Speech Title: Big Data, Machine Learning and Justice

ABSTRACT: In this presentation we start with the main challenges of using big data and machine learning, including scalability and fairness. We exemplify these challenges analyzing how machine learning has been applied lately in justice and how human biases are exposed by models that learn from human data. However, even though these models are not perfect, they are many times better than humans because they are always coherent in their decisions. We will finish with some bad and good practices that should be avoided or enforced, respectively, when training machine learning models.

BIO: Ricardo Baeza-Yates is, since June 2016, CTO of NTENT, a semantic search technology company based in California, USA. He is also the Director of Data Science Programs at Northeastern University, Silicon Valley campus, since August 2017. He is also part-time professor at Universitat Pompeu Fabra in Barcelona and Universidad de Chile in Santiago. Before, he was VP of Research at Yahoo Labs, based in Barcelona, Spain, and later in Sunnyvale, California, from January 2006 to February 2016. Until 2004 he was the founding director of the Center for Web Research at the University of Chile. He is co-author of the best-seller Modern Information Retrieval textbook published by Addison-Wesley in 1999 and 2011 (2nd ed), that won the ASIST 2012 Book of the Year award. From 2002 to 2004 he was elected to the Board of Governors of the IEEE Computer Society and between 2012 and 2016 was elected for the ACM Council. Since 2010 is a founding member of the Chilean Academy of Engineering. In 2009 he was named ACM Fellow and in 2011 IEEE Fellow, among other awards and distinctions. He obtained a Ph.D. in CS from the University of Waterloo, Canada, in 1989, and his areas of expertise are web search and data mining, information retrieval, data science and algorithms in general.

Speech Title: Data Science in Smart Cities

ABSTRACT: A Smart City is a city that performs well in the following characteristics: economy, people, governance, mobility, environment and living. The high degree of datification and connectivity embedded in a Smart City demand tools and mechanisms for data manipulation and representation that facilitate the extraction of meaningful insight. However, this process of extracting knowledge from data requires Data Science. Design and operation of smart, efficient, and resilient cities has come to require data science skills. Today, rich data and powerful algorithms in the hands of domain experts have transformed decisions about marketing and advertising, but not those decisions about how we maintain our urban infrastructure and built environment. It is time to understand how these approaches can be applied to the challenges in adaptive monitoring and control of civil infrastructure systems, and to invent the tools which will allow researchers and practitioners to better leverage these approaches so that decision-making will be based on all available data. In this talk, we will discuss the fundamentals of reproducible data science and analytics, probability and statistics, and machine learning to leverage data generated within different kind of systems.

BIO: Dr. Seifedine Kadry has a Bachelor degree in applied mathematics in 1999 from Lebanese University, MS degree in computation in 2002 from Reims University (France) and EPFL (Lausanne), PhD in applied statistics in 2007 from Blaise Pascal University (France), HDR degree in 2017 from Rouen University. At present his research focuses on Data Science, Machine Learning, and probability and reliability analysis. He is ABET program evaluator.

Speech Title: DTS Data Analysis using Machine Learning

ABSTRACT: BP AGT, and specifically ACG field has the highest number of DTS (Distributed Temperature Sensing) installed wells with a long history of DTS data (over 10 years for some wells). These data had been actively used in understanding reservoir performance and well integrity issues in a qualitative way. Although numerical interpretation of DTS data is underway, recently emerged computing power and ever-growing amount of data allows us to utilize machine learning techniques to quickly analyze the data and recognize desired patterns and physical relationships. These relationships can further be used to integrate with other surveillance data and make decisions related to reservoir and wells performance. BP provided an opportunity to the University to work with cutting edge technology data in the Petroleum Industry. Selected group of talented students from ADA University has been entered into the world of petroleum data. They loaded and organized the required data and provided fit for purpose initial data visualization. Ultimately, machine learning architecture built for DTS data analysis is to be created for predicted purposes (e.g. water breakthrough time, gas/oil ratio, pressure fluctuations etc.). Project run by phases and each phase split into several check-points.

BIO: Born in Baku, Azerbaijan. Finished the Master degree of Business/Managerial economics from the Azerbaijan State Oil and Industry University in 2000. I started programming back in 1993 and entered the world of oil industry in 1996 as a developer/data analyst. Joined BP Exploration (Caspian Sea) Ltd. back in 2001 and hold various data analytical positions. Right now, I am the member of Subsurface Information Management (SIM) organization. At current role of Senior Subsurface Data Scientist making decisions on data models and analytics, supporting research projects and developing the scientific proposals. A PhD Candidate and Researcher at the Azerbaijan National Academy of Sciences (ANAS) in earth sciences since 2017.

Speech Title: Digital Transformation for SOCAR Upstream

ABSTRACT: SOCAR’s vision of transforming to leading integrated operator with world standards through simplification, standardization and automation of business processes through implementation of world class technology platforms and improving organizational efficiency by imparting right training, building essential skills and bringing the culture of excellence. SOCAR is committed to the transformation and will bring together multiple technologies through product ecosystem complimentary to existing landscape and business needs. The guiding principles for future integrations are –

• Technology platform will be extendable to multiple SOCAR units without much customization
• Simplified business processes and workflow
• Development and implementation will be done in agile way with expectation of business benefit realization at end of each sprint (8 to 12 weeks of sprints focused on delivery of business processes)
• Enable development of local skills and capabilities

BIO: As program manager for Business transformation stream, Milind is responsible for execution of projects and developing the scope and solutions for initiatives undertaken by SOCAR. Milind has ~25 years of industry and international consulting services experience across the value chain of the O&G industry, encompassing business operations, capital project, complex transformational programs, product development, and IT services management.