Apparatus and product of manufacture for generating a probability value for an event

1. A non-transitory computer-readable medium that stores a program that causes a processor to perform functions to generate a probability value for an event by executing the following steps:

receiving a plurality of input signals at a first processor, plurality of input signals generated from a source;

submitting the plurality of input signals to a multilayer perceptron operating on a first processor to generate a plurality of raw scores;

sorting at the first processor the plurality of raw scores by similar values;

calibrating at the first processor a first half of the plurality of raw scores with similar values to generate a probability value that an event will occur;

validating at the first processor the probability value that the event has occurred with actual data;

validating at the first processor a second half of the plurality of raw scores with similar values at the multilayer perceptron to determine if the probability value is correct; and,

generating at the first processor a graph of the probability value versus time on a graphical display;

wherein the plurality of digital input signals comprises at least one of a value for a fraudulent credit card transaction, a value for a monthly salary income for the loan applicant, a value for monthly rental income for the loan applicant, a value of a collateral for the loan, a value for a monthly car payment for the loan applicant, or a value of a number of years employed for the loan applicant.

2. The non-transitory computer-readable medium according to claim 1 wherein the multilayer perceptron comprises a plurality of inputs, a plurality of hidden nodes and a single output.

3. A system for generating a probability value for an event, the system comprising:

a source for generating a plurality of digital input signals;

a processor connected to the source to receive from the plurality of digital input signals from the source; and

a graphical display connected to the processor for displaying a final output;

wherein the plurality of digital input signals is submitted to a multilayer perceptron at the processor to generate a plurality of raw scores;

wherein the processor is configured to sort the plurality of raw scores by similar values;

wherein the processor is configured to calibrate a first half of the plurality of raw scores to generate a probability value that an event has occurred;

wherein the processor is configured to validate the probability value that an event has occurred with actual data of an event;

wherein the processor is configured to validate a second half of the plurality of raw scores with similar values from the multilayer perceptron to determine if the probability value is correct;

wherein the processor is configured to generate a display of the probability value versus time on the graphical display;

wherein the plurality of digital input signals comprises at least one of a value for a fraudulent credit card transaction, a value for a monthly salary income for the loan applicant, a value for monthly rental income for the loan applicant, a value of a collateral for the loan, a value for a monthly car payment for the loan applicant, or a value of a number of years employed for the loan applicant.

4. The system according to claim 3 wherein the multilayer perceptron consist essentially of a plurality of inputs, a plurality of hidden nodes and a single output.

5. A non-transitory computer-readable medium that stores a program that causes a processor to perform functions to determine a probability value for an event by executing the following steps:

generating a plurality of training set inputs from a machine comprising a source, a processor and a user-interface;

submitting the plurality of training set inputs to a recognition algorithm to generate a raw score;

calibrating the raw score to generate a probability value that an event will occur;

validating a set to test; and

generating probability values against data submitted for analysis.