The Data Analytics Blog

Our news and views relating to Data Analytics, Big Data, Machine Learning, and the world of Credit.

All Posts

5 Software essentials for account management strategies

July 17, 2020 at 3:00 PM

Effective account management strategies can prove highly profitable, particularly in a competitive marketplace where acquiring good customers is a challenge.

In our first blog we looked at the data, analytics and strategy requirements for deploying account management strategies (first 5 items in the list below). In this blog, we focus on the software requirements. 

  1. Clean data
  2. Scorecards
  3. Account management strategies (by decision area)
  4. Champion/challenger
  5. Monitoring
  6. Account processing system
  7. Data management platform
  8. Scoring engine
  9. Business Rules Management System
  10. Operational execution

Whilst account management strategies can be run offline in a manual process, it is quite cumbersome.  Automation should be the goal.

6.  Account processing system

An account processor processes accounts every month performing a wide range of actions. A primary set of actions include aging the account, calculate interest and calculating fees. A monthly snapshot of the account is provided. This is a relatively short string of data incorporating the age of the account, delinquency status, block code status, outstanding balance, amount due, amount paid this month, fees and interest charged, etc. For effective account management strategies, this information needs to be extracted monthly. 

The account processing system also frequently ingests the account management strategy.  It could be that you process an account management offer for a customer each month. The offer should be stored somewhere and that is usually the account processing system. Authorisations are also usually run through the account processing system from point-of-sale (POS) into the business rules management system (BRMS) and then back again.

7.  Data Management Platform

One of the missing (and sometimes overlooked) components in the processing of behaviour scoring is an effective data management platform (DMP). The DMP has multiple functions, but its primary functions include:

  1. The ingesting of data sets – this is data from the account processor and potentially other sources (e.g. dialler data, credit bureau data, collections management system data, etc.). This step may include cleaning of data.
  2. The storing of multiple data sets (for example this could be the same data set over multiple months)
  3. The production of aggregate variables (also known as feature creation)
  4. The submission of these features into a decision engine for scoring and decisioning

In account management there are many aggregated fields that are used in both the scorecards and in the strategies, these fields are produced by a DMP or by a step in SQL or manual step in SAS.  In account management these fields incorporate trends typically over the last month,  3 months, 6 months and 12 months.  The feature creation process includes calculations such as maximums/minimums (e.g. maximum balance over the last 6 months), averages (e.g. average amount due over the last 3 months), months-since (e.g. months since a payment was missed), counts (e.g. number of partial payments in the last 6 months), mixed (e.g. highest ratio of amount paid over amount due last 12 months). 

To understand how Principa’s DMP can benefit your business, please do get in touch with us.

8.  Scoring engine

A scoring engine enables a score to be calculated utilising the features created by the DMP. In account management there are multiple scores that can be built (we covered this in the previous blog) and a scoring engine should have the ability to produce multiple scores (some do not). Two scores can be combined later in a matrix or in a decision tree. For more information on what a scoring engine should incorporate please see our helpful blog on the topic.

9.  Business Rules Management System (BRMS)

A BRMS is software that allows users to manage business rules used in automated processes. This is done through a variety of decisioning metaphors including the following:

  • matrices (to combine two scores into a risk grade),
  • decision trees (to segment the population into scenarios),
  • terms of business tables (to apply actions to each leaf/scenario of the tree).
  • calculations (calculations based on the outputs of the terms of business table).

It is also worth noting that many BRMSs incorporate scoring engines and some will also wrangle data as a DMP does. Whilst BRMSs can be used across the credit lifecycle, in account management BRMSs often feature “pre-fabricated” decision areas such as credit limit management or authorisations.

Each of these pre-fabricated decision areas may feature a short-list of decision-keys and set outcomes.  Outputs are either fed back into an account processing system or an extract file is produced that can then be actioned elsewhere.

If you’d like to see what Principa’s BRMS DecisionSmart does, visit our DecisionSmart product page or visit our DecisionSmart FAQ page.

10. Operational Execution

Once an account is scored and an account management strategy is enacted, action needs to be taken on the account. A variety of systems can be used for this. Some of these are listed below:

  1. Wireless application service providers (WASPS) – for the purpose of providing bulk SMS or MMS to the customer.
  2. Account processing systems – credit limit offers, automated credit limit decreases, authorisations (via APS to POS)
  3. Automated chatbots (like Principa’s Atura – click here for a live demonstration ) for the purpose of processing a credit limit increase, cross-selling, up-selling, sending vouchers and special offers
  4. Call centre management software (for the purposes of credit limit offers, cross-sell, up-sell)
  5. Cal centre virtual assist (like Principa’s Agent-X) – these guide a call centre agent through the call based on key information about the customer.


If you would like to know anything about the systems mentioned above or would like to find out how Principa can help your company get the most out of account management strategies, get in touch with us on

Contact Us to Discuss Your data analytics Business Requirements

Thomas Maydon
Thomas Maydon
Thomas Maydon is the Head of Credit Solutions at Principa. With over 17 years of experience in the Southern African, West African and Middle Eastern retail credit markets, Tom has primarily been involved in consulting, analytics, credit bureau and predictive modelling services. He has experience in all aspects of the credit life cycle (in multiple industries) including intelligent prospecting, originations, strategy simulation, affordability analysis, behavioural modelling, pricing analysis, collections processes, and provisions (including Basel II) and profitability calculations.

Latest Posts

How chat is revolutionising the digital onboarding experience

Principa’s onboarding chatbot solution; Atura allows lenders to engage a customer effectively through an application process while accessing necessary data and decisioning calls using Principa’s SmartSuite software. The digital revolution “Digital” has been a financial services buzz-word for some time. Most South African lenders Principa works with have been working hard to adapt to a digital existence for several years. Some have been successful, others are still working on the challenge - and most have only partially adapted.

How to choose the correct collections chatbot

Principa has a wealth of experience in building and deploying chatbots for the financial services industry. Our custom-built solution is flexible and fully customisable which allows your bot to assume your brand’s persona. We can also seamlessly integrate with existing systems. Click here to find out more. 

Model validation and adjustment

The time is NOW for model validation and adjustment. One of the major premises used in credit scoring is that “the future is like the past”. It’s usually a rational assumption and gives us a reasonable platform on which to build scorecards whether they be application scorecards, behavioural scores, collection scores or financial models. That is reasonable until something unprecedented comes along. You can read about this black swan event in our previous two blogs here and here.