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 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.
Tijdens dit evenement werden een aantal inspirerende praktijkvoorbeelden van innovatieve AI-projecten gepresenteerd. Daarnaast werden handvatten aangereikt om AI-projecten [...]
SAS werkt samen met NVIDIA op het gebied van deep learning en computer vision. Het doel is om klanten te helpen met het toepassen van Artificial Intelligence (AI) bi [...]
SAS investeert de komende drie jaar $1 miljard in AI door middel van software-innovatie, onderwijs, aanbod van expert services en meer. De investering betreft nieuwe [...]
Kunstmatige intelligentie (AI) biedt veel kansen, mogelijkheden en voordelen voor innovatie. Wat is de impact van deze nieuwe privacywetgeving op AI-projecten?
Artificiële Intelligentie (AI) en analytics worden door de politiek gebruikt om hun boodschap op een gerichte manier bij het juiste kiespubliek te krijgen.
72 procent erkent de voordelen van analytics, maar bij slechts 39 procent is het de kern van hun bedrijfsstrategie