The digital learning ecosystem An efficient management approach to capability development, delivering smarter teams, improved productivity and better business outcome for the managers.
The digital learning ecosystem Digitally and seamlessly connecting you, the learner, with pertinent learning objects and related technologies ensuring systematic, engaging and continued learning.
Industry and client recognition
Best Outreach Program Finalist: WorldOil Awards
Overall Customer Satisfaction Score
Training provider of the year: 2013, 14 and 15
Upstream learning simulator With more than 50,000 participants instructed in various disciplines, data driven OilSim runs real-world oil and gas business scenarios and technical challenges.Engaging. Educational. Enjoyable
Develop measurable skills and capabilities
This is a virtual course covering the Fundamentals of Data Analytics agenda, which introduces the data analytics techniques to extract knowledge from raw data. The course aims to educate the class audience on how to create data-driven models through the data mining pipeline that consists of data exploration, data preprocessing, machine learning modeling, and model evaluation. The course combines theoretical knowledge with hands-on training of the data analytics techniques. After taking this course, the participants should be able to build and evaluate data-driven models via the machine learning approach.
This is a practical course with 50% of the time dedicated to hands-on sessions using the Data Science profile in Schlumberger's DELFI Cognitive E&P environment and / or Orange Open Source Data Mining Software suite which is based on visual programming. Hands-on sessions will be based on oil and gas related datasets.
This course will be delivered entirely online, over a total of 20 hours (five 4-hour sessions over 5 days).
Session 1 - 4 hours
On the first day of the course the participants will be able to get a bird-eye view of the data analytics process. They will explore one of the four data analytics modules called exploratory data analysis, a necessary step to get the feel of the data. Learning will be reinforced via hands-on training using the DELFI Data Science Profile and / or Orange.
Session 2 - 4 hours
Supervised Machine Learning
The second day will start with data preprocessing, a necessary step to clean and format the data before building machine learning models. Later in the day, supervised machine learning concepts will be introduced, and participants will be able to build data-driven models via a supervised machine learning algorithm called Decision Tree. Learning will be reinforced via hands-on training using the DELFI Data Science Profile and / or Orange.
Session 3 - 4 hours
Supervised Machine Learning
On the third day of the course, the participants will learn about model evaluation matrices (e.g., confusion matrix, ROC, AUC, etc.) and model evaluation methods (e.g., 10-fold cross validation) will also be discussed. Later in the day, regression analysis, particularly linear regression and logistic regression will be introduced. Learning will be reinforced via hands-on training using the DELFI Data Science Profile and / or Orange.
Session 4 - 4 hours
On the fourth day of the course, participants will complete a hands-on session on regression analysis, after which they will be introduced to more advanced machine learning techniques of ensemble methods. They will be able to implement the complete data mining pipeline including model building and model evaluation using the DELFI Data Science Profile and / Orange.
Session 5 - 4 hours
Unsupervised Machine Learning
On the last day of the course, the participants will be introduced to unsupervised machine learning algorithms. The course will end with a hands-on session on clustering using the DELFI Data Science Profile or Orange.
Geoscientists, Engineers, IT professionals and aspiring Citizen Data Scientists working in the oil and gas industry
who want to get introduced to data analytics techniques for building data-driven models.
No prior experience of data analysis is required, although basic math and statistics knowledge is useful.
Customize your own learning journey and track your progress when you start using a defined learning path.