Share with your friends










Submit

Analytics Magazine

Corporate Profile: O.R. and advanced analytics at Chevron

From solving conventional problems to solving common problems unconventionally, Chevron applies data science across the enterprise.

Shira Hetz and Margery H. ConnorBy Shira Hetz and Margery H. Connor, CAP

In a company as large and complex as Chevron, the opportunities to apply data science, operations research and decision analysis techniques to business challenges are numerous and create significant value. Chevron Corporation, based in San Ramon, Calif., is one of the world’s leading integrated energy companies, which means it participates in every aspect of the oil and gas business. This includes exploration, production and transportation of oil and gas; the refining, marketing and distribution of transportation fuels and lubricants; and the manufacture and sale of petrochemicals and additives.

From reservoir models to simulate the flow of fluids using seismic data, to managing flow of oil from the well to the retail pump, to forecasting resources for the success of major capital projects, Chevron’s experienced analytics professionals consistently generate valuable business insights for the business to make data-driven decisions.

Its size and scale are just part of Chevron’s strength. As an employer, Chevron boasts a very strong culture described in “The Chevron Way” [1], which emphasizes a core set of values and strategies that include investing in people to develop and empower a highly competent workforce. In fact, Forbes magazine ranked Chevron as the sixth happiest company to work for in 2018, outranking its oil and gas competitors by a large margin. This is partly because Chevron hires for a career at the company and not for a specific role. The company carefully manages employees’ careers to develop the breadth and depth of knowledge in various areas of the business while aligning development opportunities with employee’s interests and career aspirations.

“At Chevron, we firmly believe that by fostering diversity and inclusion, we foster our success,” says S. Shariq Yosufzai, vice president of Global Diversity for Chevron. “Diversity and inclusion helps our employees achieve their full potential, leading to greater innovation and higher performance. By aligning and inspiring the workforce, building strong relationships with business partners and deliberately developing organization capability, we deliver results that positively impact the bottom line.”

In 2015, Chevron was awarded the INFORMS Prize for effectively and repeatedly applying the principles of advanced analytics and operations research/management sciences in pioneering, varied, novel and lasting ways.

This article provides readers with insight into Chevron as a company focused on its employees and their contribution to the fields of operations research, data science and decision analysis.

Chevron Corporation, based in San Ramon, Calif., is one of the world’s leading integrated energy companies. All photos courtesy of Chevron.

Chevron Corporation, based in San Ramon, Calif., is one of the world’s leading integrated energy companies. All photos courtesy of Chevron.

Operations Research

Chevron has a long history of applying operations research. Early efforts included the use of linear programming for refinery planning in the early 1970s. Refinery planning is the process of optimizing the process of converting crude oil into gasoline, jet and diesel fuels, as well as lubricants and specialty products such as additives. Chevron produces but also purchases crude oil; acquiring crude at a competitive price is very valuable. The ability to process almost two million barrels of crude oil per day means an improvement of one cent per barrel is worth millions of dollars annually.

As the operations research competency progressed through the next decades, it evolved into distributive recursion-based linear programming as a foundation for an in-house software tool called Petro. Petro has been used by Chevron in decision-making for more than 30 years and has generated approximate $10 billion in value. Mike Wirth, Chevron’s chief executive officer, has noted that it’s an excellent example of how operations research and analytics contribute to the competitive success of the company.

By the numbers, Chevron is a huge international company with operations around the globe.

By the numbers, Chevron is a huge international company with operations around the globe.

Petro considers a long list of dynamic variables and helps analysts advise crude traders on optimal bids for respective market conditions. Analysts trained on the tool work in the refineries and next to traders in each of Chevron’s trading hubs in Houston, London and Singapore. Petro processes 400 to 500 variables associated with crude oil characterization, along with thousands of refinery-capability variables, to arrive at the most valuable operations parameters within a few seconds. In addition, Petro analysts advise refinery operations and product traders on the most economic mix of products to produce, buy or sell.

Petro scenarios results are also used in discussions with the Environmental Protection Agency and the California Air Resources Board to analyze different fuel blends being considered for future regulation. The collaboration with external agencies is central to Chevron’s goal of supporting the community and environment through scientific and technological discoveries.

Chevron also employs operations research techniques for the optimization of chemical plants to increase productivity and the optimization of schedules for large crude carrier vessels.

Data Science

“Advanced analytics and operations research are critical to helping us stand out from the competition and deliver significant advantages,” states Bill Braun, chief information officer of Chevron.

While Chevron has been applying analytics to various parts of its business for decades, the company has recently emphasized the need to scale up data science across the enterprise in a systematic way. In addition to solving traditional petrotechnical challenges based on physical models, Chevron is now combining the knowledge of engineers with that of experts in data science who provide insights with advanced computing tools such as machine learning algorithms.

