PROJECT 1
Integrating customer experience and bank data within business banking
Client: Absa Bank
Led by: Prof. Riaan de Jongh (North-West University)
Background information
The extent to which our clients convey positive messaging and sentiments to their colleagues or families is a critical indicator used to assess customer experiences within various banking products and services offered by Absa.
The Net Promoter Score (NPS) is a well-known measure of customer experience, calculated based on responses to a single question: How likely is it that you would recommend our company/product/service to a friend or colleague? The scoring for this answer is most often based on a 0 to 10 scale with the score being calculated as follows:
NPS = % "Promoters" (9s and 10s) - % "Detractors" (0s to 6s)
"Promoters" (scores of 9 / 10) are considered likely to actively promote Absa and its products. "Detractors" (scores of 0 to 6) are considered likely to actively demote Absa and its products. "Passives" (scores of 7 / 8) are not likely to communicate further about Absa products.
The goal of this project is to determine the most important factors influencing positive customer experiences with the bank. The project relates specifically to the business division of Absa Bank.
Project aims and objectives
The aim of this project is to:
-
Develop client profiles (demographic, behavioral, other) of our customers using the three Customer Experience / NPS classifications (i.e. Promoters, Detractors and Passives)
-
Identify potential drivers of Customer Experience and provide recommendations as to how to:
-
Ensure that customers who are Promoters remain in this bucket
-
Provide insight into how Detractors / Passive can be promoted up the chain to becomE Promoters.
-
In summary, the intent of this is to leverage this data, developing meaningful profiles and insights which Absa can use to improve its Net Promoter Score.
About the dataset
The provided dataset contains information on:
-
Customer demographics
-
Financial (income / balances as it relates to the Bank)
-
Transactional data (detailed longitudinal data describing the client's historical transactions with the Bank)
-
Product holding Combinations
-
Net Promoter Score
The dataset provided to the group have been cleaned and have had anomalies removed, and should therefore require minimal additional manipulation.
Intended outcomes and real-world relevance
The intended outcome of the project is a model capable of accurately predicting Net Promoter Score (or membership of the three NPS groups) using the available input variables. Of course, the more accurate the model in terms of predictive power, the better. The Net Promoter Score has been shown to have a proven link with customer retention and overall satisfaction. Identifying the key drivers of the NPS therefore has the potential to directly affect the quality of the products and services Absa offers.