Rosella       Machine Intelligence & Data Mining

  Home | Data Mining/Machine Learning | MyDataSay/Android | BI Server | Products & Downloads | Site Map | Contact/Sales |

Rule Engine with Machine Learning, Deep Learning, Neural Network

Rule Engine and Machine Learning are often viewed as competing technology. But this view is not correct. Rule Engine and Machine Learning can be incorporated together to become a very powerful platform. For example, Deep Learing refers structured multiple neural network models. Rule Engine can be used to glue multiple neural networks to work as a single powerful model seamlessly, thus implementing structured neural networks which are Deep Learning Models.

RME-EP (Rule-based Model Evaluation with Event Processing) is a very powerful expert system shell rule engine, incorporating predictive modeling by machine learning algorithms, such as neural network, self organizing maps, decision tree, regression, time series, statistical functions, and so on. It combines rule based "forward-inference" reasoning with predictive modeling by machine learning. It provides a powerful platform for structured Deep Learning.

SQL-like Rules for Business users

RME-EP has been developed to use SQL-like expressions which can be learnt by business users and domain experts very easily and quickly. Non-IT professional users can write RME-EP expert system rules by themselves without IT professional help. RME-EP opens a new era for business users and domain experts. Note that SQL users can learn RME-EP very quickly!

The popularity of SQL as the preferred database query language has been largely due to the natural intuitiveness of the language as well as the richness of logical expressions. SQL is very easy to learn. Expressions written in SQL is very easy to understand and hence has been widely used by many non-IT professional such as business analysts and users, as well as by IT professionals. RME-EP is based on SQL-99 syntax supporting most logical and arithmetic language features.

Predictive Modeling by Machine Learning for Deep Learning

The core concept of RME-EP is Rule-based (Predictive) Model Evaluation. RME-EP incorporates predictive models with many logical and mathematical functions of SQL-99. By incorporating advanced predictive models into rule engine, RME-EP provides a superb platform for advanced rule-based expert systems and deep learning. RME-EP supports the following machine learning based predictive models;

  1. Neural network: Neural network is a very powerful predictive modeling technique. CMSR/RME-EP provides neural modeling tools which are robust and intuitive but still easy to use. Neural network can be used to predict numerical scores as well as classifications.
  2. Neural Clustering: Neural clustering also known as Self Organizing Maps (SOM) is a very powerful clustering and segmentation method. When combined with neural network, it renders very poweful Radial Basis Functions.
  3. Decision tree: Decision tree is primarily used for classification task. In addition, CMSR decision trees can also predict statistical probability of events.
  4. Regression: Regression is widely used technique by statisticians. It can predict numerical scores.
  5. Time-series analysis: RME-EP has built-in time-series regression functions. It can develop best regression functions based on RME-EP fact working sets.

(Example) Deep Learning Risk Modeling by Rule Engine and Machine Learning

The following is a RME-EP Deep Learning style example for risk scoring. This is an extension of predictive modeling by machine learning described in the following links;

The following figure shows the deep learning process of this example model;

Deep Learning Model

Note that this RME-EP model uses five neural network models: Model1, Model2, Model3, Model4 and Model5. Model1, 2 and 3 evaluate input data. Model4 and 5 are used to integerate results of Model1 ~ 3.

In the begining, variables are declared. Rule 1, 2 and 3 evaluate first three models and store on variables "Model1 score", "Model2 score", "Model3 score", respectively. Rule 4, then, computes maximum, minimum and average values of these three models. Rule 5 and 6 evaluate second tier integration models "Model4" and "Model5", using three model output values plus maximum, minimum and average values. Final result scores will be averaged and stored on "Final average". Based on "Final average" and Max/Min/Avg values, risk levels are verbalized by Rule 8 and 9.

It is noted that this model incorporates neural network and decision rules as a single RME-EP model. It is a decision support expert system on a model. The following is a screenshot of of this deep learning model output on MyDataSay Android Application. MyDataSay download has this model. You can download from the link. Note that RME-EP is a feature of CMSR Data Miner / Machine Learning Studio, you can download and try this model with CMSR Data Miner / Machine Learning / Rule Engine Studio. Downloads contain more advanced sample models.

Deep Learning Model

The following is a coding of this model. More advanced demo model is available from CMSR Data Miner / Machine Learning / Rule Engine Studio download.

/*
 * This model is an example of deep learning. Three neural models  are 
 * evaluated. Then maximum, minimum and average of three neural network 
 * outputs are computed. Then, these six values are fed to Model4 and 
 * Model5 models to produce final scores. Then final average of final scores
 * is computed. Finally, final average as well as max/min/avg values are used to 
 * classify into verbal class names.
 *
 * Model4 and Model5 are trained as follows;
 *   1. Create a temporary RME-EP model that computes scores of three
 *       models. And maximum, minimum and average values of three neural models.
 *   2. Apply to training dataset database table.
 *   3. Import the updated database table into CMSR.
 *   4. Create and train integration models Model4 and Model5
 *       using outputs of three model values, maximum, minimum, averages 
 *       with RISKFLAG as target.
 *   5. Combine into this model.
 * 
 */

// declare runtime options;
DECLARE OPTIONS EXPLICIT,ERRORNULL,MAXFIRE(0);
// DECLARE OPTIONS USEBETWEEN('2017-1-1', '2017-12-31');

// define input data fields and values in appearing order;
DECLARE Gender AS STRING INPUT VALUES IN GENDER OF Model1;
DECLARE Race AS STRING INPUT VALUES IN RACE OF Model1;
DECLARE Jobpost AS STRING INPUT VALUES IN JOBPOST OF Model1;
DECLARE CLASSIFICATION1 AS STRING INPUT VALUES IN CLASSIFICATION1 OF Model1;
DECLARE EDUCLEVEL AS STRING INPUT VALUES IN EDUCLEVEL OFModel1;
DECLARE AGEGROUP AS STRING INPUT VALUES IN AGEGROUP OF Model1;
DECLARE Salary AS INTEGER INPUT;

