Standard Bank shows “it’s possible” by using AI and analytics to improve customer service

Africa’s largest financial institution, Standard Bank, has a mission: to find ways to differentiate itself so that the bank can meet the needs of its customers in today’s complex and ever-changing world. Present in more than 20 countries in sub-Saharan Africa and around the world, the Bank aims to show its clients that It can be.

That means it needs the right tools, resources, and platforms to enable the innovation, resilience, and efficiency needed to empower its customers. For Standard Bank, that means using Microsoft’s Power BI platform to leverage data insights and predictive and prescriptive analytics through AI and machine learning. This enables the bank to better serve its customers through more accurate targeting and service delivery.

Baker Street Standard Bank

In 2017, the organization transitioned from a traditional centralized business intelligence team to a self-service BI model, as its value-added capabilities enabled more accurate and efficient targeting and service of customers. “Power BI helps transform citizens from data scientists to those who want to become one,” said Ziyaad Valli, Lead Analytics Engineer in the BI Data Visualization team at Standard Bank.

In 2020, the adoption of enterprise self-service BI was so successful that Standard Bank’s Microsoft Teams channel for Power BI had over 3,000 members.

The bank’s data visualization team used a descriptive analytical model to assess what had already happened. But Valli wanted to explore predictive (what might happen) and prescriptive (what the possibilities are) avenues to add to tools for internal teams. As a result, the data visualization team worked with the bank’s insurance business group to use AI and machine learning to accurately predict and target customers.

Use data to tell a more accurate story

In July 2020, Standard Bank Insurance launched a funeral cover product – insurance to cover funeral expenses – which sold well: customers queued at branches and phoned the bank’s call centres. Mohammed Tootla, Head of Data Visualization for Standard Bank’s Insurance Business Group, decided they needed more of their data.

“We started looking for alternatives to tell a better story with our data,” says Tootla. “We wanted to explore machine learning, but we didn’t have data scientists on our team.”

Tootla then contacted Valli, explaining that his team wanted to move forward with predictive and prescriptive analytics. The Valli and Tootla teams started collaborating in Power BI. They aggregated and analyzed funeral cover sales across multiple dimensions, uncovering a startling insight that matched sales prospect feedback: Millennial customers were creating higher demand than any other generation.

The other key learning was that sales took place on a particular day of the week. According to marketing and industry standards, most sales should take place on Wednesdays and Thursdays. However, the data showed that sales of funeral blankets took place on Fridays.

“We were able to uncover these key patterns and insights only because of the AI ​​analytics capabilities within Power BI,” says Tootla.

Understanding these trends in the data has allowed Standard Bank to make proactive adjustments to target the right audience and prepare for sales accordingly.

Better serve customers and mitigate customer cancellations

Next, Valli and Tootla looked at forecasting models to compare what sales might look like if factors remained unchanged, with “what if” parameters – policy-adjusted forecasts – such as: what if South Africa reverting to strict lockdown due to COVID -19 and travel restricted?

They created hindcast data models for four periods to compare predictions to actual results and presented them to business managers, who determined that the hindcasts stayed precisely within the upper and lower thresholds of the actual numbers.

With the forecasting model, prospects are now using predictive and prescriptive information to more properly staff branch and call center employees to better serve customers.

The Tootla team also had another goal: to analyze the high churn rate of their group’s short-term insurance portfolio. The previous report already used descriptive analytics models, but these only provided insight into why a customer had canceled insurance in the past. They did not indicate what might happen in the future.

Valli and Tootla created a binary classification model using the machine learning (AutoML) feature of Power BI, which quickly drove value by affecting bank results.

Using the churn model, 88,000 customers were assessed, including 40,000 active and 48,000 previously canceled. The churn model predicted the risk of losing approximately 8,000 active customers and broke down the 8,000 customers by segment, policy persistence, age, province and income, so the insurance group could target them in churn campaigns. loyalty.

“We were very impressed with the fast turnaround time with which Power BI AutoML delivered results,” says Tootla. “A data scientist would come in and might not produce a report for months. We produced the first binary classification model in three weeks.

Unite datasets and add value

Valli and Tootla agree that the project is still in its infancy. Tootla plans to extend the forecasting and churn models to the entire Standard Bank insurance product line. Beyond that, he plans to unite sales, cancellations, and retentions datasets.

“We would like to bring in customer demographic information and create an all-in-one dataset model that we can use as input to our customer lifetime value model,” he says.

The collaboration and results changed the way Valli thinks about data by holistically evaluating all new features and considering how they can add value to any business unit his team supports. He says AI analytics is all about helping the bank extract value and demonstrate the robust capabilities of Power BI tools.

“It’s just the beginning. We’re going to do a lot more in the future and we’re all really excited about it,” says Valli.