Team member: Awad Ali, Head of Artificial intelligence & Analytics
Country: United Arab Emirates
Organization: ADNOC
Established in 1971, Abu Dhabi National Oil Company (ADNOC) is a diversified group of energy and petrochemical companies that employs more than 50,000 people and is a major contributor to the GDP of the United Arab Emirates (UAE). ADNOC operates across the entire hydrocarbon value chain with different fully integrated Group Companies providing services in the fields of exploration and production; oil refining and gas processing; chemicals and petrochemicals; refined products and distribution; maritime transportation; and support services, including sales and marketing, human capital, legal, finance and IT.
ADNOC has been named the UAE’s most valuable brand for a second consecutive year starting from 2019, a 28.6% increase over the previous year and a 145% increase since the launch of its transformation strategy in 2017, making it the fastest-growing brand in the Middle East and the first UAE brand to surpass $10 billion in value.
Awards Category:
- Best Acceleration Use Case
- Best ROI Story
Business Challenge:
As one of the leading energy groups in the Middle East, ADNOC manages a vast network of over 500 service stations that operate 24/7 across the region. Each station offers three different fuel grades, and diesel to serve customer demand at all times.
At this scale, ensuring a consistent supply of all fuel grades represents significant business and technical challenges for the retail and operations teams. They were previously working with a basic model averaging forecast for predicting fuel demand, which proved to lack accuracy.
The inaccuracy led to a loss of business opportunities, as competitors were able to capitalize on the gaps in ADNOC's fuel supply chain. Moreover, it had a negative impact on the company's reputation, further highlighting the need for a more efficient and accurate solution.
In response to these challenges, ADNOC gathered a small team of data scientists, engineers, and business leaders from Retail Operations, Logistics, and Finance to build a new predicting data workflow.
Business Solution:
ADNOC aimed to build a more accurate model to predict fuel consumption across each station to ensure operational excellence and maximize efficiency without losing sales.
After researching the market, ADNOC found Dataiku to be the leader in developing fast and efficient AI solutions. Dataiku offers a quick learning curve, allowing data scientists to be productive in just a few days without requiring long product training. It also provides a visual data flow that is easy to understand, from syncing to the data and preparing it to developing the models and generating new outputs. Additionally, Dataiku's explainable AI feature enables data scientists and stakeholders to understand the factors influencing model predictions through interactive reports for feature importance, partial dependence plots, and individual prediction explanations.
The team built three models:
- The hourly prediction model runs every hour to predict seven days ahead, providing visibility to the Operations team for planning the following week. Seasonality plays an important role in this model, as it accounts for low consumption during the night and high consumption during the day. This ensures that trucks deliver the right quantity of fuel.
- The daily prediction model runs monthly to predict 45 days ahead. Its purpose is to plan the retail workforce distribution in each station for each shift during the next month. This model optimizes resource allocation for the 10,000 staff members of the Retail Operations unit based on real demand.
- The monthly prediction model provides an 18-month sales volume forecast for fuel, allowing Finance and Retail Planning Management to forecast profit and loss for the year ahead across stations and cities. This helps them to allocate budget and resources across departments more efficiently.
With the help of Dataiku, ADNOC successfully built a more accurate prediction model for fuel demand, addressing the challenges encountered with their previous average-based model.
Day-to-day Change:
This new scientific approach has completely overhauled the fuel delivery system, which is now automated using a command center. A master dashboard is updated in real-time to display traffic lights to indicate the status of each station:
- Green light signifies that the station is operating perfectly.
- Yellow light indicates that it may run out of business within the next eight hours.
- Red light warns that the station has only three hours left before running out of fuel.
- Black light means that the station has already run out of fuel.
In addition to this market-leading command center, the fuel delivery process itself has been automated, ensuring that fuel is delivered from the nearest fulfillment center. This streamlines the delivery process and reduces wait times for fuel replenishment.
Moreover, an advanced system has been implemented to track vehicle movement on the road, providing near real-time updates on their location and progress. This cutting-edge technology allows for better coordination and management of fuel deliveries, ultimately improving overall cost efficiency, as well as staff and customer satisfaction.
Business Area Enhanced: Supply Chain/Supplier Management/Service Delivery
Use Case Stage: In Production
Value Generated:
The advanced fuel demand prediction system triggered tremendous benefits across the board:
- Revenue
The newly built models reduced inventory loss from 0.8% to 0.12%, the scale of which translates into tens of millions in revenue gain. This improvement is tracked on an automated dashboard, which is critical for monitoring the reduction in business opportunity loss.
- Operation and Retail staff
Staff optimization has been implemented across 500 service stations, involving 10,000 staff members. Previously, it was a real challenge to move staff members dynamically without the aid of scientific data and models. Now, staff loyalty and happiness have increased as they benefit from more accurate planning and no longer need to manage deceived customer expectations.
- Customer experience
Customer experience also improved globally, as customers are almost guaranteed to find all fuel grades across each station anytime they need it. This resulted in better interactions with retail staff and increased customer loyalty.
- Financial planning
Budgeting has also seen significant advancements, with more accurate forecasts for target and future sales for each division in the retail sector. This has allowed for better financial planning and resource allocation across departments.
The team is looking to implement route optimization next, whereby the shortest routes will be automatically selected to deliver fuel to multiple locations in one truck ride - saving both time and resources. This will further enhance the efficiency and effectiveness of the company's operations.
Value Brought by Dataiku:
- Time to market
One of the key benefits of using Dataiku is the significant reduction in time to market for data solutions, which allows businesses to bring value more quickly. With traditional methods, development time may have taken more than eight months. The ease of using Dataiku, combined with its comprehensive feature set, enabled us to cut development and productionalization time in half.
- Collaboration
Facilitating collaboration is at the heart of Dataiku, thanks to its visual interface bringing together data science teams and business stakeholders to develop more effective solutions. This level of collaboration is essential for ensuring that all parties are on the same page and working towards the same goals. It also enabled us to involve more junior profiles without over-relying on seasoned data scientists to make progress throughout the project.
- Technical flexibility
Dataiku also offers unparalleled flexibility when it comes to connecting to different data sources. Users can read data and write back to any source without limitations. This freedom allows us to store data back in our own systems and push it via API to other platforms as needed, ensuring that we can make the most of the workflows created in Dataiku.
- Explainability
Dataiku provides advanced capabilities for explainable AI, such as interactive reports on feature importance, what-if and subpopulation analyses, and individual prediction explanations. In addition, model and project documentation is automated, which enables teams to save time on maintaining docs while providing consistent records of the project for compliance.
Value Type:
- Improve customer/employee satisfaction
- Increase revenue
- Reduce cost
Value Range: Dozens of millions of $
