How The Predictive Analytics-based Framework Helps Reduce Bad . - WNS

1y ago
788.70 KB
12 Pages
Last View : 25d ago
Last Download : 7m ago
Upload by : Camden Erdman

WNSExtending Your EnterpriseHow a Predictive Analytics-basedFramework Helps ReduceBad Debts in Utilities

WNSExtending Your EnterpriseBad Debt Write-offs — BusinessTrade-off or Survival Tactic?For the past few years, utilities have relinquishedhundreds of thousands of dollars in consumer baddebts. Customer defaults continue to rise in anenvironment speckled with rising levels ofunemployment, economic uncertainty and dippingconsumer spends. A spate of stringentgovernment regulations — to protect customerrights, reduce environmental impact and improvesafety compliance — do not make it any easierfor the utilities business to thrive. To makematters worse, unscrupulous consumers continueto exploit loopholes in the utility's businessprocesses to default on their payments.Bad debts force utilities to trade off profits forsurvival. When towing the line between baddebts, failed collections efforts and a stringentregulatory environment, utilities are forced to takethe 'write-off' route even if it means giving up onthe revenue they rightly gent Govt.RegulationsRising Levels ofUnmemploymentFig.1: The typical maze of challenges that utilities have to grapple with.Little wonder then, that, write-offs have risenfrom approximately USD 400 Million in 2008 toabout USD 2.8 Billion in 2014, as reported by aleading strategy consultancy firm, PA Consulting,in its recent customer service benchmarking data.In such an environment laden with constraints,how can your utility company effectively minimizebad debt write-offs?This whitepaper puts forth the answers to thiscritical question.01 wns.comUtilities can reduce their bad debts significantlyby adopting the 'integrated three-pronged revenueprotection strategy' that focuses on:nIdentifying high-risk customers;nRevising collections tactics targeted towardsthe high-risk customer segment; andnImproving customer interactions andexperience interventions.

How a Predictive Analytics-basedFramework Helps Reduce Bad Debts in UtilitiesThe customer occupies a central position in thisstrategy — analyzing, understanding andpredicting customer behavior becomes central toits success. The level of customer understanding,required for this three-pronged framework, isenabled only by predictive analytics. Predictiveanalytics is an advanced form of data analyticsthat utilizes a large number of variables based onboth internal and external data sources andleverages advanced statistical tools as well asspecialized analytical techniques to predict likelyfuture outcomes.Predictive analytics lays the foundation to thisstrategy by helping identify high-risk customerbehavior and in enabling the implementation ofcollections strategies targeted towards high-riskcustomer segments.PREDICTIVE ANALYSISPREDICTIVE ANALYSISTargeted CollectionStrategiesEnhanced CustomerSatisfaction InterventionsIdentifying High-RiskCustomersFig.2: Predictive analytics lays the ground for an effective bad debt minimization strategy.Predictive Analytics forIdentifying High-riskCustomer BehaviorWith the risk of bad debts looming large, utilitycompanies cannot afford to follow a one-schemefits-all policy for managing customer defaults.Most utilities charge their customers on a 'credit'basis, that is, after the use of the service.Reliance on credit payment is not ideal for allcustomer categories, as customers tend to misusethis option. Utilities should first make efforts toidentify and classify customers (both existing andnew) into high- and low-risk segments and thendevelop targeted strategies to securitize revenuefrom high-risk customer 02

