1. Russian Plekhanov University of Economics Customer-telecommunications company’s relationship simulation model (RSM), based on non-monotonic business rules approach and formal concept analysis method. Victor Romanov Roman Veynberg AlinaPoluektova
2. THE TC-COMPANIES HAVEPROBLEMS WITH CUSTOMER PROFILE FITTING Customer Satisfaction ChangeWave Research AT&T’s low churn rate – despite its relatively poor Very Satisfied rating and its high percentage of dropped calls Sprint/Nextel (35%) is second in terms of customer satisfaction, with Tmobile (23%) and AT&T (23%) lagging well behind. ChangeWave Research: April 27, 2010
3. FITTING SERVICES TO CUSTOMER PROFILE We propose: To increase profit, to hold clients and attract new ones TC-companies can use customers’ personal data and services data (customer’s consumption level) for service fitting to the consumption profile of specific customer. For discovery the uniform consumption profile groups of customers and business rules we propose to apply the Formal Concept Analysis Method for making specific services adjusted for each category of clients. To ensure operability in conditions when customer’s data may be incomplete or contradictory, extracted business rules should be considered within the frame of non-monotonic logic, and realized as defeasible theory rules.
4. Why business rules? Dynamic competition economy In big and medium business a lot of documents contain business rules. EDM new conception propose extract business rule as different component, This makes possible more easy update them It is difficult to find and change them
5. Business static void processLoanRequest(Borrower borrower, Loan loan) { System.out.println("Processing request from " + borrower.getName()); // Approve or reject the loan checkLoanConditions(borrower, loan); // Display the verdict if (loan.isApproved()) { System.out.println("==> Loan is approved :-)"); } else { System.out.println("==> Loan is rejected :-("); for (Object msg : loan.getMessages()) { System.out.println("==> Because " + msg); } } } /** * Check conditions on the borrower and the loan using hard-coded policies */ static void checkLoanConditions(Borrower borrower, Loan loan) { // Check maximum amount if (loan.getAmount() > 1000000) { loan.addToMessages("The loan cannot exceed 1,000,000"); loan.reject(); } // Check repayment and score if (borrower.getYearlyIncome() > 0){ int val = loan.getYearlyRepayment() * 100 / borrower.getYearlyIncome(); if ((val>=0) && (val<30) && (borrower.getCreditScore()>=0) && (borrower.getCreditScore()<200)) { loan.addToMessages("debt-to-income too high compared to credit score"); loan.reject(); } if ((val>=30) && (val<45) && (borrower.getCreditScore()>=0) && (borrower.getCreditScore()<400)) { loan.addToMessages("debt-to-income too high compared to credit score"); loan.reject(); } if ((val>=45) && (val<50) && (borrower.getCreditScore()>=0) && (borrower.getCreditScore()<600)) { loan.addToMessages("debt-to-income too high compared to credit score"); loan.reject(); } if ((val>=50) && (borrower.getCreditScore()>=0) && (loan.getAmount() > Business Logic Applications codes IT What business rule is Business rule is the assertion at the natural or formal language,which for each state of business system defines permissible decisions on business control
6. Business rules management system The sources where rules originated from Documents Applications The rules are stored and updated The rules are extracted and executed The rules are inserted Personell Processes Business Rule Management System User Applications Rules + Metadata Rules repository Rules Server
8. FormalConceptAnalysis Customers regarded as objects with their attributes - personal data, realty, employment positions may be named as CONTEXT. The FORMAL CONCEPT of customers is a collections (subset of) whole set of customers with their attributes set, such that each member of the collection has in common all attributes from this particular attribute set. Formal concept lattice may be used for visualization telecommunication company’s customer groups, that make possible for management assign to these groups corresponding set of discount options. Besides selecting the group of customers FCA method provide possibility by mean data mining approach extract new rules from customer database. Application of non-monotonic rules expands possibility taking in account not only strict implications, but also rules with fixed level of support and confidence.
9. The business rules formal definition At the theory level of first level logic (FOL) business rules have statement view IF-THEN and expresses logical consequence or implication. IF p, THEN q,where q – assertion named as consequent, describing decision which are offering in this conditions. p is a assertion, named as antecedent, which is describing state of business conditions IF(conditions), then(the list of actions), else(alternate list of actons).
13. The rules discovered The rules discovered by FCA look like this: different kind of if customers satisfy different conditions and for them different marketing actions are effective:
14. Rules quality criteria Let M – attribute set and G objects set. The rules are defined as the implication X⇒Y, whereX,Y ⊆ M, X Y =. The implication means that all objects of context which contain attributes X also contain attribute Y. That is in the situation X manager ought make decision Y. 3 conviction confidence lift support Is defined as supp(X Y)/ supp(Y) supp(X) Is defined as conf(X⇒Y)= supp(XY)/ supp(X) Conviction conv(X⇒Y)=1-supp(Y)/1- conf(X⇒Y) Supp=card(ψ(X)/card(G)) - is a rate of contextobjects K := (G,M, I), which contain attributes X
15. The rules discovered with confidence <100 % IFLoc_call AND Cons_mid AND Single THENAct2_eff (confidence = 80%) IFCons_midTHEN Act2_eff (confidence = 70%) IF Head THENAct3_eff (confidence = 67%) IF single AND Loc_callTHENAct2_eff (confidence = 62%) IFCons_lowTHENAct3_eff (confidence = 50%)
16. CONCLUSION: The formal concept analysis software, being applied to client data, shows, that action1 is efficient for “Head, medium income and medium consumption” category of clients; action2 is efficient for “male, student, low income, medium consumption and use smsms” category of clients ; action3 is efficient for “citizen, use international call, GPRS with high income and consumption” category of clients So, proposed approach transforms user data into TC-company’s services, fitted to customer profile and stimulate consumption increasing so as company’s profit