The Story

A leading bank with a customer base of 10 million identified a significant opportunity to increase revenue by tapping into the underutilized monthly utility bill payments market, valued at $140 billion. The company faced the challenge of low usage and adoption of their card for these payments. To address this, Appice implemented machine learning (ML) models to predict which app users were most likely to convert and devised an omnichannel strategy to target this group. This case study highlights how this ML-powered upselling approach led to a remarkable 32% revenue increase, explicitly focusing on monthly utility bill payments.

Here is what the bank expected:

1. Improve Customer Engagement and Satisfaction

The bank aimed to enhance customer experiences by delivering personalized and relevant communications.

2. Optimize Marketing Campaigns and Promotions

The bank sought valuable insights into customer preferences and behavior, enabling them to create targeted and effective marketing campaigns.

3. Enhance Operational Efficiency

Automating manual processes and streamlining workflows would free up resources, save time, and allow employees to focus on higher-value tasks.

The Challenges

Despite having a substantial customer base, The bank observed low usage of their card for monthly utility bill payments. Given the size of the utilities industry, this represented a significant untapped market potential. The challenge lay in identifying the customers most likely to convert and utilize their Cards for these payments. SBI Card needed a solution to predict customer behavior accurately and devise an effective strategy to drive the adoption and usage of their card for monthly utility bill payments (Manglam, 2023).

1. Navigating Data Integration

Consolidating customer data from various systems and ensuring its accuracy and completeness presented a significant challenge. The bank invested in robust data integration solutions to seamlessly integrate data from different sources, enabling a unified view of customer information.

2. Ensuring Privacy and Security

Safeguarding customer data and complying with regulatory requirements were crucial considerations. The bank implemented stringent security measures to protect customer information, including encryption protocols and access controls. They also obtained consent from customers to ensure compliance with privacy regulations.

What We Did

To address the challenge, we implemented machine learning models to predict customer behavior and identify those most likely to convert. These predictive models analyzed various data points, including customer transaction history, spending patterns, demographics, and engagement with the mobile app. Based on the ML model’s predictions, SBI Card implemented an omni-channel strategy to target the identified group of customers (Jaffery, 2022). 

This strategy encompassed the following pointers:

1. Data Integration and Segmentation

The first step was integrating customer data from various sources, including transaction records, demographic information, and online interactions. This enabled the bank to create a unified view of each customer. They then segmented their customer base based on demographic profiles, transaction history, and product usage patterns. This segmentation allowed for personalized and targeted marketing campaigns.

2. Push Notifications

The system was designed to deliver personalized messages triggered by user behavior, such as completing transactions, updating account information, or participating in targeted promotions. The bank also ensured that customers could customize their notification preferences to align with their preferences and needs.

3. User Behavioral Analytics

We implemented a comprehensive user behavioral analytics platform to gain insights into customer behavior and preferences. This platform tracked user interactions within the mobile app, such as navigation patterns, feature usage, and transaction history. The collected data allowed the bank to create customer segments, understand their preferences, and tailor marketing campaigns accordingly. It also helped identify patterns and trends, guiding the bank’s decision-making processes.

3. Personalized Customer Journey Mapping

The bank developed a detailed customer journey map to visualize and optimize the end-to-end customer experience. This involved identifying critical touchpoints, pain points, and opportunities for improvement throughout the customer journey. The map provided a holistic view of customer interactions with the bank, enabling it to identify areas where it could streamline processes, eliminate bottlenecks, and enhance customer satisfaction.

The Impact

Implementation of our proposed solutions resulted in the following outcomes: 

1. 32% Revenue Increase

By accurately predicting customer behavior and targeting the right segment of app users, the bank achieved a remarkable 32% increase in revenue. Customers identified as most likely to convert responded positively to the targeted campaigns. They began using their SBI Card for monthly utility bill payments, leading to increased transaction volumes and revenue generation.

2. Increased Adoption of Monthly Utility Bill Payments

The ML models successfully identified customers who had the propensity to adopt monthly utility bill payments. The omni-channel strategy effectively communicated the benefits and advantages of using the SBI Card for these payments, resulting in increased adoption rates. Customers recognized the value proposition and convenience of consolidating their utility bill payments onto a single card, driving usage and engagement.

3. Incremental Revenue

The ML-powered upselling approach yielded 27% incremental revenue from monthly utility bill payments. The company tapped into a previously untapped market segment by converting customers who were previously not utilizing their SBI Card for these payments, driving revenue growth and expanding their market share.

4. Improved Customer Engagement

The personalized push notifications significantly increased customer engagement and usage of banking services. Customers appreciate timely updates, relevant offers, and notifications tailored to their preferences. This resulted in higher customer satisfaction levels and increased loyalty towards the bank.

5. Increased Cross-Selling Opportunities

The bank observed a rise in cross-selling opportunities through targeted and relevant offers. Customers who engaged with specific campaigns tended to explore and adopt additional banking products and services, leading to increased revenue and customer loyalty.

6. Personalization at Scale

The bank successfully achieved personalized communication at scale through marketing automation. By leveraging customer data and segmentation, they delivered tailored messages to a large customer base, fostering a sense of individual attention and relevance.

References

Manglam, Shivam Kumar. “Navigating Big Data Integration: Challenges and Strategies.” DataAnalytics.Report, 13 Apr. 2023, data analytics. Report/articles/navigating-big-data-integration-challenges-and-strategies.

Jaffery, Bilal. Connecting Meaningfully in the New Reality. Deloitte, 2022.