Real-time Transaction Audit and Monitoring

As more and more transactions are processed with less and less human intervention, it is essential to have intelligent audit and monitoring systems in place. Audit and monitoring business transactions occurs for various reasons;

• Regulatory compliance: laws and government regulations require certain controls imposed on business transactions, e.g., SarBox Sarbanes-Oxley Act Section 404, etc.
• Internal policies: Companies and organizations set out internal policies for management and marketing purposes.
• Fraud detection: Fraudulent claims are costly for healthcare and insurance industries. Early detection can be vital in reducing fraudulent claims. For more, please read Healthcare Fraud Detection.
• Risk management: Credit card payments have risk of being defaulted. Detecting early signs of default may prevent further credits.
• Verification: Transactions can be mistakenly processed. Verification can reduce mistakes and errors.
• Event monitoring: Detection of unusual events is important in various industries.
• Customer churn alert: detection of imminent customer churns.
• Intelligent precision marketing: Intelligent algorithms can detect cross-sell and up-sell opportunities automatically as customers select products.

Business Activity Monitoring (BAM) with Complex Event Processing (CEP)

Current generation Business Activity Monitoring (BAM) systems are limited to real-time visual dash boards. They are very much stone-age monitoring systems! They are not equiped with functions that can capture complex events described with complex rules.

RME-EP is a new generation expert system that combines the best of rule-based inference and predictive modeling. RME-EP changes the current notion of BAM. Incorporating rules with predictive models, it makes complex event processing (CEP) possible.

How predictive modeling can harness BAM?

Literally speaking, predictive models mean prediction of risky events! They can be developed to detect various risky events with high accuracy. In another words, predictive modeling can be used to identify potentially risky transactions. For example, neural network can be trained so that it can detect potentially fraudulent credit purchases, or to alert risky insurance applications to actuaries, and so on. StarProbe data miner supports powerful predictive modeling tools. Users can build models with the help of intuitive model visualization tools. StarProbe data miner comes with the following predictive modeling software programs;

• Predictive Neural Network
  Neural network is a predictive model which is based on the architecture of, say, our brains. Neural networks can be trained to predict both numerical risk levels and categorical risk classifications. It can predict rare events very well. For more, please read Neural Network.

• Decision Tree
  Decision tree is a predictive modeling technique which is based on recursive segmentation and probabilistic reasoning. It is primarily used to classify risk categories. StarProbe data miner supports prediction of statistical probability as well. For more, please read, Decision Tree Classifier.

• Rule Induction classification
  Rule induction is based on Hotspot Profiling. It builds predictive models based on profiles of risk hotspots. This is a technique that you will be very interested!

• Regression
  Regression develops mathematical predictive formulas for numerical information. Although limited for general modeling, it can be useful for developing segment-specific models.

RME-EP: Audit-rule Specification Language

RME-EP is a variant Rete engine. Rete engine is a de-facto industry standard technique for rule-based expert systems. RME-EP provides a very powerful rule-specification language which is based SQL-99. The following shows an example of BAM. It shows how new sales trends can be detected automatically and informed. Note that detecting new sales trends is not trivial tasks! It involves compex processing. The following RME-EP rules make it simple and easy!

// SALES TREND MONITORING;
// declare data types;
DECLARE ALL AS REAL  // set default types;
DECLARE sales.trend AS STRING;
DECLARE Region AS STRING;
DECLARE Channels AS STRING;

// RULES;
RULE 1: // if sales droped over 5% with correlation coefficient 0.3 and over;
IF TIMESERIES(RR, LINEAR, 1, Month1, Month2, Month3, Month4, Month5, Month6) > 0.3 
     AND TIMESERIES(GROWTH_RATE, LINEAR, 1, Month1, Month2, Month3, Month4, Month5, Month6) < -0.05 
  THEN SET sales.trend AS 'declining' END;

RULE 2:  // if sales increased over 15% with correlation coefficient 0.3 and over;
IF TIMESERIES(RR, LINEAR, 1, Month1, Month2, Month3, Month4, Month5, Month6) > 0.3 
     AND TIMESERIES(GROWTH_RATE, LINEAR, 1, Month1, Month2, Month3, Month4, Month5, Month6) > 0.15 
  THEN SET sales.trend AS 'increasing' END;

RULE 3: // alert if something detected;
IF sales.trend IS NOT NULL 
   THEN THROWEVENT('alert', Region, Channels, sales.trend) END;

For more information, please write to us.