2025, Vol. 8, Issue 2

Low-income customers in both the United States and Ghana encounter persistent barriers to accessing banking and insurance products, including irregular income patterns, low financial literacy, limited formal credit histories, and minimal exposure to risk-protection mechanisms. These factors reduce product uptake, weaken customer-bank engagement, and limit the feasibility of traditional cross-selling strategies. Predictive analytics offers a robust approach for understanding behavioral patterns, anticipating financial needs, and delivering personalized product recommendations tailored to the circumstances of underserved populations. This paper introduces a comparative analytics framework designed to optimize cross-selling and insurance product recommendations for low-income U.S. and Ghanaian banking customers. The framework integrates transactional data, mobile money usage behavior, micro-savings patterns, demographic markers, and digital engagement signals. Machine learning models including uplift modeling, clustering algorithms, and next-best-offer engines are applied to predict product receptiveness, identify underserved customer segments, and prioritize outreach strategies that align with customer needs and risk exposure. The analysis highlights key behavioral predictors of insurance adoption, such as seasonal spending cycles, remittance flows, emergency withdrawal frequency, and bill-payment regularity. For Ghanaian customers, mobile money ecosystems and informal financial networks provide valuable alternative-data inputs for modeling. For U.S. customers, debit-card activity, overdraft patterns, and digital-channel interactions enhance prediction quality. The results show that personalized cross-selling informed by predictive analytics significantly improves product match quality, strengthens trust, and increases adoption rates among low-income customers. By demonstrating how data-driven recommendation engines can be culturally adaptive, equitable, and context-sensitive, this study provides actionable insights for financial institutions aiming to expand inclusion while optimizing product portfolios in diverse low-income markets.