Deep Insights. Deep Expertise.
Discover
Data Science (Market Data)
A Tier 1 South African Bank needed to validate the market data time series used in the Value At Risk (VaR) and Capital calculation processes.
They also required the development of control methodologies around the market data time series. Leveraging data science (market data) techniques (Long short-term memory (LSTM) neural networks, autoencoders and convolution neural networks), Riskworx developed tools to flag inconsistencies in the data set, supporting the validation process. The tools also suggest data fixes, alternative market data and predict VAR, P&L and ledger outcomes. Visit riskworx.com and our LinkedIn page