Transaction Audit and Event 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.

How to develop audit rules?

Audit rules often exist naturally, e.g., stipulated by laws, internal policies, etc. In addition, rules may be extracted from past data. Profiling past violations using hotspot analysis can produce rules that can be used in auditing. By examining sample violation cases manually, rules may be extracted. In addition, predictive modeling described in the next section can further enhance auditing capabilities.

How predictive modeling can harness auditing?

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.

Decision tree classification predictive modeling. Neural network predictive modeling.

The Audit-rule Specification Language

Predictive modeling is powerful and versatile in predicting events. However, predictive modeling alone cannot describe real world events. More real world events can be described using rules and formulas than predictive models. Rule-based modeling incorporates three into a single paradigm: rules, mathematical formulas, and predictive models. More specifically, rules and mathematical formulas can be written with predictive models. This renders very powerful audit-rule specification language environment. The following example coded rules demonstrate the expressive power of the audit-rule specification language;

    // expressing logistic regression function;
    RETURN  // classification based on logistic regression;
       CASE 5.0 / (1.0 + EXP(2.5 + 0.4 * X))
        WHEN < 1.5  THEN 'Low risk'
        WHEN < 3.5  THEN 'Average risk'
        WHEN >= 3.5 THEN 'High risk'
       END ;

    // complex rules with predictive models;
    IF MIN(AVG(MODEL(Default1), MODEL(Default2)), // minimum of averages
               AVG(MODEL(Default3), MODEL(Default4))) > 0.25 THEN
         RETURN MIN(MAX(MODEL(Default1), MODEL(Default2)), 0.3)
    END ; // maximum.

    // if any one predicts as 'Risky', it returns average probability;
    IF 'Risky' IN (PREDICT(tree1), PREDICT(tree2), PREDICT(tree3)) 
       THEN RETURN AVG(PREDICT(tree1, 'Risky'), PREDICT(tree1, 'Risky'), 
                    PREDICT(tree3, 'Risky')) // returns average probability
    END ;

How to implement audit and monitoring rules?

Audit rules can be implemented in a number of ways. One way is to embed it into your auditing software programs. StarProbe Rule-based Modeling Environment (RME) is a package developed in Java. It can be embedded into any Java-based programs. Another way is to use web-based services as described in the following section.

Fully ready for SOA and Web Services

Audit and monitoring can be implemented in various ways using SOA (Service Oriented Architecture) and Web Services. Typical implementation methods are as follows;

  • SOAP : This is an industry standard for delivering services over the web in a platform neutral manner. Audit models can be called from any software program on any platform in a secure manner.
  • Servlets and JSPs : Servlets and JSP pages can use pre-embedded packages to deliver models over the web-browsers.
  • XML : Data can be exchanged using XML formats.
audit and monitoring on web.

The following is an example of web deployment;
audit and monitoring on web.

Cost effective and Secure delivery of Services

StarProbe RME and Webkit provides cost-effective secure delivery of auditing solutions. StarProbe data miner supports predictive model and audit-rule development, testing, and validation. Using the Webkit, audit models can be deployed on a secured web server. This will ensure secure services quickly!

For more information, please write to us.