Question

How would banks use neural networks with sas miner?

Answer 1

Neural Network with SAS Miner in Banks

Neural Networks are used for image recognition and natural language processing which means that it is mainly used for deep learning application. The main area which uses neural networks are finance, marketing, and insurance domain.

It also supports SAS as a preferred language in regulated environment like finance or clinical trials.

Neural Networks works like a human brain that is it is a series of algorithm that endeavours to recognise underlying relationship in a set of data through a process that mimics the way the human brain operates. It is a system of neurons which maybe organic or artificial in nature.

A simple neural network has the following structure.

1. Input Layer

2. Hidden Layer

3. Output Layer

Neural Network in finance field assist in the development of time-series forecasting, algorithmic trading, securities classification, fraud detection, credit risk modelling, proprietary indicators and price derivatives.

The network bears a strong resemblance to statistical methods like curve fitting and regression analysis.

The Neural Network with SAS miner which is mainly used in financial sectors like banking, trade, marketing etc.

In Banks, they provide loans to the customers based on different category. In such situations, the neural networks play whether the customer is eligible for loan or the loan may be rejected. The bank mainly thinks the minimal failure rate of loan application and maximize the return on the loan issued. The failure rate of loan approved using neural network has been observed to be lower than that of some of their best traditional methods

Also, some credit card providers use this neural network to decide to grant an application by using the method of analysing the past failure and making the current decision based upon their past experience.

Here the neural network with SAS miner is very effective because it provides the data mining process to create a highly accurate predictive and descriptive models based on the vast amount of data from the Bank.

They have some of the steps for SAS miner.

1. Sampling Techniques.

2. Variable selection.

3. Model selection.

4. Logistic regression.