Deloitte Germany (Data analysis)
Company: Deloitte provides audit, risk advisory, tax, financial advisory, and consulting services to public and private clients spanning multiple industries; legal advisory services in Germany are provided by Deloitte Legal. With a globally connected network of member firms in more than 150 countries, Deloitte brings excellent capabilities and high-quality service to clients, delivering the insights they need to address their most complex business challenges. Deloitte’s approximately 286,000 professionals are committed to making an impact that matters.
Project: The goal of this project is to analyze data anomalies in the context of credit card data. Based on anonymized credit card transactions, time series patterns need to be analyzed in order to detect payment fraud. Based on both statistical and machine learning approaches, competing fraud detection models will be investigated. As a result, the applied approaches will be compared with respect to accuracy, complexity and feasibility. Additionally, the results will be visualized. You will work together with experienced data scientists and you will learn in this project how to visualize and to communicate results within a heterogeneous team. Furthermore, you will get deep insights into the challenges that practitioners are facing, especially when the achieved solutions to such real-world problems need to be implemented into applied risk management processes.
This project will be hosted by the Med Lab together with the Analytics Institute.
The Analytics Institute has been working as a think tank and accelerator in the sectors of business and technology since 2014. Since it was created, it enables companies to think new and differently about the use of data analytics and Big Data to explore and exploit available opportunities.
The Analytics Institute operates at the intersection of business, academia and technology as an expert and catalyst for analytics in the marketplace, enabling clients, partners and stakeholders to develop, implement and improve sustainable analytics solutions within their business and technological infrastructure.
The prospective participant should:
- have a solid statistical or mathematical background,
- have a good command of a programming language and should be experienced in writing scripts, e.g. in R or Python,
- and experience with Big Data.
- He or she should be prepared to work with real-world datasets from industry partners (which involves cleaning and preprocessing to overcome inconsistencies and incompleteness).
Ideally he or she
- is familiar with methodologies of outlier detection,
- has already worked with machine learning algorithms,
- is interested in financial risk management and
- has experience in visualizing of large data sets.