You are on page 1of 9

Public

Patrick Papsdorf
Adviser Discussion:
European Central Bank
“Detection and Explanation of
Anomalous Payment Behavior in
RTGS Systems” by Trieples,
Daniels, Heijmans

15th Payment System Simulator Seminar


31st August 2017, Helsinki/Finland

The views expressed here are those of the author and do not necessarily represent the views of
the European Central Bank and the Eurosystem.
Rubric

See https://jakubmarian.com/wp-content/uploads/2014/12/milk-consumption.jpg

See https://jakubmarian.com/wp-content/uploads/2017/03/nuts2-researchers.jpg

P.Papsdorf - Discussion anomaly detection 2 www.ecb.europa.eu ©


Rubric
Summary

Anomalous payment behaviour


Anomaly detection in payments data

•Demand: high for identifying anomalous behaviours


timely, (semi) automatically with high accuracy
•Challenges: data complexity (3V’s), networks,
scope setting, resources …
•Paper:

See Practical Machine Learning: A New Look at Anomaly Detection


by E. Friedman, Ted Dunning

P.Papsdorf - Discussion anomaly detection 3 www.ecb.europa.eu ©


Rubric
Summary

AI / machine learning
Anomaly detection (outlier detection)
Identify items/events/observations that do not conform to an expected pattern See https://betanews.com/2016/12/12/

or other items in a dataset.


deep-learning-vs-machine-learning/

Here: Unsupervised anomaly detection. Detects anomalies in unlabelled data sets.


“You don’t know exactly what you are looking for.” See Practical Machine Learning: A New Look at Anomaly Detection
by E. Friedman, Ted Dunning

Supervised anomaly detection based on labelling of data as "normal" and


"abnormal".

Autoencoder
•Feed-forward neural network, which learns from examples. It applies learnings to new data.
No learning of concrete examples but recognition of patterns. See Wikipedia on neural networks

•Trained to reconstruct input layer at the output layer by processing input via a hidden layer in
which a set of neurons form a compressed representation
Input layer of the input in a lower dimensional
Hidden layer Output layer
space. (See Triepels, Daniels, Heijmans)

See https://blog.keras.io/building-autoencoders-in-keras.html

P.Papsdorf - Discussion anomaly detection 4 www.ecb.europa.eu ©


Rubric
Summary [Please select]
[Please select]

What was done here


Dutch component of TARGET2, customer payments of 20 most active banks broken down in time intervals and
liquidity vectors

•Three different autoencoders


•Optimal point of neurons/compression determined: more neurons would not lead to much better
reconstruction (low MRE), i.o.w. dynamics of liquidity vectors well captured.
•Anomalies spotted (above set threshold) and three observation areas (A, B, C) examined by drill down using
time interval, banks, in/outflows
•Bank that was subject to bank run was identified

P.Papsdorf - Discussion anomaly detection 5 www.ecb.europa.eu ©


Rubric
Comments and questions

• Thank you for this!

• Novel approach to apply AI to payments data.

• Autoencoder method resulted in identifying outliers.

• Possibly opening a new strand in FMI analytics interesting for


System Operator and Oversight.

• Many potential fields could be considered, like AML/CTF, fraud,


intraday liquidity management, funding issues, MM outliers, auto-
triggers/alerts, interdependencies …

P.Papsdorf - Discussion anomaly detection 6 www.ecb.europa.eu ©


Rubric
Comments and Questions

Model set-up
•One hour time intervals for liq. vectors vs longer/shorter intervals.
•Reasoning for chosen timespans of datasets.
•How to operationalize method in a dynamic environment - continued
learning?

Anomaly detection
•Threshold setting and review is manual.
•Type1 and Type 2 errors to underpin “reasonable accuracy”.
•Compression level: risk of Over-fitting vs. Under-fitting.
•Timeliness and accuracy – some outliers (A,C) only explained as non-
relevant over time.

P.Papsdorf - Discussion anomaly detection 7 www.ecb.europa.eu ©


Rubric
Comments and Questions

Scenario
•Chosen scenario typically evolves very differently.
•Once run is detected it may be too late.
•Are there other earlier signals in payments data? E.g. CB
operations, interbank, delays, intraday credit usage, cash
reservations that could be tested.
•Knowledge of bank run helped to understand identified outlier (B).

P.Papsdorf - Discussion anomaly detection 8 www.ecb.europa.eu ©


Rubric

Thank you
… and a discussion appetizer for later

S.Hawking: “The
L.Page: “Artificial
development of full
intelligence would be the
artificial intelligence
ultimate version of Google.”
could spell the end
of human race.”
Ethical and moral aspects
related to AI
E.Musk:
“biggest risk
V. Rometty: “this technology will we face as a
enhance us. So instead of artificial civilization.”
intelligence, I think we'll augment
our intelligence.”

P.Papsdorf - Discussion anomaly detection 9 www.ecb.europa.eu ©

You might also like