WNSExtending Your EnterprisePredictive analytical models that assess risksduring the onboarding of new customers useprofile parameters such as income levels,demographics, and credit history. Most utilitieshave stringent SOPs for evaluating new customerapplications; however, they often overlook riskslurking within existing customer accounts. Risksin existing customer accounts can be identifiedby analyzing additional information, such as,customer meter settings, usage patterns, paymenthistory, and complaints and communication.NEW CUSTOMERnIncome LevelsnDemographicsnCredit HistoryEXISTING CUSTOMERnCustomer Meter SettingsnUsage PatternsnPayment HistorynComplaints and CommunicationFig. 3: Profile parameters to identify risks vary between new and existing customer accounts.Customers, who find it difficult to pay their utilitydues, usually request for negotiation of paymentterms and credit extensions from their utilityproviders. However, there are instances wherecustomers default even after such options areprovided and may opt for unscrupulous practicesto escape payment. Some may pose as 'new'customers and apply to the utility company for anew account, while some may move to newaddresses frequently, without informing theirutility suppliers. Although most utility companiesask for information on the account holder's name,the Social Security number, and / or tax ID,individuals resorting to the 'name game' concealthese bits of information that can prove their03 wns.comlinks to other accounts. Utility companies thatfail to identify customers with prior trailing dues,run into the cycle of customer defaults, bad debtsand the resultant losses.Predictive data analytics helps identify fraudulentcustomers that have 'trailing' debts and mayresort to 'name game' tactics to get away withoutpaying their dues. The segment of potentialdefaulters can be further expanded by includingmore parameters such as customer profile andcredit rating data from credit bureaus namelyEquifax, Experian, and TransUnion. Identifyinga larger number of customers under the ambitof potential defaulters further minimizes the riskof delinquencies.

How a Predictive Analytics-basedFramework Helps Reduce Bad Debts in UtilitiesVendors with expertise in data management (datacollection, cleaning, preparation and analysis)can effectively assist utility companies preventrevenue leakage by spotting aliases andcustomers with high attrition risk.A proven predictive analytics model is one thatallows utilities to segment customers based ontwo parameters — the debt value the customerowes, and the propensity to pay back the debt.By plotting the outstanding dues on the x-axisand the propensity to pay back the debt on they-axis, utilities can create a collectionsprioritization matrix (as shown in fig. 4) to decideon the next steps in the collections strategy.Outstanding DuesMediumHighDo NothingDo NothingSteady Follow-upMinimal CollectionsEffortsSteady Follow-upStrict Follow-upMinimal CollectionsEffortsStrict Follow-upAccelerated CollectionEffortsMediumHighPropensity to Pay BackLowLowFig.4: Sample collections prioritization matrix prescribing 'collections' steps to be taken.This novel approach in segmentation on the basisof the customer's propensity to pay back the debtprovides new insight for the debt collectionstrategy. As shown in fig. 4, customer accountswith high outstanding and propensity to pay areprioritized for accelerated in-house collections.On the other hand, a lower outstanding amountand propensity to pay accounts are written-offimmediately as the effort and cost-to-collect thedebt, exceeds the debt due on the customeramount.Proactive action upon identification of high-riskcustomers can help reduce bad debt write-offs byas much as 40 percent and securitize revenuesfor utility 04

WNSExtending Your Enterprisetelephony infrastructure that help them improveoutbound contact center performance.Predictive Analytics-drivenTechnology for RevampingCollections TacticsAn efficient collections strategy aims to improvethe collections rate and minimize the cost- andeffort-to-collect. The collections process follows a'dunning path' during which the utility companyfollows up the customer to pay up theoutstanding amount. If such efforts fail or end inno recovery after a certain period of time, thecustomer account is placed under a DebtCollection Agency (DCA). The average recoveryrates for DCAs vary within 10-15 percent acrossprimary, secondary and tertiary placements,depending on the region. The averagecommissions are in the range of 25-50 percent,based on the age of the debt. In scenarios whereall debt accounts are transferred to DCAs,collection costs tend to become exorbitant. Thus,most utility companies have an internal debtmanagement and collections team focused onearly-stage delinquent accounts.Most collections focused contact centers deploystate-of-the-art information technology andThe two most commonly deployed forms ofautomation in a collections contact center arethe 'Predictive Dialer' and 'Computer TelephonyIntegration' (CTI).Predictive dialers that operate on the principlesof predictive analytics, measure the number ofavailable agents, available lines, and average callhandling time to improve resource utilization.The predictive dialer has the capability toautomatically call a list of telephone numbers insequence, screening out no-answers, busysignals, answering machines and disconnectednumbers while predicting possible points atwhich a human caller will be able to handle thenext call.CTI in turn, links the dialer with the customerinformation system to disseminate customeraccount information to collection agents. Itessentially displays the propensity rank (based onanalytical modeling) of the customer along withthe collections strategy, helping agents, tailortheir conversation, offer advice and re-structurepayment methods, as shown in fig. 5.Outstanding Dues (in )HighMediumHHCollectionMHTips:nnLowPropensity to Pay BackHighMediumLowHMHLMMMLHigh Value Customer - Deal RespectfullyRecover Full Outstanding - Do not offer part settlementuntil debt 3000K on the customer accountnMaximumLHrepayment tenure is 60 monthsLMnRetain customerLLFig.5: A sample CTI screenshot, showing collection tips generated for the collections agent.05

