5 analytic resolutions for oil and gas professionals

115780102There’s a lot of hand-wringing in the oil industry these days. Prices are down, supply and demand are out of balance, companies are merging, and jobs may seem insecure. In uncertain times, individuals can get distracted from professional goals. So, it is in this spirit that I offer 5 analytic resolutions for oil and gas professionals to keep us all focused for the new year.

While these ideas won’t make the oil price rebound, if leaner times are ahead, a little analytical know-how may translate to job security. With a little time invested in the resources below, you can deliver analytical value and be equipped with knowledge of leading big data analytic technologies.

  1. Read Chapter 1 of “Harness Oil and Gas Big Data with Analytics” by Keith Holdaway. Just released this summer, the book “takes the idea of analytics work to a new level[1].” If the 30-page excerpt whets your appetite, the full book is available for purchase on Amazon or support.sas.com.
  2. Get up to speed on Hadoop, Deep Learning, and Data Virtualization. These technologies are critical for managing and deriving value from big data. Develop your knowledge in these areas for your next career step via the “Big Data Matters” webinar series.
  3. Visit WorldOil.com to watch the webinar Real-time Data Analytics for Critical Asset Performance with Paul Barnes, former Innovation Director at Aera, and Moray Laing and Mike Pool of SAS. Paul reveals his tips for bringing disparate groups together to drive change, then Moray and Mike introduce the art of the possible with streaming data analytics.
  4. Download “Don’t just visualize, Predict!” This oil and gas webinar will have your mind spinning with new ways to use your treasure trove of data to build predictive models. And if it looks too good to be true, try your hand at SAS Visual Analytics with these free downloads.
  5. Register for SAS Global Forum 2015 in Dallas, TX, April 26-29. Networking, training, and did I mention networking? Keith Holdaway (book author from tip #1) and other industry peers will be there presenting papers of use cases for advanced analytics. Register soon to get the best deal!

Did these suggestions spark some ideas for your own analytic resolutions? Please comment back to share them! Happy Holidays!

[1] Digital Energy Journal, Aug/Sept 2014

Post a Comment

A ‘Compelling Event’ for Cost Containment in Healthcare?

Historically healthcare has been most ‘self’ motivated to improve its ‘cost containment’ processes and methods.  This is evident from the significant gap that exists between the technology and process in finance versus healthcare.  Many healthcare organizations (either government or commercial) are not ‘profit’ oriented – take the Blues for example, they are all ‘non-profit’.

As we tend to see in a market economy, profit and competition breeds more effective profit and weeds out the less effective organizations.  Healthcare, as a whole, has not had nearly the same market driver as other industries – there are significant local and federal regulatory restrictions, massive barriers to entry, not to mention, that healthcare (for those that can afford it) is not really optional.  The result is that the healthcare industry has not moved even close to the pace of more competitive industries.

However, with all that said, it does appear that times are changing.

In the Netherlands, for example, following the introduction of a comprehensive reform package in 2006, universal medical coverage has been achieved, and not through a predominantly government-run system.  The Dutch government now requires that all health insurance organizations have a comprehensive cost containment solution for fraud, waste and abuse.  Which would indicate that many Dutch health organizations did not possess those type of solutions.

In the United States, the Affordable Care Act, has not only sought to introduce more competition, but also to encourage and push for better cost control.  Which is interesting, seeing the number of incidents that appear in the press associated to ‘mistakes’ made by Medicare, Medicaid, VA (Veterans Affairs), etc.  But any organization's efforts to improve is a good thing, and it would be wiser to encourage the effort than criticize past missteps.

So this brings us back to the primary question: Everyone realizes that the cost of healthcare is quickly out-pacing our ability to support it.  But is that sufficient motivation for ‘very’ profitable organizations and governments to adjust their practices? Does all of this regulation indicate or create a ‘compelling event’ for cost containment in healthcare?

Post a Comment

Farewell to 2014

Another great year is winding down. Ed and I are taking a little time off to enjoy the season and our family.

I thought I'd share the latest portrait of me. (You already knew I was gorgeous; now you also know what a good sport I am.)



So, from our house to yours... Season's Greetings. Fröhliche Weihnachten. Happy Holidays.

Post a Comment

Rudolf the red nosed Bayesian network?

As a follow-up to my previous Christmas blog post, Twas the night before big data,  I give you ...

Bayesian network, the directed acyclic graphical (DAG) model

( yeah, yeah, I know it doesn’t quite have the same ring as last year’s title, but you'll recognize the tune)


You know Linear and Logistic Regression and Decision Tree and Neural Network,
You know TwoStage and MBR and SVM and Partial Least Squares,
But do you recall?
The most famous predictive model of all?

Bayesian networks
Has a directed acyclic graphic model with nodes representing random variables
And if you ever saw it
You would even say the links between nodes represent conditional dependency of the random variables

All of the other models used to laugh and call him names
They never let poor Bayesian networks
Join in solving any decision games

Then one foggy Christmas Eve,
The data scientist came to a say,
Bayesian networks with your different types of Bayesian network structures
Won’t you solve this problem with random variables under uncertainty?

