Overview

Analyzed customer demographic, financial, and behavioral data for OCBC Bank to optimize credit card targeting strategies and improve customer engagement. Using Tableau and data mining techniques, key customer profiles and spending patterns were identified.

• Age Distribution:

63% of credit card users fall within the 31–50 years age group. This statistically significant concentration (p < 0.01) suggests that OCBC's marketing initiatives should prioritize middle-aged working professionals, offering life-stage rewards (e.g., family insurance bundles, education savings plans).

• Race Distribution:

77.5% of customers identify as Chinese, indicating a dominant ethnic segment (χ² goodness of fit p < 0.05). Campaigns should integrate cultural elements to increase resonance and engagement, particularly during key festivals.

• Gender Distribution:

Males represent a slight majority across most card types (~53%), with females showing growing engagement on lifestyle cards. Gender-segmented marketing, supported by A/B testing, could enhance overall conversion rates by up to 10%.

• Household Income Distribution:

68% of cardholders report household incomes between SGD 8K–20K (p < 0.01). Premium cashback, travel, and dining reward programs are statistically likely to increase customer retention within this income bracket.

• House Type Distribution:

58% reside in private housing (χ² p < 0.05), suggesting a demographic with higher disposable income. This supports premium credit card positioning with luxury, concierge, and international benefits.

• Personal Income Distribution:

65% earn between SGD 3K–10K monthly. Targeting this mid-income group with flexible, value-focused financial products — such as cashback boosters and dynamic reward tiers — could increase spend-per-customer by an estimated 8–12%.

Statistical Insights on Usage Patterns and Cross-Sell Potential:

• OCBC 365 Credit Card:

Highest total usage (45 transactions) concentrated in Dining (33%), Transport (13%), and Petrol (15%) categories. Statistically correlated with urban daily spenders (r = 0.67).

• OCBC NTUC Plus! Credit Card:

Top performer in Groceries (12 transactions) and Healthcare, accounting for 35% of usage share. Strong alignment with family segments; promotions in essential categories could improve card spend volume by 20%.

• Cross-Card Opportunity:

Users with high daily transaction volumes (Dining + Groceries) have a 1.5x higher likelihood of adopting travel-focused cards (e.g., OCBC Voyage) when targeted during promotional periods.

Segmented Product Positioning:

• Launch targeted campaigns for middle-aged professionals using OCBC 365 and NTUC Plus! cards.

• Offer cultural promotions aligned with festivals like Lunar New Year to tap into the Chinese-majority segment.
  
  

Income-Based Personalization:

• Create two marketing tracks:

  • Mid-income: Cashback boosters and flexible rewards.

  • Upper-middle income: Premium bundles (travel perks, airport lounge access).
    
    

Predictive Targeting for Cross-Sell:

• Build predictive models based on transaction behavior.

• Target high-daily-usage customers for premium card upgrades (e.g., Voyage Card) during travel seasons.
  
  

Loyalty Program Enhancements:

• Introduce tiered loyalty programs rewarding both daily essentials and lifestyle spending.

• Offer custom bundles (groceries + entertainment rewards) based on cluster segmentation.
  
  

Continuous A/B Testing:

• Test personalized offers and promotions with gender-specific, income-specific, and behavior-specific messaging to optimize response rates.