![](https://cdn.prod.website-files.com/6689360616dc49618ad1d796/6691727accbe8bd65b7d1932_66916200ff070cc6f72447ed_Rectangle%2520374.png)
![](https://cdn.prod.website-files.com/6689360616dc49618ad1d796/6691727accbe8bd65b7d192c_669161f3e66038d7a9d714f2_image%25203-7.png)
Tailoring cross-sell and up-sell offerings to customers.
Benefits & Results
Background
Banco Ciudad is the primary financial institution in the Autonomous City of Buenos Aires, Argentina. It is a government-owned bank offering a wide range of banking services, including personal and business banking, loans, investment products, and financial advisory services. The bank plays a significant role in the local economy by financing small and medium-sized enterprises (SMEs) and offering competitive financial products tailored to the needs of its diverse customer base.
Challenges
Issue Identification: Banco Ciudad faced challenges in evaluating cross-sell opportunities and determining which combinations of active customers and existing products were most likely to lead to new product purchases.
Issue Impact: The inability to effectively assess cross-sell opportunities significantly impacted revenue potential and lower average revenue per customer. Ineffective targeting resulted in reduced sales, customer frustration, and decreased satisfaction.
Solution
NowVertical leveraged historical data on client usage, payments, and other activities to identify clients likely to acquire additional products like credits, credit cards, and insurance. The solution involved an end-to-end data analytics solution integrating CRM and customer-facing channels into a comprehensive customer data platform
Implementation
- Conducted an assessment to evaluate existing data and customer processes, identifying gaps and areas for improvement.
- Collected, cleaned, and integrated historical client data into a centralized data warehouse.
- Structured the data to facilitate analysis, creating customer-centric models representing a 360-degree view of behaviors and interactions with various products.
- Developed predictive models using Logistic Regression and Gradient Boosting to identify clients with a high propensity to acquire additional products.
- Provided ongoing support to refine models and address any operational issues.