Data Science Summit

Making Analytics Work for Business

Businesses today are collecting vast amounts of data from operations, manufacturing, supply-chain management, customer behavior, marketing campaign performance, workflow procedures, and so on. At the same time, information from external sources such as market trends, industry news, and competitors’ movements are also widely available. The volume and variety of data have far surpassed the capacity of manual analysis. The good news is, computing power, too, have become far more advanced with network ubiquity and well-developed algorithms. The convergence of these phenomena has given rise to data science application in businesses. Data Science Summit at Geospatial World Forum 2019 will highlight best practices in extracting useful information and knowledge from data that improve business performance.


Christian Heipke, Professor, Photogrammetry and GeoInformation, Leibniz University of Hannover, Germany
Christian Heipke Professor
Photogrammetry and GeoInformation
Leibniz University of Hannover
Callum Staff, Lead Data Scientist, Marks & Spencer, United Kingdom
Callum Staff Lead Data Scientist
Marks & Spencer
United Kingdom
Weigang Yan, Senior Data Scientist, Cambridge City Council, United Kingdom
Weigang Yan Senior Data Scientist
Cambridge City Council
United Kingdom
Mykola Kozyr, Project Coordinator, EOS Data Analytics, Ukraine
Mykola Kozyr Project Coordinator
EOS Data Analytics
Matthew Wilson, Professor ,  University of Canterbury, New Zealand
Matthew Wilson Professor
University of Canterbury
New Zealand
Adrian Badi, Senior Data Analyst, Business Intelligence, William Demant, Denmark
Adrian Badi Senior Data Analyst, Business Intelligence
William Demant
Ipsit Dash, Senior Consultant, Government (Space), CGI Nederland, The Netherlands
Ipsit Dash Senior Consultant, Government (Space)
CGI Nederland
The Netherlands


Building Effective Machine Learning Models for Business

Model fitting is the essence of machine learning. A properly fitted model can capture the complex relationships between known variables and the target variable, allowing it to find relevant insights or make accurate predictions. This is crucial in order to solve specific real-world business problem with a high level of accuracy. Data scientists will discuss best practices in building an accurate predictive model, from data cleaning to deployment.

Data-driven Products and Services

Developing data-driven products is certainly a very innovative way to use and monetize data, but also a complex one. Ability to handle data consistently and securely is the key for any business to succeed in this domain. Data-driven products are powered by analytics, business domain knowledge, and scalable IT architectures. It requires organizations to become truly digital – in their products as well as in their business models. Data-driven products get additional value when advanced analytics is embedded. Data scientists from major data-driven businesses will share their know-hows for successful and sustainable data-driven products and services.

Extracting Business Value from Unstructured Data

It is estimated that between 80 and 90 percent of data in an average organization is unstructured. And most of the data remains to be untapped or simply disposed. A few examples of unstructured data are word documents, images, emails, social media posts, product reviews, digital audio files, etc. The value of unstructured data comes from the patterns and the meanings that can be derived from it; this includes identifying issues, market trends, or overall customer sentiment towards a brand. Extracting intelligence in unstructured data can help businesses yield deeper insights and drive strategic business decisions. Data scientists will discuss the best solutions for the analysis of unstructured data via AI and machine learning.