“Data scientists are solving real and complex challenges that directly impact the company’s operational and financial performance,” says Justin Lo, data science team lead in Chevron’s Modeling & Analytics Center of Excellence. “We have generated over $100 million of quantifiable value using data science in the last three years and are building up data science organizational capability to drive capital efficiencies across the company.” Business managers are charged with ensuring that data scientists are working on the highest priority items and that the project solutions are being deployed and adopted by business end users to drive performance – which gives them a stake in the outcome.

In addition, data science is being applied beyond engineering and physical models. For example, Chevron data scientists are working to unravel the mystery of the unconventional reservoir for Chevron. Unconventionals, also known as tight oil, or oil that is found in low-permeability rock, poses a unique set of challenges. By applying machine learning to its proprietary database of petrophysical, completions and production attributes and implementing the completions design into its workflows to efficiently and cost-effectively develop economic and high performing wells, Chevron has significantly improved performance in this important asset delivering value even at low oil prices.

From solving conventional problems for the unconventional reservoir to solving common problems unconventionally, Chevron has also applied data science to operational challenges in its deep-water assets. The Loop Current in the Gulf of Mexico influences many industries that operate in the gulf.

Data scientists at Chevron are working on a long-range model to predict the position of the Loop Current and the eddies it spawns to ensure activities such as platform installation and drilling operations are scheduled to avoid these features. If successful, the model could also provide benefits to marine transportation routing, the fishing industry, naval operations planning and regional assessment of intense hurricane risk.

Other data science initiatives underway include work in procurement and supply chain, audit and finance, drilling and completions and facilities engineering. These activities are closely governed to ensure they will directly impact the bottom line and improve the ability to protect people and the environment.

Chevron workers in Duri Field in Sumatra, Indonesia.

Chevron workers in Duri Field in Sumatra, Indonesia.

Decision Analysis

As with O.R. and data science, Chevron has a long history of leveraging decision analysis to make strategic decisions and there is great depth of knowledge in this methodology. It is also a core requirement for all major capital projects. The decision analysis tools include stakeholder analysis, project scope framing, decision criteria and incorporating uncertainties. All Chevron managers are trained on how to use and interpret these analytical products.

Decision analysis was adopted at Chevron in 1991, and within a year, more than 1,500 individuals had participated in multi-day courses. Today, decisions analysts work across Chevron with more than 200 employees dedicated to using the practice. Chevron’s commitment to decision analysis is exemplified in the use of a proprietary decision tree software, Simultaneous Decision Analysis, which is used by upwards of 1,300 employees. The decision analysis career ladder is a well-defined track intended to provide challenging opportunities, growth and increased responsibility for each practitioner in every role. Professional development is fostered through education programs, mentorship, internal conferences and external activities. Annual internal conferences attract more than 100 attendees from across Chevron.

The commitment to decision analysis starts the first day: All college graduates in scientific and engineering career fields participate in a development program that includes three days of classroom instruction in decision analysis. More than 500 employees participate in the course annually, ensuring all Chevron’s earth scientists, engineers and technologists are familiar with decision analysis and the associated tools from the very start of their career.

Chevron was formally recognized in 2015 by the Society of Decision Professionals for exemplary organizational decision quality with the inaugural Raiffa-Howard Award at the Decision Analysis 50th Anniversary Gala. The Award’s Board of Examiners noted that, “Chevron culture is infused with decision quality. Decision-makers … understand decision analysis and expect evidence in their decision recommendations.” Chevron was also awarded the INFORMS Decision Analysis Practice Award in 2010.

Growing Organizational Capabilities

The demand for advanced analytics at Chevron continues to grow rapidly, and it is met by a balance of new college graduates and experienced external hires. The professionals working in this space have degrees in engineering, operations research, math, computer science, statistics and other related fields. Many have advanced degrees.

Information technology leadership established a central Modeling and Analytics Center of Excellence (COE) in Chevron’s Information Technology Company (ITC) to build a team with standardized training, technology and terminology. They do internal consulting to solve some of Chevron’s toughest challenges, from reducing well development costs to asset reliability. There are currently 15 data scientists in the COE and another 20 in the business.

To spark interest and to identify employees with advanced analytics skills and passion who might be good candidates for data science roles, ITC hosts internal data science competitions. Two competitions are being planned for 2018. In addition, a data science development program matches prospective data scientists with a mentor to work on a targeted data science project.

The COE and ITC culture is dynamic and team oriented. Data scientists can focus on one area of Chevron’s business or work in different areas of the business. They collaborate to solve challenges by sharing ideas and leveraging each other’s experiences. The Modeling and Analytics Community of Practice (CoP) has more than 1,000 members and hosts monthly technical talks, as well as a two-day forum focused on knowledge transfer.

What is Next?

Chevron has a long history of leveraging data and technology. Today, efforts to accelerate the adoption of emerging technologies are well underway. These include increased automation, the Industrial Internet of Things, augmented reality, blockchain, leveraging the cloud and harnessing the power of data science. With new solutions and insights, some of which were discussed in this article, the Chevron workforce continues to consistently elevate and evolve the company’s ability to power progress around the world. Chevron generates huge amounts of data, and opportunities to solve real business problems is endless. This is the perfect place for job satisfaction. Every employee is offered challenging work assignments, receives leadership and peer recognition and has a direct impact to influence capital gains for the company.

