for Hadoop – connect to Hadoop, Hive, Spark interface
Q: What is roadmap with integration of R?
A: R is already integrated
Q: What training is available for business analysts to make the right choice
A: tutorials, official training program
Another poll appeared:
Yet another poll:
The business analyst will build models; the above adds up to more than 100% because you could select multiple answers.
There was a demo of predictive analytics using hybris. Embedding the prediction analytics inside your operational applications is interesting.
Meet Charles at ASUG Annual Conference in this session: BI109 Predictive Analytics 2.0: Roadmap, what's new and what's next
Also some upcoming ASUG Predictive Analytics webcasts are listed below:
These are my notes from today's call.
First, a poll:
53% of attendees on today's webcast are not using SAP Predictive Analytics.
The first speaker was Sven Bauszus, SAP. He said nothing is stronger than an idea whose time has come, and it was "time for a predictive analytics solution" due to simplicity, ease of use, productivity. Why now? He mentioned the 4 V’s of big data, and competition, insights, predict and act in time. He also said it was “not just for statistical experts”.
The figure above shows how Analytics needs to evolve, with requirements for predict and act
Why did it happen, while will it happen
How can we make it happen?
Predictive Analytics take a step further by taking action
Descriptive is part of predictive analytics
"What is the point of doing predictive analytics if you don't integrate into your operations?" So prescriptive is needed too.
Big data goes main stream
More companies leverage data asset
68% of those who use advanced analytics have a competitive advantage and they reduce operational risk
Above shows the use cases for Predictive Analytics
The SAP speaker said this is not a TCO discussion but a quantifiable return on investment, to help increase in accepting customer offers
Retailer in 1K stores was able to improve sales forecasting and exploit hidden revenue potential, slash inventory costs; builds 500 predictive models a month – models built for shelf planning, store clustering, sales and purchasing planning – 82% accuracy in forecasting, with 10 times more categories than before
The “need for speed” was mentioned with the "Business potential is huge"
Predictive maintenance helps predict when failure occurs, tasks for monitoring for future failure so maintenance occurs before failure occurs to prevent unplanned maintenance
The first speaker summarized the above with "democratizing predictive analytics" and support real time
Q: We have many predictive in market, what is so unique about predictive analytics?
A: Combine predictive automation, full support of in memory database scoring, reduces need for data movement
Predictive platform has scoring engine on the back end
Easy to use
Focus on rapid deployment
Q: I am existing BI customer, how can I leverage Predictive & skills on my team?
A: Technology is seamlessly embedded with portfolio
Q: What advantages of Predictive Analytics using SAP HANA
A: In-memory capabilities of HANA; take advantage of power speed and real time of HANA
Predictive Analytics does not require SAP HANA
Part 2 will post soon.
BI pre-conference session at ASUG Annual conference
Monday, May 4. (extra registration fees apply).
Featuring Hands-on SAP BusinessObjects BI 4.1 w/ SAP NetWeaver BW Powered by SAP HANA – Deep Dive
See details here: http://bit.ly/ASUGPreConBI
Focus on Analysis Office, Lumira, and Design Studio. You get to work with these for 7 hours! Full day BI workshop. Limited to 30 people. One person per machine (no sharing).
Also some upcoming ASUG Predictive Analytics webcasts are listed below:
The wait is over! On Feb 27th 2015, we released the first HANA cloud image of SAP Predictive Analytics. Now SAP Predictive Analytics scenarios can be simulated and run on the AWS cloud in the context of HANA. This HANA Cloud image is hosted on AWS which depicts the HANA models and predictive models with data visualization based on a few customer centric scenarios.
Let us get into a quick background of Predictive Analytics RDS and how we arrived at the creation of this image. An RDS for Predictive Analytics has been inspired by the strategic thoughts and initiatives to show case how predictive analytics tools could be realized for customer centric use cases. As part of its inception in 2013, the predictive analytics RDS has modeled a lot of customer scenarios ranging from different industries and LoBs showcasing the different approaches of predictive modeling using Predictive Analysis (now expert analytics in PA 2.0), InfiniteInsight (now automated analytics in PA 2.0), SQL scripting in HANA to utilize native Predictive Analysis Library (PAL).
By the current v4 release of the Predictive Analytics RDS on Feb 23rd 2015, about 30 customer scenarios around 5 industries and 3 LoBs are available. These different scenarios show case the end-to-end story of data gathering from enterprise data sets, data preparation in HANA and modeling the generic objects, doing predictive modeling on key KPIs utilizing one of the approaches(predictive analysis or infiniteinsight or HANA scripting) and finally visualizing the data using SAP BusinessObjects Explorer or SAP Lumira (SAP Predictive Analysis) or SAP UI5.
Scenarios available in the HANA Cloud Image on AWS:
As part of the Cloud image(that is hosted on AWS), we have made a few scenarios from the RDS already pre-built. This helps the customers to get a complete end-to-end story in the context of HANA. The scenarios that were picked up for the very first version of this cloud image are as follows:
You would be able to experience the above scenarios in the context of HANA with enterprise data set that is already available on cloud image.
We have show cased different approaches of doing predictive modeling using the SAP Predictive toolset.
Architecture of the Cloud Image:
The pre-built HANA cloud image is available(in the SAP store) for a trial period of 15 days. During this time, there is no additional cost to access this image as long as you have an AWS account. The cloud image is hosted on AWS and hence you will need to pay a nominal fee towards AWS but the access to HANA cloud image is available for trial and evaluation purposes in the context of customer centric scenarios.
In the upcoming weeks, the HANA cloud image shall be updated with many more scenarios from the RDS story as well make it available on the latest Predictive Analytics tools. Please stay tuned for more information in this regard. The current HANA cloud image explains and showcases the concept behind using the data from HANA, doing the predictive modeling using all the different approaches of Predictive Analysis or InfiniteInsight or HANA scripting. The concepts remain the same but we shall be upgrading to the latest versions of the tools. The current concept or the best practices image available as an enterprise HANA cloud image is upward compatible.
Please click here to access the HANA Enterprise Cloud image for Predictive Analytics on AWS in the SAP Store.