The Data Analytics Blog

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

All Posts

Predictive Models To Empower Your Sales Call Centre Agents

January 24, 2019 at 7:52 AM

In an outbound sales environment, the agent needs to work through a long list of customers and the more information available to the agent on the customer, the better.

We’ve identified two types of models that can assist the agent and improve outbound campaign results.

Models to use in a sales call centre

Take-up model:

A propensity to take-up model, allows an agent to understand the likelihood of a client being interested in taking up the offer. It is typically used to prioritise leads, but it is also useful information for the agent when phoning the customer. The agent can adjust his conversation accordingly and be more prepared for the call if he knows that the customer will be more or less likely to be interested.

Best Product model:

The second model is a best product model. This model can be used to identify which product the customer is more likely to be interested in. The model will also give you the probability to take-up the offer, similar to the previous model. It can also be used to identify the second or third best product to offer. Therefore, it basically gives you a product ranking and likelihood to take-up.

Methodology and benefits

The models developed will predict how likely a client is to be interested in the specific offer or product. The model uses past behaviour and trends to predict future behaviour. Therefore, it is essential that the historic campaign data is available for the same offer or product. The model will allow you to rank the universe according to the likelihood of taking up the offer.

If you have multiple products and are interested to know which products to offer to which customers, the best product model can be used. This methodology gives you a model per product that predicts the likelihood of a customer taking up the product. These models can be used to identify the best product and also rank the products per customer based on likelihood to take-up.

Data used

To develop a propensity to take-up model, the following historical data sources are required:

  • Dialler data indicating who was contacted together with the dialler outcome
  • Sales data indicating who took up the offer
  • It is essential to be able to match the sales and dialler data on the unique customer ID
  • Bureau data to be used as predictive characteristics for SACRRA members
  • Other demographic and geospatial data to be used where the client is not a SACRRA member

To develop a best product model, the following historical data sources are required:

  • Dialler data indicating who was contacted together with the dialler outcome for each of the products
  • Sales data indicating who took up for each of the products
  • It is essential to be able to match the sales and dialler data on the unique customer ID
  • Bureau data to be used as predictive characteristics for SACRRA members
  • Other demographic and geospatial data to be used where the client is not a SACRRA member

Keep your agents informed and empowered

It is vitally important, however, that your call centre agents have easy-access to the outcomes and recommendations made by these models.

With models built by Principa in our proprietary decisioning software, DecisionSmart, Principa’s Agent X Call Centre Virtual Assistant can deliver real-time call and agent specific data, decisions and information to your agents visually, to inform, guide and motivate them.

Read more on Agent X or request a demo.

Contact Us to Discuss Your Business Requirements

Francel Mitchell
Francel Mitchell
Francel Mitchell is the Head of Decision Analytics at Principa. Francel’s team has a winning track record using descriptive, predictive and prescriptive analytical techniques within the financial services, marketing and loyalty sectors. Utilising available data and through the application of advanced analytical techniques, the team takes pride in their ability to predict human behaviour that can be used to assist business in making profitable decisions.

Latest Posts

IFRS9 Expected Credit Loss (ECL) Models For Retail Lending

It is expected that IFRS9 adoption should lead to an increase in provisions (initially a balance sheet / retained earnings adjustment only with commentary on retrospective impacts). Typically, the increase is mostly a result of loss provisions for all accounts (regardless of a loss event) and the extension of the loss period from a typical 12 months to lifetime (e.g. for structured loans the remaining term of the loan plus time to default/write-off plus the recoveries window).

Engaging Your Customers In A Digital Era At The 20th Customer Engagement Technology Conference

We’re excited to announce that we are a sponsor at this year’s 20th CET conference in South Africa! The Customer Engagement Technology Conference has been successfully bringing together marketing, digital/ IT and business heads to discover the latest solutions that enable greater customer experience in various industries.

Why The Human Mind Is Flawed At Making Credit Decisions

For a while, we have been running a blog series on cognitive biases and logical fallacies that data scientists should avoid. In philosophy there are a host of informal logical fallacies – essentially errors in thinking – that crop up every day. In this series we have looked at the practice of data science to determine how these same fallacies also occur. Today we will be looking at fallacies and their manifestation in credit: The Monte-Carlo fallacy and the Hot-hand fallacy with some studies in the credit world.