Home Retail AI powers proactive hyper-personalized experience for retail banking customers

AI powers proactive hyper-personalized experience for retail banking customers

by Ozva Admin

a recent satisfaction study by JD Power for US Retail Banks found that banks have struggled to meet customer personalization expectations with nearly half of customers moving to digital-centric banking relationships. Today, the expectations of bank customers have changed, now they are looking for hyper-personalized offers like those provided by Netflix, Amazon and Starbucks. Hyper-personalization can be achieved by leveraging artificial intelligence (AI) and machine learning (ML) with real-time data and tailoring customer experiences. This blog explores the opportunities to leverage ML models to hyper-personalize the customer experience across customer channels, namely contact center, web, and social.

Change in focus of customer experience

Customers expect a meaningful and highly personalized digital experience for their individual banking needs. Banks can predict these needs by better understanding their customers: their goals, preferences and behaviors in real time and proactively offering personalized offers. Consider a scenario where a customer spends more money than usual, which could lead to him not having enough funds for his next EMI. What if the bank can predict spending based on the past spending trend? The bank can then proactively alert the customer and offer discounts on a personal loan. Such a proactive, contextual, and personalized bank-initiated experience can deepen customer relationships.

Since this has been a topic of interest in the recent past, let’s explore how AI/ML research is applied to three different customer channels independently, and then compare the three approaches.

AI-based hyper-personalization or recommendation models

1. Customer Service Call Center: Predicting the reason for a customer’s call and performing a preventive intervention would attract customers. Researchers have developed an AI-based system
multitasking neural network (ANN) to predict a customer’s call intent and subsequently migrate the customer to digital channels. The machine learning model was trained using the customer profile, call transcript data, customer service record, and transaction log. The goal is to predict whether the customer will call the contact center in the immediate future, say within the next 10 days.

When the customer calls the IVR system, a personalized voice message will recommend the relevant digital services based on the model’s prediction. If the customer accepts the recommendation, then they are redirected to launch a chatbot via SMS with a URL. This results in a hyper-personalized and efficient customer service experience. Consider a scenario where a customer has deposited a check but the amount has not been credited to their bank account even after a week. The customer would consult by calling the contact center. The machine learning model would predict the intent of the call for this specific customer and move to their preferred digital channel for appropriate resolution.

2. Web channel: User behavior based personalization is usually done by data mining algorithms, but user behavior prediction for full personalization is very difficult. This is because usage data changes frequently with the changing interest of the user. Researchers have found a clever novel web personalization model for user preference recommendation. The machine learning model predicts web content for the user and learns user behavior continuously. Banks can use the model to recommend products tailored to a specific user.

Instead of offering personal loans to every customer who enters their website, banks can customize the home page for their customers based on browsing history and their current life stage. For example, a client with a young family would be more interested in obtaining a mortgage or car loan or long-term investments. A client who will be retiring soon may need help with retirement plans and wealth management. With the previous AI model, banks can dynamically adapt the website by recognizing the customer and anticipating the need.

3. Social media channels: These platforms generate a large amount of customer-related data, including behavioral data that banks can use to gain a deeper understanding of customer needs. These valuable insights can lead to proactive personalized offers for customers. Researchers have developed a integrated framework to help banks get value from social media analytics. This will help leverage advanced AI-based predictive and prescriptive analytics to develop insights for hyper-personalization of the customer experience. Consider an example of a client who posts comments on Facebook about specific tourist destinations and her interest in visiting these places. This is a great opportunity for the bank to analyze the publications and suggest personalized offers such as personal loans, travel insurance and deals on travel tickets.

In these three customer channels, the data required for predictions varies from channel to channel. Figure 1 offers the summary of the data involved in customer engagement in each channel. We see increased data complexity in the contact center and social media channels due to unstructured data.

Enriching customer experiences: the way forward

We discuss recommended machine learning models for different customer channels. Because data sets, data types, and user behavior on each channel are different, each customer interaction is unique. We see increasing complexity in AI models as we move from web channels to contact center channels to social media channels. Banks can consider this when prioritizing and implementing machine learning models for hyper-personalization.

AI-based prediction models using real-time data look very promising. It provides an opportunity for banks to tailor each customer touch point. We discussed hyper-personalization across all three channels and the tremendous value that can be unlocked. This can allow banks to hyper-personalise, improve customer loyalty and drive significant growth.

You may also like

Leave a Comment