How a Predictive Analytics-basedFramework Helps Reduce Bad Debts in UtilitiesOne very effective way to check paymentdelinquencies is to employ a cut-off credit scorefor onboarding new customers.Many utility companies set this threshold limit atlow levels to ensure that marginal consumerscontinue to receive their services without needingto pay a deposit. By simply raising this limit,utilities can increase the number of customersthat are required to pay a deposit. Thoughconsumer protection regulations vary betweenstates in the UK, nearly all states allow utilitycompanies to ask for a security deposit fromhigh-risk customers.The deposit amount can be customized to suitcustomized specific customer demographicswithout harming the revenue-generating potentialof the utility company. For instance, utilitycompanies can determine the deposit amountbased on the tariff structure, payment trackrecords, and the disconnection history of acustomer. Pre-payment meters offer an effectiveoption to check debt pile-up on a delinquentcustomer account.Traditionally, utilities follow the route ofconverting customer accounts in debt to prepayment meters only after the account exceeds acertain debt threshold value or if it remains indebt for long. A smarter strategy would be toproactively promote pre-paid meters to theidentified segment of high risk customers beforethe first instance of default occurs. This strategyhelps protect revenue and reduces the resourcesand efforts spent on debt collections.A combination of these tweaks and changes leadsto improved collections performance and reducedbad debt on customer accounts.The first two steps of this revenue protectionframework focus on predictive analytics tools,technology and models. The third stepconcentrates on improving customer interactionsand experience and works in tandem with thefirst two steps.Improving CustomerInteractions and ExperienceFor most consumers, paying off utility bills,figures as the last of their 'payment priorities', incomparison with insurance, video-DTH rentals,and telephone bills. Since, electricity, gas andwater are considered essential life services, utilitycompanies cannot disconnect services tocustomers who have not paid their bills, forrecovery of debts.Despite the pressing need to recover revenuefrom defaulting customers, utility providers needto be mindful of customer satisfaction andexperience. After all, customer satisfaction laysthe foundation to retain market share amidstincreasing competition.Maneuvering between a rigorous collectionsstrategy and ensuring a high customersatisfaction index at the same time can be tricky.However, it is not impossible.A blend of appropriate advisor knowledge, utilitycollections experience, empathy towardscustomers in financial distress and compliance toconsumer protection regulations can increasecollections success and at the same time create abase of satisfied customers.A knowledgeable customer service advisor has theright orientation needed to understand thecustomer and industry dynamics. This orientationcomes from rigorous trainings on evaluation ofthe customer's situation and the ability to showempathy by offering financial advice or flexiblerepayment modes to suit the customer's profile.With such interventions customers usually openup to the prospect of discussing differentpayment options before entering into a promise topay back the debt. This improves customercommitment to honor agreed payment schedulesand reduces effort in the collections 06

WNSExtending Your EnterpriseFurther, as utilities operate in a regulatedenvironment, they need to comply with consumerprotection guidelines of the state. Theseregulations pertain to customer interaction, modeof collecting debt, identification of inability topay, treatment of customers on social tariffs, andprotection of vulnerable customers. Noncompliance invites harsh penalties. Utilities areresponsible for the actions of DCAs who collectthe debt from customers on their behalf. Inrecent times, there has an increase in the numberof complaints to the Office of Gas and ElectricityMarkets (OFGEM) about aggressive debtcollection practices. This puts additional pressureon utilities to re-evaluate their current debtcollection mechanism and put in place a systemto govern DCA performance.07 wns.comIt is advisable to strike a balance betweenproactive collection steps to address customerdelinquency and adherence to consumerprotection regulations.Optimizing the debt collection process showssignificant positive results within a short period ofimplementing a pilot process based on the abovediscussed three-point framework. Consumerdelinquency management methods have thepotential to reduce losses incurred by utilitycompanies by as much 50 percent. What's more,the payoff is much higher than investment andsustainable in the long run.

