Correlations, forecasts, and making sense of it all with visualization

"Correlation does not imply causation.” Does that bring back memories from your college statistics class? If you cringe when you hear those words, don’t worry. This phrase is still relevant today, but is now more approachable and easier to understand.

Here at SAS, we use SAS® Visual Analytics to make sense of it. We can use a correlation matrix to explore relationships between variables, and forecasting to figure out which variables explain a response or target variable.

Before we take a look at that, let’s first dig into how forecasting works in SAS Visual Analytics. Although the business user may not necessarily know this, SAS Visual Analytics runs both Exponential Smoothing Models (ESM) and Auto Regressive Integrated Moving Average models – ARIMA, for short.

If those sound scary, all you really have to know is that they predict future data as a function of the historical data values. Time series models aren’t the same as simply extending a linear trend. Recent data points are weighed more heavily when calculating the future data points. Makes sense, right?

Read More »

Post a Comment

The real deal in fraud and financial crimes

Financial institutions evaluating fraud management solutions face a crowded vendor landscape. Dozens of vendors claim to offer various pieces of the puzzle. With so many choices available, how will you sort through the marketing rhetoric to find the best fit for your organization?

You could assemble a team of analysts and advisors from the risk management and financial services industries to serve as independent advisors. Give them several months to gather and review vendor submission forms, administer user surveys, interview customers and users of each solution, conduct briefings with vendors, attend conferences, host roundtable discussions, collaborate with industry consultants, and review academic and regulatory studies.

You could, or you could be thankful that research firms have already done it. Read More »

Post a Comment

Using SAS and open source: a hybrid approach

The automotive industry will face a huge challenge for several years. With the Paris Agreement made during the United Nations conference on climate change last year, world leaders agreed to hold the increase in average temperature to well below 2°C by placing restrictions on carbon emissions.

How can automakers design a new engine using less fossil energy, reducing carbon emission and yet still offering the same level of performance, autonomy and practicality as the petrol engine?

electriccarA few years ago, the immediate answer from automakers was to shift to electric vehicles with no carbon emissions. However, the performance of electric cars hasn’t yet been equal, and to date the market promise hasn’t yet been fulfilled – relatively few electric cars have been sold.

In the world of analytics software, we may have a similar situation. The digitization of business in a context of sluggish growth along with the rise of mobile activity, and the Internet of things, to name a few, will increase the demand for scalable, effective and low cost analytics.

Read More »

Post a Comment

Lifelong learning and analytics

Doris002b

Doris (Simpson) Sadovy, a teenager in Atlantic City, half a dozen years before me

I sometimes feel bad about being born. Not so much the actual event, mind you, just the timing. I was born during what should have been my mother’s last year of college.

At many colleges in those days, when a woman got married, she was forced to move out of the daytime program and into night school. You know what a bad influence those married women can be. And if she got pregnant?  Well, that was evidently just too much for the delicate sensibilities of college administrators of the time.

My mom and dad got married in between her junior and senior years of college. I was born in March the following spring. Although she wasn’t showing when the fall semester started, she knew she couldn’t hide it until Christmas.

Since this was a teacher’s college, and she’d be practice teaching in real schools, she risked being arrested for contributing to the delinquency of a minor if she didn’t fess up right from the start. So, because of me, she had to drop out just two semesters short of her degree.

I was trouble before I was even born. Read More »

Post a Comment

And the weather yesterday was …

200362007And the weather yesterday was a sunny 18oC with warm spells in the south and showers in the north. This is similar to the pattern we saw last Thursday.”

Imagine if the weather forecast only restated what happened in the past -- would we bother waiting until the end of the news each night to watch? Compare this to organisations -- how much of an organisation’s business intelligence is a historic view of what happened? And when organisations do use forecasts, they’re often a rehash of previous numbers with an aspirational target added to improve sales performance.

In the UK, weather forecasting benefits industry to the tune of over £1bn per annum, for an annual spend of £120m (see Public Weather Service Value for Money Review, March 2015 for details). It’s the predictive nature of the weather forecast that makes it so valuable to so many sectors of industry, from aviation to civil planners to retailers.

Read More »

Post a Comment

New study confirms: SAS most valuable career skill

young man at laptop in libraryIf you're looking for higher pay and better opportunities, what career skills should you seek to acquire? You might think leadership or communication skills would top the list, but a recent study says otherwise.

According to a massive study from MONEY and Payscale.com, SAS Analytics skills are the most valuable skills to have in today's job market.

The study “analyzed 54 million employee profiles, across 350 industries, with 15,000 job titles—from entry-level workers to top execs."

Read More »

Post a Comment

Gearing up for pharma’s big change

sas.com_MedResearch_84A4033The pharmaceutical industry will undergo significant changes this summer. A set of standards for the identification of medicinal products (IDMP) from the European Medicines Agency (EMA) will take effect in July, requiring the whole industry to apply the terminologies released by EMA. The changes have raised many concerns regarding how data is managed across the industry.

