Aurora Bank Analysis
(Excel & Power BI)
Key Insights
-
High-Risk Customers: 53.45% of customers are "High Risk," with an average DTI ratio of 172.91% and debt of $79,710.58.
-
Credit Scores: 46.55% of customers have "Good" credit (670-739), while only 8.3% are "Excellent" (800+).
-
Age & Risk: Gen X (44-59) has the highest "High Risk" and "Extreme Risk" levels, needing targeted strategies.
-
Transaction Types: Chip transactions dominate at 67.53%, showing a preference for secure, in-person payments.
-
Errors: "Insufficient Balance" is the most common error, especially for Gen X customers, indicating financial strain.
-
Fraud: High transaction amounts and counts flagged several clients for "Potential Fraud," requiring stricter monitoring.
-
Revenue Sources: Money transfers, grocery stores, and wholesale clubs are top contributors to revenue.
-
Gen X Profitability: Gen X leads in transaction volume, averaging $42 per transaction, driving significant revenue.
-
Credit Card Use: Customers have an average credit limit of $14,350 and 3.07 cards, indicating high credit exposure.
Introduction
Welcome to the Aurora Bank Data Analysis! As a data analyst at one of the most dynamic financial institutions, I was tasked with uncovering critical insights from data on customers, transactions, cards, and merchant categories.
Key Findings
-
Peak Demand Periods: Ticket volumes are highest on weekdays (85%), especially on Mondays and Fridays, with peak hours at 3 PM. Weekend activity is significantly lower at 15%.
-
Geographical Trends: Germany, Italy, and Poland generate the highest ticket volumes, indicating a need for focused support in these regions.
-
Topic Popularity: "Product Setup" and "Pricing & Licensing" are the most common topics, accounting for a large share of tickets.
-
SLA Compliance: Most tickets meet SLA for first responses (87%), but SLA violations for resolutions remain a concern, particularly for agents like Connor Danielovitch and Nicola Wane.
-
Agent Performance: Sheela Cutten leads in resolving tickets within SLA, while Connor Danielovitch and Nicola Wane have the highest SLA violations.
-
Channel Effectiveness: Chat consistently achieves the highest customer satisfaction, while phone channels show variability with extreme highs and lows.
-
Revenue-Driving Topics: High-ticket topics such as "Product Setup" and "Pricing & Licensing" dominate, reflecting their importance in customer engagement.
-
Customer Satisfaction Trends: Chat satisfaction peaked in October (4.43) and February (4.5), while phone satisfaction varied significantly, reaching a low of 1.5 in August.
-
Resolution Delays: While first responses are timely, resolution times often exceed acceptable limits, indicating systemic inefficiencies.
-
Weekend Support Gaps: Reduced activity on weekends could lead to delays in addressing critical issues.
Data Analysis Focus Areas
-
Understand Customer Profiles: Explore customer demographics, financial health, and behaviors to unlock new opportunities for engagement.
-
Analyze Spending Trends: Uncover patterns and growth opportunities in transaction data.
-
Identify Risks: Spot potential red flags in rising debt, transaction errors, and fraudulent activity.
Recommendation
-
Segment High-Risk Customers: Focus on customers with high debt-to-income (DTI) ratios and poor credit scores for targeted financial counseling or repayment restructuring.
-
Enhance Customer Loyalty Programs: Leverage insights from credit score levels and demographics to create tailored rewards or incentives for loyal, low-risk customers.
-
Streamline Fraud Detection: Implement automated fraud detection systems based on flagged "Potential Fraud" cases, considering transaction thresholds and client ID grouping.
-
Increase Revenue Streams: Introduce premium financial services for customers in the "Excellent" and "Very Good" credit score categories to maximize profitability.
-
Expand Profitability Analysis: Regularly evaluate the profitability of various credit products and revise interest rates or terms to reflect risk levels.