How a Predictive Analytics-basedFramework Helps Reduce Bad Debts in UtilitiesHow One of the Leading Utility CompaniesIncreased its Debt Collections by 50 Percentin 3 Months with Predictive AnalyticsThe ClientnCustomer segment prioritization for outboundcontact. Customer segments were prioritized onthe basis of the propensity-to-pay scores andthe amount of outstanding debt.nRigorous cost-benefit analysis to streamlineoperational, financial, and human resourceactivities. This exercise would go on tooptimize the debt management process.nInbound and outbound test strategyimplementation to engage customers.The customer service executives used thecustomized call scripts and pre-determinedverbiage to carry out settlement negotiationswith and provide debt management adviceto customers.nPerformance monitoring of pilot strategiesregularly against critical tactical and qualityindicators and also against the parameters setby the champion process.A Leading Energy and Utilities CompanyThe ChallengeThe client wanted to better manage its energyfinal debt portfolio. Its debt recovery rate was at4 percent, compared to the 14 percent achievedby its competitors. On the other hand, thecommissions charged by the client's debtcollection agencies were as high as 50 percent ofthe collected amount that kept the operationalcost-to-collect very high. This made dents in theprofit margins of the client. The client wanted tooptimize its final debt collection processes toimprove recovery of receivables. The client alsowanted to formulate focused debt managementstrategies for different customer segments tomanage customer write-offs more effectively andin the process decrease operational costs.The WNS SolutionWNS concentrated on transforming the client'scollections process by embedding predictiveanalytics and making changes to the customerinteraction strategy. Key aspects of theWNS solution were:nnnBenefits DeliveredBy using predictive analytics to carry outpropensity based customer segmentation andenforcing customized engagement and advisorypolicies for different customer segments, WNSwas able to fulfill the business objectives of theclient. The WNS solution achieved the followingresults for the client:Propensity-to-Pay predictive data modelexclusively for residential customers. Thismodel predicted the likelihood of customersbeing able to pay their dues after theiraccounts were finalized. The model assigned apropensity-to-pay score to every customer.nDebt collection increased by 50 percent within3 monthsnCustomer classification into high, medium, andlow propensity-to-pay segments based ontheir scores.The challenger process recorded an 8 percentrise in conversion rates compared to thechampion processnOperational expenses decreased by 20 percentFocused delinquency management strategiesfor every segment.Thus WNS helped the client optimize itscollections process by bringing in actionableinsights using predictive 08

WNSExtending Your EnterpriseGathering Business IntelligenceDefining Program StatementImpact assessmentReduce customer effort bystreamlining processesDefiningContext forGrowthROI projectionLearning best practicesfrom diverse tionRevenuePromoter IndexKnowledgeManagementPeriodic model treatmentfor relevancyReal-time model assessment bychampion / challenger strategiesContinuous Improvementthrough InnovationCost toCollect lding Productivemodels and VisualizationsEmbeddingAnalyticsDrawing data drivenconclusionsDesigningStrategiesAnalytics based tailor-made processimprovements (based on customersegmentation and risk score)End-to-end service architecture toachieve business outcomesFig. 6: The framework used by WNS to transform the client's collections processReduction in Days Sales OutstandingFinancialBenefitsIncrease in Top-Line RevenueImprovement in Credit RatingsCompliance with Regulatory GuidelinesImprovement in Customer Relationsand Market StandingReputationManagementFigure 7: The Benefits of Reducing Consumer Bad Debt Write-Offs in the Utility Industry09

