You are on page 1of 15

Welcome!

An Introduction to

Neural Networks
www.vintasystems.com

WHAT ARE NEURAL NETS?

Neural Nets are function approximation tools


Il

OI

f (?)

Ii
Ix

Inputs

Oj

Outputs

Oy

WHAT ARE NEURAL NETS?

Output

Hidden
Input

Neural Nets learn the relationship between the


independent variable and the dependent variable

NEURAL NETS vs

STATISTICAL
APPROACHES

Neural Nets make no assumptions on the


statistical distribution of data

Neural Nets are non-linear approaches that


provide much accuracy when modeling
complex data patterns
Logistic Regression is one Neuron Neural Net

CREDIT RISK MODELING


Current Banking Practice
Use regression techniques to derive a model relating the input
risk factors and a credit decision
The estimated coefficients in the Regression Model are used to
derive the weights in a credit scorecard
Use historical data for model derivation
Modern AI-Based Practice
Use AI-Based Model (Neural Net, Rules, Hybrid) to derive a
model relating the input risk factors and a credit decision
AI-Based Model can detect complex patterns in data that humans
are unable to see. Also uses Historical data

NEURAL NET BUILDING BLOCK

xi

yi

Neuron is a building block of a Neural


Net
A neuron receives inputs via weighted
links from other neurons

Inputs

Outputs

Neuron

The inputs are processed according


to the activation function of the neuron
The outputs of a neuron are passed
to other neurons in the neural net

TYPES OF NEURONS IN A NEURAL NET

Output Neuron Sends signals


to the external environment in the
form of an encoded answer to the
problem presented

Output

Hidden
Input

Input Neuron receives


encoded information from the
external environment

Hidden Neuron allows


intermediate calculation between
inputs and outputs

TYPES OF NEURONS IN A NEURAL NET

Best known Neural Net for business application is


the Multi-layered Feed Forward Neural Net
(MFNN) with the Back Propagation Learning Rule
95% of the reported Neural Net Business
Applications utilize MFNN

HOW DO YOU TRAIN A NEURAL NET?

Neural Nets learns from examples


Weight
Output
Input
Nodes

Neurons

Link

Collection of examples is known as the training


set.
Training set must be prepared properly. Good
examples must be used.
Use as much relevant input as possible.
Training set must be a representative set.

Remove outliers in the data.


As examples from the training set are fed in the neural net, the weights
interconnecting the neurons evolve (learning process).
Objective of the learning process is to minimize the training error (difference
between the neural net output and the desired output supplied in the training set).

HOW DOES A NEURAL NET LEARN?


MFNN Learning

Each input pattern (Example: (xixn)) produce an output Ok


Each Neuron calculates output yj as follows:

x1
xi

yj = f (Net Input)
wji

yj

Where:

Net Input =

wji xi

I=1

xN

f = transfer function typically the

wjN

logistic function

For an output neuron Ok


Ok =

f (Net Input)
J

Net Input =
j=1

Vkj yi

HOW DOES A NEURAL NET LEARN?

The output Ok is compared to the desired output Dk found on


the training set.
Based on the discrepancy between the Neural net Output Ok
and the desired output Dk , the neural net weights are updated.
Weight update rules that minimizes the total average-squared
error (or SSE) are used.
For Back propagation learning, minimization techniques in
calculus are used to derive the weight update rules.
Convergence is achieved when calculated SSE is within the
tolerance limit.

SAMPLE NEURAL NET TRAINING


To approximate AND function
Assign weight to input links
Calculate Net Input
In the Net Input is greater than threshold
Then output = 1
Else Output = -1 (Transfer Function)

NEURAL NET MODELING STEPS

1. DATA PREPARATION

Identification of Input & Output Variables

Representative Data Acquisition

Data Remapping / Transformation

Removal of Outliers

Creation of a Training File

2.

MODEL GENERATION

3.

MODEL VALIDATION

4.

MODEL RETRAINING

Additional Training Data

Adding / Deleting Input Variables

Pruning Input Variables

ACTUAL NEURAL NET APPLICATION


IN BANKING & FINANCE
VISA International implemented an operational fraud detection system
based on a neural net
HSBC (Falcon Project) used neural nets for credit card fraud detection
Money transfers between New York and London banks are monitored to
detect possible money launderers using Neural Nets & other AI-Based
Models.
A lot of big banks worldwide have adopted Neural Nets as their
underlying technique in making credit decisions.
A lot of banks have used Neural Nets for validating bank signatures.
Finance companies have used neural nets for exchange rate forecasting,
derivative security pricing, future price forecasting, bankruptcy prediction
and stock performances and selection prediction.
Banks have used neural nets for Customer Relationship Management.

Thank You!

27-C Rufino Pacific Tower


Ayala Avenue cor V.A. Rufino St.
Makati City
Phone: +63 2 893-3963
Fax : +63 2 893-3824
www.vintasystems.com

You might also like