Then all the models loved him,
As they shouted out with glee,
Bayesian networks
You’ll go down in history!

All kidding aside, follow these links to learn more about Bayesian analysis in SAS or SAS High Performance Bayesian networks, which is part of SAS High Performance Data Mining.

Happy New Year!

Post a Comment

VirtualOil Portfolio benchmarking and forward month analysis

How’s your oil book looking? As prices continue their decline, the industry is making rapid adjustments, including project shut-ins and corporate restructurings. With WTI at $55 per barrel and the forward price five years out hitting $66, energy firms are scrambling to lock in value while bargain hunters start to sniff out attractively priced oil and gas investments.

As a simulation exercise, SAS has created a fictitious oil portfolio nicknamed VirtualOil, which readers can use as a generic benchmark against their physical oil commodity book’s performance. Each month, we reflect on what the visual analytics can tell us about the portfolio’s movement. This chart represents both Mark-to-Market and Value-at-Risk, at the barrel level, of the rolling five-year portfolio. This month, VirtualOil still shows a value of $12.29 per barrel over our $50 strike price, even though the portfolio is heavily weighted toward the first few months. The optionality becomes more valuable as we approach the strike price.

VirtualOil Five-Year Rolling Portfolio

VirtualOil Five-Year Rolling Portfolio


Read More »

Post a Comment

Is fraud really the biggest issue in health care cost?

200314219Health care fraud is often depicted as the great, five-headed hydra in Greek mythology. When you cut off one head, two more grow back.  But more to the point, health care fraud has been presented as one of the primary (if not the primary) causes of unnecessary healthcare spend.  However, just because fraud sounds bad and clearly is a problem, sometimes it is too easy to simply blame fraud with such broad strokes.

According to the World Health Report 2008, fraud and error account for roughly seven percent of the cost of claims in the United States (Adjusted to USD 2013, that comes out to $487 Billion annually). However, compare that with the analysis of PriceWaterhouseCoopers Health Research Institute 2007, which puts avoidable costs at 54 percent. Likewise, Berwick & Hackbarth, 2011, says that “waste in healthcare” is 47 percentof claims.  Waste takes on many forms, including:

  • Medical errors.
  • Extreme treatment variation.
  • Fragmented healthcare delivery.
  • Inefficient administration.

Read More »

Post a Comment

Vocabularies: Deciphering the language of business rules

A vocabulary example (click to enlarge)

Vocabularies example (click to enlarge)

Having met and discussed business rules with many customers over the last year, several questions arise in nearly every business rules conversation. Business rules can vary a lot by industry, but understanding the need for business rules in decision processes is common across every application. In all cases, quite a bit of time is spent focusing on vocabulary creation – something that is necessary before any business rules are written.

Vocabularies need to be recognizable to the business and must be organized in a way that reflects the natural logic of the business application. A data driven approach to selectively creating or deriving a vocabulary has been very useful and well received by customers in every industry.

So what is a vocabulary? In its most common form, a vocabulary is a "fundamental tool for communication and acquiring knowledge," according to Wikipedia. In the context of decision management, a vocabulary is a set of terms that are used to create business rules. It is part of the business rules language, along with operators that define how the terms are combined.

Read More »

Post a Comment

Sensors, those amazing (very) little things!

IoT - connected devicesThe first sensors appeared many decades ago, and have been around for quite some time in various forms, even though they’ve really only entered the popular vocabulary over the past few years thanks to the Internet of Things.

How do sensors work? A sensor detects events, or changes in quantities, and provides a corresponding output, generally as an electrical or optical signal.

Today, sensors are used in everyday objects such as touch-sensitive elevator buttons and lamps that dim or brighten by touching the base as well as a large number of other places most people are unaware of. For example, they are used in manufacturing, medicine, robotics, cars, airplanes and aerospace.

The largest challenges when it comes to sensors occur after measurements have been made. At that point, you have to decide: Where do I collect the data being generated and how can I use it, for example, to improve my operations by decreasing variability and improve quality?

Read More »

Post a Comment

Making 'management by walking around' more productive

two business people looking at ipadThe idea of "management by walking around" has been around for a while.  First brought to prominence in Tom Peters and Robert Waterman’s best-seller In Search of Excellence, the concept is that managers get out of their offices and meet employees in their work areas to get a sense of how things are going, listen to whatever is on their minds, and explore what is working and what isn’t.

In our modern, technology-driven world where people communicate more with email, social media and other channels, it’s more important than ever to make the effort to interact  face-to-face with your teams.  Read More »

Post a Comment

Winning arguments to convince your boss about Hadoop

hadoop-logoGetting universal buy in for Hadoop needn’t be an uphill struggle. In many cases, it only takes one pilot project to realize the benefits of low cost storage combined with powerful analytics.

The Hadoop topic provoked passionate conversatoin at a recent roundtable discussion attended by over 25 people from a range of industries including Retail, Telco, Gaming, Travel, Banking and Government. On hand to provide expert opinion were Cloudera (a Hadoop reseller) and experts from the SAS Data Management practice. This Customer Intelligence breakfast roundtable was held in London on November 18. We started by asking two key questions: Read More »

Post a Comment