How a Predictive Analytics-basedFramework Helps Reduce Bad Debts in UtilitiesConclusionReducing consumer bad debt write-offs hasseveral benefits in the utility industry. Thesebenefits have a positive effect on the day-to-dayoperations of the company and also impact itsreputation in the market along withstakeholder relations.Predictive analytics has emerged as a key enablerthat helps segment customers into identicalgroups based on their attributes and formulatecustomized debt management and advisorypolicies targeted to a particularcustomer segment.Utility companies need to reduce instances andvolumes of consumer bad debt write-offs to staycompetitive in a dynamic economic environment.What's more, they need to achieve this goal in theface of continuing challenges—shrinking incomelevels of consumers, stringent regulatoryguidelines, and pressure from shareholders tooptimize performance and returns on investment.Targeted strategies assure better performance andacceptance with the customer segment and helpsreduce consumer bad debt write-offs and driveseveral significant business benefits, byimproving customer satisfaction 10

Copyright 2015 WNS Global Services I wns.comAbout WNSWNS (Holdings) Limited (NYSE: WNS), is aleading global business process managementcompany. WNS offers business value to 200 global clients by combining operationalexcellence with deep domain expertise in keyindustry verticals including Travel, Insurance,Banking and Financial Services,Manufacturing, Retail and Consumer PackagedGoods, Shipping and Logistics and Healthcareand Utilities. WNS delivers an entire spectrumof business process management services suchas finance and accounting, customer care,technology solutions, research and analyticsand industry specific back office and frontoffice processes. WNS has its global deliverynetwork spread across China, Costa Rica, India,Philippines, Poland, Romania, South Africa,Sri Lanka, United Kingdom andthe United States.Write to us at marketing@wns.comto know moreWNSExtending Your Enterprise

enabled only by predictive analytics. Predictive analytics is an advanced form of data analytics that utilizes a large number of variables based on both internal and external data sources and leverages advanced statistical tools as well as specialized analytical techniques to predict likely future outcomes. Predictive analytics lays the .

Related Documents:

May 02, 2018 · D. Program Evaluation ͟The organization has provided a description of the framework for how each program will be evaluated. The framework should include all the elements below: ͟The evaluation methods are cost-effective for the organization ͟Quantitative and qualitative data is being collected (at Basics tier, data collection must have begun)

Silat is a combative art of self-defense and survival rooted from Matay archipelago. It was traced at thé early of Langkasuka Kingdom (2nd century CE) till thé reign of Melaka (Malaysia) Sultanate era (13th century). Silat has now evolved to become part of social culture and tradition with thé appearance of a fine physical and spiritual .

̶The leading indicator of employee engagement is based on the quality of the relationship between employee and supervisor Empower your managers! ̶Help them understand the impact on the organization ̶Share important changes, plan options, tasks, and deadlines ̶Provide key messages and talking points ̶Prepare them to answer employee questions

On an exceptional basis, Member States may request UNESCO to provide thé candidates with access to thé platform so they can complète thé form by themselves. Thèse requests must be addressed to esd rize unesco. or by 15 A ril 2021 UNESCO will provide thé nomineewith accessto thé platform via their émail address.

Dr. Sunita Bharatwal** Dr. Pawan Garga*** Abstract Customer satisfaction is derived from thè functionalities and values, a product or Service can provide. The current study aims to segregate thè dimensions of ordine Service quality and gather insights on its impact on web shopping. The trends of purchases have

Chính Văn.- Còn đức Thế tôn thì tuệ giác cực kỳ trong sạch 8: hiện hành bất nhị 9, đạt đến vô tướng 10, đứng vào chỗ đứng của các đức Thế tôn 11, thể hiện tính bình đẳng của các Ngài, đến chỗ không còn chướng ngại 12, giáo pháp không thể khuynh đảo, tâm thức không bị cản trở, cái được

SAP Predictive Analytics Data Manager Automated Modeler Expert Modeler (Visual Composition Framework) Predictive Factory Hadoop / Spark Vora SAP Applications SAP Fraud Management SAP Analytics Cloud HANA Predictive & Machine Learning Spatial Graph Predictive (PAL/APL) Series Data Streaming Analytics Text Analytics

predictive analytics and predictive models. Predictive analytics encompasses a variety of statistical techniques from predictive modelling, machine learning, and data mining that analyze current and historical facts to make predictions about future or otherwise unknown events. When most lay people discuss predictive analytics, they are usually .