Shira Hetz started with Chevron in 2011 and is currently a data scientist in Chevron’s Gulf of Mexico business unit. Her responsibilities include leading data science projects, solving text analytics-related problems and building operational capability within her business unit. She holds bachelor and master’s degrees in mathematics and statistics from Texas A&M University.

Margery Connor, CAP, is a senior operations researcher at Chevron, where she has applied her proficiency, professional focus and operations research capabilities to address many business problems to bring significant value over a 30-year career. Connor received a bachelor’s degree in systems engineering from the University of Virginia and a master’s degree in operations research from University of California, Berkeley. In recognition of her technical contribution to Chevron, she was appointed a Fellow in 2013. Connor is Chevron’s representative on the INFORMS Roundtable and a member of INFORMS.

Acknowledgement

The authors would like to thank the colleagues and advisors who helped write this article and represent Chevron.

Reference

  1. https://www.chevron.com/about/the-chevron-way

Analytics data science news articles

Related Posts

  • 61
    “Drive thy business or it will drive thee.” Benjamin Franklin offered this sage advice in the 18th century, but he left one key question unanswered: How? How do you successfully drive a business? More specifically, how do you develop the business strategy drivers that incite a business to grow and…
    Tags: data, business
  • 57
    Data science has seen a dramatic rise in the last decade. The LinkedIn 2017 US Emerging Jobs Report revealed the two fastest growing jobs as “machine learning engineer” and “data scientist.” Universities are struggling to keep up with this trend, assembling new programs to address the growing need for data…
    Tags: data, business, science
  • 56
    New research by Continuum Analytics finds that 96 percent of data science and analytics decision-makers agree that data science is critical to the success of their business, yet a whopping 22 percent are failing to make full use of the data available.
    Tags: data, science, business
  • 56
    July/August 2013 O.R. vs. analytics … and now data science? By Brian Keller In a 2010 survey [1], members of the Institute for Operations Research and the Management Sciences (INFORMS) were asked to compare operations research (O.R.) and analytics. Thirty percent of the respondents stated, “O.R. is a subset of…
    Tags: data, science, operations
  • 52
    Many organizations have noticed that the data they own and how they use it can make them different than others to innovate, to compete better and to stay in business. That’s why organizations try to collect and process as much data as possible, transform it into meaningful information with data-driven…
    Tags: data, science


Headlines

Fighting terrorists online: Identifying extremists before they post content

New research has found a way to identify extremists, such as those associated with the terrorist group ISIS, by monitoring their social media accounts, and can identify them even before they post threatening content. The research, “Finding Extremists in Online Social Networks,” which was recently published in the INFORMS journal Operations Research, was conducted by Tauhid Zaman of the MIT, Lt. Col. Christopher E. Marks of the U.S. Army and Jytte Klausen of Brandeis University. Read more →

Syrian conflict yields model for attrition dynamics in multilateral war

Based on their study of the Syrian Civil War that’s been raging since 2011, three researchers created a predictive model for multilateral war called the Lanchester multiduel. Unless there is a player so strong it can guarantee a win regardless of what others do, the likely outcome of multilateral war is a gradual stalemate that culminates in the mutual annihilation of all players, according to the model. Read more →

SAS, Samford University team up to generate sports analytics talent

Sports teams try to squeeze out every last bit of talent to gain a competitive advantage on the field. That’s also true in college athletic departments and professional team offices, where entire departments devoted to analyzing data hunt for sports analytics experts that can give them an edge in a game, in the stands and beyond. To create this talent, analytics company SAS will collaborate with the Samford University Center for Sports Analytics to support teaching, learning and research in all areas where analytics affects sports, including fan engagement, sponsorship, player tracking, sports medicine, sports media and operations. Read more →

UPCOMING ANALYTICS EVENTS

INFORMS-SPONSORED EVENTS

INFORMS Annual Meeting
Nov. 4-7, 2018, Phoenix

Winter Simulation Conference
Dec. 9-12, 2018, Gothenburg, Sweden

OTHER EVENTS

Making Data Science Pay
Oct. 29 -30, 12 p.m.-5 p.m.


Applied AI & Machine Learning | Comprehensive
Starts Oct. 29, 2018 (live online)


The Analytics Clinic
Citizen Data Scientists | Why Not DIY AI?
Nov. 8, 2018, 11 a.m. – 12:30 p.m.


Advancing the Analytics-Driven Organization
Jan. 28–31, 2019, 1 p.m.– 5 p.m. (live online)


CAP® EXAM SCHEDULE

CAP® Exam computer-based testing sites are available in 700 locations worldwide. Take the exam close to home and on your schedule:


 
For more information, go to 
https://www.certifiedanalytics.org.