Propensity-to-Pay: Machine Learning for Estimating Prediction Uncertainty
This addresses the challenge of inefficient resource allocation and failure to proactively identify vulnerable customers for energy organizations, but it is incremental as it applies existing methods to a new domain-specific dataset.
The paper tackled the problem of predicting residential customers' propensity-to-pay energy bills to identify financial hardship early, using a case-study from an energy organization, and found that a Bayesian Neural Network was proposed and explored for deployment among seven models tested.
Predicting a customer's propensity-to-pay at an early point in the revenue cycle can provide organisations many opportunities to improve the customer experience, reduce hardship and reduce the risk of impaired cash flow and occurrence of bad debt. With the advancements in data science; machine learning techniques can be used to build models to accurately predict a customer's propensity-to-pay. Creating effective machine learning models without access to large and detailed datasets presents some significant challenges. This paper presents a case-study, conducted on a dataset from an energy organisation, to explore the uncertainty around the creation of machine learning models that are able to predict residential customers entering financial hardship which then reduces their ability to pay energy bills. Incorrect predictions can result in inefficient resource allocation and vulnerable customers not being proactively identified. This study investigates machine learning models' ability to consider different contexts and estimate the uncertainty in the prediction. Seven models from four families of machine learning algorithms are investigated for their novel utilisation. A novel concept of utilising a Baysian Neural Network to the binary classification problem of propensity-to-pay energy bills is proposed and explored for deployment.