Abstract: 

Explaining the decisions and behavior of machine learning and AI models has become increasingly important. That is especially relevant when high-stakes decisions are involved and in industries such as finance, healthcare, and insurance. In this talk, we will frame explainability within the financial domain and discuss some pros and cons of explaining machine learning models. We will also highlight where explainability fits in the machine learning development cycle and what different stakeholders may need from it. The talk will finish with some important 'do's' and "don't"s of successfully applying XAI.

Bio: 

Violeta has been working as a data scientist in the Data Innovation and Analytics department in ABN AMRO bank located in Amsterdam, the Netherlands. In her daily job, she works on projects with different business lines applying the latest machine learning and advanced analytics technologies and algorithms. Before that, she worked for about 1.5 years as a data science consultant in Accenture, the Netherlands. Violeta enjoyed helping clients solve their problems with the use of data and data science but wanted to be able to develop more sophisticated tools, therefore the switch. Before her position at Accenture, she worked on her PhD, which she obtained from Erasmus University, Rotterdam in the area of Applied Microeconometrics. In her research, she used data to investigate the causal effect of negative experiences on human capital, education, problematic behavior and crime commitment.