Path analysis with SAS Visual Analytics

Introduction

Understanding the behavior of your customers is key to improving and maintaining revenue streams. It is a an important part when crafting successful marketing campaigns. Using SAS Visual Analytics you can analyze, explore and visualize user behavior, click paths and other event-based scenarios. Monitoring the customer journey by visualizing all touchpoints in your organisation will help you to identify gaps and improve the overal customer experience. Flow visualizations will help you to best understand hotspots, highlight common trends and find insights in individual user or aggregated paths.

In path analysis you are typically trying to determine a sequence of events in a particular time window. For example you pay attention to paths more frequently used than others in order to understand what path prospects take before they become new customers. Path analysis works best with linear event streams such as customer life cycle (1. prospect, 2. trial subscription, 3. customer, 4. product upgrade, etc.) but is also commonly used for web usage analysis. As a data scientist you may look for optimal paths to compare with paths customers have actual taken. This often reveals interesting insight and opportunities for revenue improvements.
Read More »

Post a Comment

Can a humanities major learn to program in SAS?

Before I started my internship with SAS, my only experience with data or analysis came from an “Introduction to Statistics” course I took freshman year to satisfy my math requirement. If I’d known then that statistics and knowing SAS programming would be the #1 skill for a bigger paycheck, or an “unemployment immunity card,” I would’ve taken notice!

As it turns out, I chose to study Spanish and intern here at SAS in External Communications. But I always wondered if someone like me, who really had no programming experience, could ever learn SAS. I got my chance this past summer when all the SAS interns were invited to a half-day training session with SAS® University Edition, the new free software from SAS for noncommercial use.

Sitting next to the experienced CompSci interns, I wondered if I’d be able to hack it. Then a marvelous thing happened: I actually wrote my first SAS program.

Read More »

Post a Comment

What is the most valued position in football?

After the 2014 FIFA World Cup, one thing’s clear: here at SAS, we love football (soccer in the US!). To wrap up the popular 2014 World Cup data visualization series on the SAS Visual Analytics Community, we created a presentation that’s chocked-full of interesting insights. From the trillions of pieces of World Cup data, we selected the best and dropped them into SAS Visual Analytics to answer interesting questions.

Check out this sneak peek: We took each of the positions’ average market value and plotted them on the soccer field in a traditional formation. The circle size indicates the market value of the positions, with the larger circles indicating a higher market value.

Click to enlarge

We even took it a step further and included a graph with the positions plotted in Germany’s winning formation:  Read More »

Post a Comment

How are Hadoop deployments like snowflakes?

Because every single Hadoop deployment, like the structure of a snowflake, is different. For the open source big data framework, there are different distributions from various Hadoop vendors and all implementations are, or should be, tailored for that specific organization’s needs.

And given this infinite variety of Hadoop foundations, the analytics deployed to pull value from the data must embody three critical characteristics:

  1. The analytics must be accurate. It’s tough to make good business decisions if you aren't sure if the analytic results are valid.
  2. The analytics must be scalable, after all this is big data and you might not know how much data you’ll use a few years down the road.
  3. The analytics must support governance so that large amounts of data don’t have to be unnecessarily moved or replicated.

SAS, with its “laser focus” on analytics, big data and Hadoop, stands out for its dedication to the three critical characteristics of accuracy, scalability and data governance.

To get a quick overview of how SAS supports these vital customer requirements, take a look at the below video produced by the same folks who made the intro to Hadoop video I recently included as part of a post "Has the Hadoop hype left you confused?"

Read More »

Post a Comment

One study that will change the way you see social work

DSC_2005_2On Facebook the other day a friend “liked” one of her friend’s posts, so it appeared in my news feed. I opened the link, read the article and started crying.

You would have too. It was an article by a former social worker in Durham County, N.C. on what it was like to work in child protective services (CPS). Was. He quit years ago. He was burned out, frustrated over lack of resources, etc. He wondered if the work he did mattered.