// define output fields in appearing order;
DECLARE "Model1 score", "Model2 score", "Model3 score" AS REAL OUTPUT;
DECLARE "" AS STRING OUTPUT INITIAL VALUE '';
DECLARE "Maximum score", "Minimum score", "Average score" AS REAL OUTPUT;
DECLARE " " AS STRING OUTPUT INITIAL VALUE '';
DECLARE "Final score1", "Final score2", "Final average" AS REAL OUTPUT;
DECLARE "  " AS STRING OUTPUT INITIAL VALUE '';
DECLARE "Risk level", "Risk level (MMA)" AS STRING OUTPUT;

/*
 * DATA MODEL EVALUATION
 */

RULE 1: // evaluate model 1;
IF TRUE THEN
	SET "Model1 score" AS PREDICT(Model1) USING(
		GENDER AS Gender,
		RACE AS Race,
		JOBPOST AS Jobpost,
		CLASSIFICATION1 AS CLASSIFICATION1,
		EDUCLEVEL  AS  EDUCLEVEL,
		AGEGROUP AS  AGEGROUP,
		SALARY AS Salary
	) 
END;

RULE 2: // evaluate model 2;
IF TRUE THEN
	SET "Model2 score" AS PREDICT(Model2) USING(
		GENDER AS Gender,
		RACE AS Race,
		JOBPOST AS Jobpost,
		CLASSIFICATION1 AS CLASSIFICATION1,
		EDUCLEVEL  AS  EDUCLEVEL,
		AGEGROUP AS  AGEGROUP,
		SALARY AS Salary
	) 
END;

RULE 3: // evaluate model 3;
IF TRUE THEN
	SET "Model3 score" AS PREDICT(Model3) USING(
		GENDER AS Gender,
		RACE AS Race,
		JOBPOST AS Jobpost,
		CLASSIFICATION1 AS CLASSIFICATION1,
		EDUCLEVEL  AS  EDUCLEVEL,
		AGEGROUP AS  AGEGROUP,
		SALARY AS Salary
	) 
END;


/*
 * COMPUTE MAXIMUM / MINIMUM / AVERAGE
 */

RULE 4: // compute max/min/avg;
IF TRUE THEN 
{
	SET "Maximum score" AS MAX("Model1 score", "Model2 score", "Model3 score");
	SET "Minimum score" AS MIN("Model1 score", "Model2 score", "Model3 score");
	SET "Average score" AS AVG("Model1 score", "Model2 score", "Model3 score");
}
END;


/*
 * EVALUATE INTEGRATION NETWORKS
 */

RULE 5: // evaluate model 4;
IF TRUE THEN
	SET "Final score1" AS PREDICT(Model4) USING(
		Model1Score AS "Model1 score",
		Model2Score AS "Model2 score",
		Model3Score AS "Model3 score",
		MaximumScore AS "Maximum score",
		MinimumScore  AS  "Minimum score",
		AverageScore AS  "Average score"
	) 
END;

RULE 6: // evaluate model 5;
IF TRUE THEN
	SET "Final score2" AS PREDICT(Model5) USING(
		Model1Score AS "Model1 score",
		Model2Score AS "Model2 score",
		Model3Score AS "Model3 score",
		MaximumScore AS "Maximum score",
		MinimumScore  AS  "Minimum score",
		AverageScore AS  "Average score"
	) 
END;


/*
 * COMPUTE INTEGRATION MODEL AVERAGE
 */

RULE 7:  // compute average of final scores
IF TRUE THEN 
	SET "Final average" AS AVG("Final score1", "Final score2")
END;


/*
 * FINAL CLASSIFICATIONS
 */

RULE  8:   // classify risk levels with final average;
CASE  
WHEN "Final average" >= 0.7 THEN 
	SET "Risk level" AS 'Very high risk'    
WHEN "Final average" < 0.01 THEN 
	SET "Risk level" AS 'Low risk'    
WHEN "Final average" < 0.1 THEN 
	SET "Risk level" AS 'Medium risk'

WHEN "Maximum score" >= 0.6 OR "Minimum score" >= 0.2 OR "Average score" >= 0.5 THEN 
	SET "Risk level" AS 'Very high risk'    
WHEN "Maximum score" >= 0.3 OR "Minimum score" >= 0.05 OR "Average score" >= 0.2 THEN 
	SET "Risk level" AS 'High risk'    
WHEN "Maximum score" >= 0.2 OR "Minimum score" >= 0.0 OR "Average score" >= 0.1 THEN 
	SET "Risk level" AS 'Medium risk'    
ELSE 
	SET "Risk level" AS 'Low risk'   
END;

RULE  9:   // classify risk levels without final average;
CASE  
WHEN "Maximum score" >= 0.6 OR "Minimum score" >= 0.2 OR "Average score" >= 0.5 THEN 
	SET "Risk level (MMA)" AS 'Very high risk'    
WHEN "Maximum score" >= 0.3 OR "Minimum score" >= 0.05 OR "Average score" >= 0.2 THEN 
	SET "Risk level (MMA)" AS 'High risk'    
WHEN "Maximum score" >= 0.2 OR "Minimum score" >= 0.0 OR "Average score" >= 0.1 THEN 
	SET "Risk level (MMA)" AS 'Medium risk'    
ELSE 
	SET "Risk level (MMA)" AS 'Low risk'   
END;

For more and software downloads, read CMSR Data Miner / Machine Learning / Rule Engine Studio.