Discussion: Broadening the data base for deepening the ...

Discussion Broadening The Data Base For Deepening The -ppt Download

  • Date:13 Jul 2020
  • Views:6
  • Downloads:0
  • Size:83.60 KB

Share Presentation : Discussion Broadening The Data Base For Deepening The

Download and Preview : Discussion Broadening The Data Base For Deepening The

Report CopyRight/DMCA Form For : Discussion Broadening The Data Base For Deepening The


Transcription:

Discussion for Broadening the data base for deepening the focus The use of big data analytics in transaction banking Dr Martin DiehlDiscussant Adrian Guerin Bank of Canada .
Any opinions expressed herein are those of the discussant and donot necessarily represent the views of the Bank of Canada Presentation Overview Introduction to Big Data Analytics and methods Use cases in financial industry.
Available data in transaction banking Overview of existing areas of research Potential applications for central banks Summary Big Data Analytics More data different types speed accuracy and value .
Variety of sources internet devices corporate systems infrastructures BDA combination of Data Mining and Machine Learning Methods Supervised learning.
Unsupervised learning Reinforcement learning Summary Use Cases Transaction BankingExisting use cases Classification .
Anomaly detection and fraud detection Default prediction Forecasting Market returns risk indicators Sentiment analysis.
Potential use cases Predict RTGS liquidity needs participant or system Forecast consumption Thank you presentation highlights analytical opportunity BDA Data Science an evolving field skills in short supply.
Applied most notably in private sector e g Google Amazon IBM Proliferation of DS training university level certificate Content is timely DLT or blockchain technology potential for wealth of data providedto central banks and regulators.
Possible regulator node with full ledger visibility near real time data Example initiatives ASX examining DLT option with DAH for CHESS replacement DTCC partnered with IBM Axoni R3 to build DLT solution for derivatives post trade processing re platform DTCC s Trade Information Warehouse .
Comments Questions Overview of primary methods very helpful as introduction Light touch on data scraping mining and NLP but appropriate given itmay not be useful in payments systems context Questions Data assessment available data .
Are there opportunities for data mining to complement transactionbanking data and analyses Can we confidently use unofficial statistics acquired through dataComment unsupervised learning Can be challenging to set up e g k means how many clusters.
appropriate and interpret are there natural groups Comments Questions AI methods as black box Comments Agree must continue to be vigilant of model risk Can measure performance of ML algorithms e g confusion matrix for.
supervised learning but May create false sense of confidence Are test train data representative contain outlies Where are the falsenegatives Question Comments Feature selection.
Key ML objective is to maximize measured model performance Does this create a risk similar to in econometrics with kitchen sink models andthe search for statistical significance Do the techniques lend themselves to overreliance on such measures is this a riskfor feature selection might we improperly leave something out .
ML methods are smart but continue to rely on data inputs featureselection and lookback period sample data considerations are important Thank you Discussion for:Broadening the data base for deepening the focus? The use of big data analytics in transaction banking – Dr. Martin DiehlDiscussant:Adrian Guerin, Bank of Canada* *Any opinions expressed herein are those of the discussant and do not necessarily represent the views of the Bank of Canada

Related Presentations