Increasing adoption of digital channels forBancor users using propensity models to identify users likely to migrate to digital channels.
Benefits & Results
Background
Bancor Cordobesa, an Argentine BFSI company, offers comprehensive bankingservices, including savings and checking accounts, loans, credit cards, andinvestment options. The bank aims to enhance financial inclusion and customerexperience through digitalization. Objectives include modernizing bankingoperations, offering innovative digital products, improving accessibility andefficiency, and providing online banking, mobile apps, and digital paymentsolutions to foster economic growth in the region.
Challenges
Issue Identification: Bancor faced several challenges necessitatingt he adoption of this solution, including low user engagement with digital channels, difficulty in predicting user behavior, and inefficient targeting of users likely to benefit from digital migration. Additionally, they struggled with optimizing resource allocation for user outreach and maximizing the impact of digital transformation efforts. These issues hindered their ability to fully leverage digital platforms and achieve seamless user transitions.
Issue Impact: Low user engagement with digital channels resulted in under utilization of their platform's capabilities and reduced overall efficiency. Difficulty in predicting user behavior and inefficient targeting led to wasted resources and missed opportunities for user engagement.This hindered their digital transformation efforts, limiting the potential growth and adoption of their decentralized finance solutions. Consequently, Bancor struggled to maintain competitiveness and failed to fully capitalize on the advantages of their digital infrastructure.
Solution
NowVertical created a custom machine learning-enabled propensity model that captures client behavior patterns using various information sources such as usage, payments, claims, and credit history. By analyzing the historical data of clients who had already adopted digital channels, the model identified current users with a higher likelihood of migrating to digital channels by overlaying typical patterns.
Implementation
- Data Collection from Customer-Facing and Customer TransactionalSystems: Bancor began by gathering data from various customer-facing and transactional systems. This included information on usage patterns, payment histories, claims, and credit records to ensure a comprehensive understanding of user behavior.
- Machine Learning ModelDevelopment: With the collected data, a custom machine learning-enabled propensity model was developed. This model analyzed behavior patterns and historical data to predict which users were most likely to adopt digital channels, ensuring precise targeting.
- Reporting of ModelResults into Insightful Dashboards: The results from the propensity model were then integrated into insightful dashboards. These dashboards provided clear visualizations and actionable insights, enabling Bancor to make informed decisions and strategize effectively to enhance digitalchannel adoption.