SLB is on a journey to reshape the future of energy, and data is a huge part of that vision. I strongly believe that AI and machine learning can transform our industry and really reshape the future of energy by integrating our domain and digital capabilities with very, very powerful platforms like Dataiku.

— Rakesh Jaggi, President of Digital & Integration at SLB SLB needed a single data science and AI platform to access the SLB domain data through no- and low-code code interfaces, where prior work is easily discoverable, and the technology is close to the systems where the insights and models will be deployed to. They of course also needed to empower data scientists and technical experts to be more efficient and effective.

SLB & Dataiku use cases

The partnership with Dataiku has enabled SLB to drive improvements and save millions on use cases across the business, including interpretation and processing of well logs, fault interpretations, drilling time reduction, HR optimization, and much more. Here is just a small taste of how SLB makes data and AI part of day-to-day decision making for everyone across the organization, whether a technical expert, data expert, or somewhere in between.

From 8 hours to 20 minutes to size well construction tenders

One of the main integrated well construction services that SLB offers to operators is the delivery of “lump sum turnkey” wells, where SLB delivers wells to its customers at a fixed cost. Because SLB carries an increased proportion of well delivery risk for this service, they must correctly size the response to the bid to ensure that the project is profitable while providing competitive prices to customers.

Determining the cost of a well starts with the manual classification of operations, followed by the extraction of key performance indicators before eventually building an operational sequence and forecasting the risks associated with each well of an invitation to tender.

The key challenges are: Data is often stored in unstructured reports (daily drilling reports, or DDRs). The period to respond to a tender is extremely short, so quick turnaround time is of the essence. Due to these challenges of scalability and speed — not to mention questions of accuracy, as human errors are incorporated by the unconscious bias of the well engineer — classifying a well previously took an SLB engineer approximately eight hours.

SLB developed a data-driven approach with Dataiku that has so far been used to assess more than $10 billion worth of well construction tenders and allows engineers to do the same analysis in just 20 minutes. In addition, the updated process allows for a structured, auditable, and data-driven approach to predicting the time it will take to drill the wells, as defined in the tender's scope of work.

76% more efficient reservoir pressure analysis

Reservoir pressure is essential data for different analysis — for example, proposals for drilling new wells, workover operations, reservoir and production engineering analysis, and more.

When events beyond the control of SLB occur that result in the suspension of oil production operations — these events include well shutdowns as well as production flowline ruptures — occur, SLB does a well-by-well analysis to identify start and end of shutoff events and stabilized pressures to get reservoir pressure data.

This analysis used to take at least one week to complete, and also there was also no general visualization dashboard that allowed the engineer to have a general overview of the data being analyzed, which further limited the efficiency of this process.

Using an efficient Dataiku workflow with a combination of datasets, recipes, and programming, the team developed a reservoir pressure detection tool that automated the identification and gathering process of stabilized pressure. The tool also allows easy visualization of results in Spotfire, and the process to analyze monthly pressure trends well by well is now 76% faster.

Optimizing human resources processes with Dataiku

SLB's use of Dataiku doesn't just stop with its core business units — it also extends to its supporting business functions, including human resources (HR).

For example, SLB's People Analytics team uses Dataiku to better equip its talent management teams globally, reducing the time invested in training by months and years and improving talent retention (saving millions of dollars annually).

What does that mean concretely? Well, just like any modern company, SLB is focused on improving employee retention. Using Dataiku, they have built data pipelines from troves of data (i.e., across salary information, vacation data, performance and career stagnation information) to notify talent managers across the company about at-risk populations so they can effectively take actions as early as possible. They also provide the talent managers with insights on how they can improve the environment for their employees, such as salary, skill, or schedule changes.

Each year, the cost of unplanned employee attrition costs SLB $80-$200 million but, with the predictive model in Dataiku, the company has been able to retain between $18-45 million of that total thanks to the work the People Analytics team has done to maintain the high-value employees identified.

In addition, SLB's D&I (Digital & Integration) HR team used Dataiku plus PowerBI to develop their Skills2Career Dashboard, which transformed the talent acquisition model from external hiring to internal upskilling, saving hundreds of thousands of dollars in recruitment drives and external hiring.