Folks, recently I was invited by re-work to be a speaker at the Deep Learning in Finance Summit held in Singapore. First of all, I wanted to thank the folks @ rework for organizing this fantastic event and inviting many talented speakers from the industry and academia. The entire 2 days agenda was a great platform to learn more about the latest happening in this area.
Regarding my presentation- The topic was “ Deep Learning & Fraud Detection in Fintech Lending”. Some of the key points that were covered during this presentation are-
Types of fintech
Key drivers for fraud in fintech lending
Common fraud modus operandi ( MOs) in fintech lending
Why deep learning for fraud detection
Sample deep learning application areas in fraud detection-
Anomaly detection using Autoencoder/ Replicator Neural Network
Social network analysis ( SNA)
Demo of Multi Layer Perceptron ( MLP) deep learning classifier built using Python, Tensorflow and Keras along with vital statistical parameters such as accuracy, logloss, precision, recall, fscore etc.
I am attaching the full presentation here. Do share your thoughts…
Happy reading.
Cheers!
-RP
6. M. O. Varied and evolving modus operandi
• Stolen identity
• Synthetic identity
• May replicate best
customer (prime
and super prime)
• Falsified info
• No willingness to
pay
• Acquire multiple loans
in a short window (
invisible window)
• May provide all info
correctly
• More likely to be on
higher side in the risk
spectrum
• No or low willingness to
pay
• Mimic good payment
behavior for significant
time
• Bust out when gains are
highest
9. Find Anomalies Replicator neural network / Autoencoder
• Traditional techniques based on density or distance works better with linearly separable
data
• Stacked Autoencoders (SAE) and Deep Belief Networks ( DBN) make no assumptions
about the distribution of data and work better on non linearly separable data
• Unsupervised learning algorithms for feature learning, feature reduction and outlier
detection
• Input vectors are used as output vectors and reconstruction error computed
• The data points with higher reconstruction error ( MSE) are more likely to be outliers
• Helps in detecting different modus operandi of fraudsters
• Output from the network is generally used as an input for the Multi Layer Perceptron (
MLP) to improve classification accuracy .
• Generally training an MLP with the features selected from Deep Autoencoders will be
more efficient and faster process
11. MLP Demo Case details
• Anonymized credit card transactions data from European customers
• 30 features ( 28 anonymized, duration elapsed, amount of transactions)
• Label- fraud or normal transaction
• 17bps incidence rate for fraudulent transactions
• 284,807 total transaction in data
Sources: http://mlg.ulb.ac.be | https://www.kaggle.com/dalpozz/creditcardfraud
14. MLP Demo Network training
Little or No Manual Feature Engineering
• No over or under sampling
• No variables dropped
• Only standardization of features done
• 75% training/ 25% validation
• No manual binning
Fitted Network
• Multi Layer Perceptron with three hidden layers.
o Activation function = Sigmoid
o # of neurons = 512 in the input layer
o Each consequent layer has half the neurons
o Cost function = logloss
o Optimizer = adam
o Epochs= 5
o Dropout rate = 30%