While pharmaceutical companies recognise the urgent need to take action to meet the EMA deadline, the real challenge is applying a speedy, mechanised process to limit resources needed to achieve compliance. Companies face the challenge of organising huge amounts of unstructured data, which resides in silos across the business, with no formalised cataloguing method. Read More »

Post a Comment

Data, data everywhere…

137957211It was John Allen Paulos who said, “Data, data everywhere, but not a thought to think.” That rings true more than ever before. Companies are struggling with the deluge of data coming at them from multiple channels. But traditional data channels are just the beginning. Companies also are facing an unprecedented data flood from the Internet of Things (IoT). Data everywhere and not a thought to think, indeed.

Technology and business professionals alike are buzzing about the IoT. In the consumer packaged goods (CPG) industry, the IoT conversation involves retail point-of-sale data, syndicated scanner data from sources like Nielsen, consumer data from loyalty programs and product data from internal sources.

As more smart devices communicate within CPG ecosystems, the data pool – or demand signal repository (DSR) as it’s known in CPG circles - grows deeper and murkier. But analytics applied to the DSR can bring much-needed clarity and insight so CPG manufacturers can help retailers and consumers remain satisfied.

With analytics, the problem presented by an ever-expanding DSR can quickly be tamed. Analytics help a CPG company understand what happened, why it happened and what may happen in the future. Combining this improved insight with promotional plans and similar campaigns help a CPG manufacturer shape demand by providing incentives that guide consumers throughout their experience with a brand.

Learn more about how analytics turns demand signals into insights for meaningful action through these two discussions:

Post a Comment

An IoT-enabled fun weekend

The buzz about the Internet of Things (IoT) combined with the insights derived from analytics afun weekend tripppears to be hotter than ever.  What's interesting to me is how many people go about their lives without knowing what the IoT is and how they're already benefitting from it (or how their jobs may soon be disrupted by it).

I was fortunate enough to participate in the Dick's Sporting Goods Pittsburgh Marathon on May 1 (actually the 1/2 marathon) because my 15 year-old daughter was running it to raise money for charity.

The IoT is all over an event like this -- from the advertising and registration to communication and company sponsorships -- not to mention all the runner's bibs with sensors attached. It wasn't long ago that runners in an event like this would've had to wait hours, or even days, before getting their results. But thanks to wonders of IoT and some basic math, runners' family, friends and fans can get real-time updates of the race as it unfolds.

Wearable devices (such as Fitbits) and smartphones, are more personal, everyday examples of IoT in action which most of us take for granted at this point. The main benefits I see in everyday IoT is that it makes people's lives easier.

For example, Uber. I'm a bit of a laggard in adopting Uber, but until this weekend I hadn't had a reason to try it. That changed when I had my hotel call a cab, and it took so long to show up that I downloaded the Uber app, set up my account, and had a pickup – all within five minutes. Not to mention the car was nicer and the rate less expensive. Lesson learned!

Successful uses of the IoT (like Uber, fitness watches, smartphones) happen and are adopted naturally -- you don't have to convince someone to try it. It gets used because it makes sense or makes life easier.

My final observation about my weekend and the IoT is that the foundation rests in energy.

Everything I did this weekend relied on easy-to-use and relatively inexpensive energy, from the car I drove to the airport, the fuel in the airplane to fly to Pittsburgh, the electricity powering the city and  the devices we used to take pictures and share our race experience with others -- it all related to the IoT.

And it all related, one way or another, on the electric grid. Smart grid is a term within the utility industry to address all the advances of adding sensors to and upgrading the electric grid to meet future energy demands -- yet another use of the IoT to make our lives better.

As you can see from my post I think our existing grid is pretty "smart" or at least enables a whole lot of "smart" IoT services already. IoT is a reality today, and it's just going to continue to grow and become more important in the future. Click the following links to learn more about IoT and analytics including who's using it and how it works.

Post a Comment

Machine Learning: An invited guest to the IoT party?

Research indicates that IoT and Machine Learning are more valuable to utilities when used in combination but there are hurdles to overcome first.

Machine learning and IoT will enable utilities to better realize the next generation of the power grid: a distributed system with power flows among millions of things like distributed energy resources (DERs), microgrids and in-home devices. All of which will help utilities deliver clean reliable energy and greater customer choice.

Utility respondents to new research from SAS and Zpryme, The Autonomous Grid, indicated that IoT and machine learning were more than market hype. These technologies are already delivering actionable results, say respondents. However, when we asked about the benefits of investing in IoT and machine learning, we received very different responses across those two technologies.

The top benefits associated with IoT are more likely to be customer-facing, such as customer service and energy efficiency, whereas the benefits named for machine learning are more grid-oriented, including areas such as service restoration, increased grid visibility/control and cybersecurity (Figure 1,2 Benefits).

ML_top5benefits    IoT_top5benefits

Read More »

Post a Comment