Geek blog series - part 2
22 juli 2019 [03:48], 1816 views
Door Redactie

Geek blog series - part 2

In this ‘Geek blog series’ these ‘Geeks’ share their expertise and insights on the latest AI and Analytics topics. Below you will find the second part of this series.

Intelligent Decisioning with open source code in SAS

By Edwin van Unen

Coding is hot again. Lots of developers prefer to use R or Python to develop machine learning models. How can you operationalize this open source code into a business environment? Because that’s what you need to do when you want to benefit from the modeling efforts. According to recent research by McKinsey and Gartner many organizations fail to bring these models into production and scale up their Analytics initiatives.

It’s quite easy to operationalize Open Source models into a SAS business environment. To show you how it works, I wrote some code in Python to decide whether a person is a geek or not. The next step is to export the model file for later use. I could have used the classical pmml interface, but in this case I use pickle. That way we can use Python score code on a SAS platform. To do so, we create a decision in SAS and import the native Python score code. Step 3 is to enhance the decision logic by adding business rules, an external webcall or a database query. And finally, we operationalize our decision by publishing the decision as a REST-API webservice.

In this example we use Python code, but you can use other coding languages like R as well to benefit from SAS. The key thing is that you can use open source code in a governed decision engine like SAS is. This way you create the best of both worlds.

 

Create your own visualization in SAS Visual Analytics

By Rik de Ruiter

Data visualization is an essential component when exploring large amounts of data. Visualizing data helps to identify patterns, trends and outliers, but also to get your message across. Popular charts are line and bar charts, but in some cases you might need more advanced visualizations. Wouldn’t it be nice if you could import third party visualizations in SAS Visual Analytics? Or even better, custom make your own visualization and import it?

Because it is so useful to make custom visualizations, we made it easy to integrate. Just make your visualization, integrate it in SAS Visual Analytics and embed it in a report. You can import visuals from Autodesk Forge Viewer, Google Calendar, D3.js, and many more formats. On our GitHub website, we tell you exactly how it works.

Let’s take for example a report for a real estate agent that shows the number and type of houses that are for sale. One approach would be to copy in a table with the numbers of small apartments, large apartments, terraced houses, semi-detached and fully detached houses. Or perhaps a bar chart. But why not make an illustration of those different types of houses in a street? Or make any other visualization you like!

The advantage of integrating visualizations in SAS VA is that it the visuals can be made dynamic: they automatically update as soon as the numbers change. This way, you don’t just use the visualization in a static report, but they stay actual. You can also add different layers with additional stats (such as the average price of the different types of houses in a city, or the types of houses in a certain ZIP code). This way you can re-use your visualization over and over again.

Want to create your own visualization after reading this blog post? Get inspired and get started!

Learn more

Want to learn more? Hear our stories during the Talk of the Geeks at the World Summit AI from Oct. 10 in Zaandam. The number of seats is limited! To secure your seat, please let us know in advance. If you can’t make it from Oct 10, join us at Analytics Experience from Oct. 21-23 in Milan.

Read the Geek blog series - Part 3

 

Reacties

Wapen je tegen betalingsfraude door een sterkere authenticatie
20 november 2019 [11:01], 126 views

Wapen je tegen betalingsfraude door een sterkere authenticatie

Het gebruik van innovatieve technologieën zoals kunstmatige intelligentie om fraude te bestrijden is een haalbare en effectieve oplossing.

 

Lees meer  

E-health hub houdt zorg betaalbaar en voorkomt eenzaamheid
13 november 2019 [09:00], 190 views

E-health hub houdt zorg betaalbaar en voorkomt eenzaamheid

E-health hub houdt zorg betaalbaar en voorkomt eenzaamheid.

 

Lees meer  

Inzet open source modellen voor slimmere en snellere beslissingen
12 november 2019 [03:11], 212 views

Inzet open source modellen voor slimmere en snellere beslissingen

Met de introductie van SAS Open Model Manager helpt SAS organisaties bij het operationaliseren van open source modellen voor slimmere, snellere zakelijke beslissingen.

 

Lees meer  

SaasNow nu ook beschikbaar via public cloud
22 oktober 2019 [02:32], 775 views

SaasNow nu ook beschikbaar via public cloud

SAS partner Notilyze, leverancier van analytics as a service, maakt SaasNow nu ook beschikbaar via de public cloud. 

 

Lees meer  

Meer rendement uit analytics-investering met ModelOps
21 oktober 2019 [10:46], 899 views

Meer rendement uit analytics-investering met ModelOps

Volgens IDC slaagt slechts 35% van organisaties erin om analytische modellen volledig in productie te nemen. Dit resulteert in onnodige inspanningen en verspilling van gel [...]

 

Lees meer  

KNVB en SAS maken één-tweetje om voetbaldoelgroepen te binden
23 september 2019 [06:33], 1731 views

KNVB en SAS maken één-tweetje om voetbaldoelgroepen te binden

SAS gaat met haar Customer Intelligence-oplossingen de KNVB en dochterorganisatie Voetbalmedia helpen om de miljoenen voetballiefhebbers nog persoonlijker te b [...]

 

Lees meer  

Kwaliteit voorspellen met de Smart Industry Assistant
30 augustus 2019 [11:27], 2175 views

Kwaliteit voorspellen met de Smart Industry Assistant

Bright Cape heeft de Smart Industry Assistant (SIA) ontwikkeld om de hoeveelheid productieafval te reduceren en de winstgevendheid te verhogen. 

 

Lees meer  

Geek blog series - part 3
29 juli 2019 [04:07], 1421 views

Geek blog series - part 3

In this ‘Geek blog series’ these Geeks share their expertise and insights on the latest AI and Analytics topics. Read the third part of this series.

 

Lees meer  

Geek blog series - part 2
22 juli 2019 [03:48], 1817 views

Geek blog series - part 2

In this ‘Geek blog series’ these ‘Geeks’ share their expertise and insights on the latest AI and Analytics topics. Read now the blogs of the second part of this series.

 

Lees meer  

Geek blog series - part 1
15 juli 2019 [03:17], 1450 views

Geek blog series - part 1

 In this ‘Geek blog series’ these ‘Geeks’ share their expertise and insights. A must-read for everyone who likes to learn more about data scien [...]

 

Lees meer