Optimized Sequence Prediction Of Risk Data For Financial Institutions

Data quality is essential in banking industry for the compliance with the standards of banking regulation, BCBS 239. But the quality is yet to be forecasted by many financial institutions. Machine learning has been recommended by the regulator in 2018 to resolve this. To assist on this, we develop a machine learning model to train several Long Short-Term Memory ("LSTM") Recurrent Neural Networks ("RNNs") for the prediction including forward LSTM RNN, backward LSTM RNN and bi-directional LSTM RNN ("BiLSTM"). With the prediction, financial institutions will understand what data quality is going to be. The networks make sequence predictions with optimizations followed by an evaluation with heterogeneous methodologies, validation techniques and algorithms.