The ICCSSA Board has decided that over the next few years the ICCSSA convention would be replaced by regular ICCSSA seminars.
Machine Learning: Part I
You are hereby invited to attend the first in a two-part series on machine learning, hosted by ICCSSA and ORSSA Pretoria.
Churn prediction using neural networks - Marc Gagiano (Business Science Corporation)
Marc will start with a brief introduction of data science in the context of business, as well as machine learning and how it fits in. There will be a brief discussion of the differences between machine learning and regression. A case study for a telecommunications company will be presented where machine learning was used to generate more revenue. The main application is churn prediction using neural networks, and confusion matrices is used to measure the performance to quantify the additional revenue generated. The algorithm, as well as variations thereof, will be explained along with details surrounding its implementation.
Granting credit based on a real-time machine learning classification engine - Christiaan Hattingh (MyBucks)
The context of this case study is specifically micro-credit. Christiaan will discuss how credit risk decisions can be viewed as a machine learning classification problem, with a brief, non-technical description of machine learning algorithms and approaches for this purpose. The real-time implementation and challenges will be discussed, as well as how machine learning allows quantitative adjustment of risk appetite, with a calculated expectation of returns...................