Here’s an excerpt: Read More »

Post a Comment

The sights and sounds of IoT data streams

The Amazon River starts a small glacial stream, pictured at right, on a mountain called Nevado Mismi in the Peruvian Source_of_amazonAndes. This, and many other small streams, lead to over 1,000 named tributaries of the largest drainage basin in the world -- and the greatest diversity of life on our planet.  Like the Internet of Things (IoT), the Amazon basin is a gigantic network of streams. The Amazon streams push water forward towards the Atlantic, while the IoT data streams are pushing industries to new levels of efficiency and effectiveness.

With enough trekking equipment and expertise, you can visit many of the streams in the Amazon basin. If you have video, audio and transmission equipment, you can broadcast the sights and sound in real-time across the Internet -- from the rush of snow melt over rock in the Andes to a bubbling piranha attack half a continent away.

Read More »

Post a Comment

Analytics is an enhanced oil recovery process

You may have heard the phase that big data is the new oil.   Well (pun intended), if that is the case, then analytics should be thought of as the fracking technique used on data to improve the value you get from this new oil.  Fracking is actually just one of many enhanced oil recovery (EOR) techniques; there are other forms like CO2 injection. But fracking is probably the most widely known EOR outside of the oil and gas industry.

EOR is any process, or combination of processes, that may be  applied to economically increase the cumulative volume of oil that is recovered from the reservoir at an accelerated rate.   EOR is also sometimes referred to as improved oil recovery (IOR).  IOR processes target mobile oil or gas and EOR processes are concerned with trapped or immobile oil or gas within a well.   Basically, IOR and EOR are about getting more oil or gas out of a well, economically (at a profit).  If it costs you $100 to get a barrel of oil out of the ground, but you can only sell it for $75, no one would do it.

Read More »

Post a Comment

Retailers want insights, not data

8558922303_8bfec65ac2_z

What insights can be gained from the massive amounts of data that allow us to make decisions that deliver the best results? Data vs. information is an ongoing battle. Many people look for more data to make confident decisions. However, what most people seek is insight.

Retailers always have tracked what was sold, where it was sold and, in most cases, who it was sold to.  Since the advent of the bar code and modern POS and ERP Systems, more data has been acquired and stored in data warehouses. Now, retailers are adding third-party data, such as census information, to the mix. Read More »

Post a Comment

Why we need digital banks

Digital Bank Chris Skinner

We often hear from retail bank customers that they aren't satisfied with the revenue captured through digital channels. It was therefore with great interest that I embarked on the mission to understand Chris Skinner’s book Digital Bank.

Why we need digital banks

The book starts by painting the landscape of the digital natives. We need digital banks because there is this generation called Generation Z, generation D, iPops, or whatever you like to call them, that has grown up with the Internet. This is the generation that does not think about the Internet – it’s just there. They don’t think about branches or call centers. They see a world in which online, mobile, and other digital channels are seamlessly integrated into their world. They just think of these things as life.

The problem? While the world becomes populated by digital natives, retail banks are run by digital aliens, who do not get the digital life.

Read More »

Post a Comment

Has the Hadoop hype left you confused?

Perhaps you're a big data expert who is fluent in Pig, Hive, MapR and all the technologies associated with the open source big data framework. Or maybe your role hasn't yet been touched by the increasingly popular Hadoop system. It's certainly worth a few minutes of your time (or perhaps much more depending on your job) to have an unsderstanding of this cost-effective system that employs commodity servers to store huge amounts of data.

Allied Market Research says the Hadoop market was $2 billion in 2013 and is expected to show a compound annual growth rate of 58 percent between 2013 and 2020 when annual Hadoop spending will top $50 billion globally--about the same as the current market capitalization of Time Warner or General Motors.

So, if your knowledge of Hadoop ends at "something to do with big data," check out this three-minute video that provides an overview of this promising and emerging technology.

The Hadoop Ecosystem explained

Read More »

Post a Comment