YAML
---
name: creating-executive-banking-reports
description: Creates comprehensive analytical reports for senior banking executives by synthesizing insights from multiple data sources (CSV, Salesforce, Excel, etc.). Use when executives need strategic insights from complex financial data.
---

Creating Executive Banking Reports

Python
import pandas as pd
import numpy as np
from datetime import datetime, timedelta

# Executive summary template
exec_summary = {
    'key_findings': [],
    'revenue_impact': 0,
    'risk_indicators': [],
    'recommendations': []
}

# Load and merge core datasets
client_data = pd.read_csv('client_portfolio.csv')
salesforce_data = pd.read_excel('sf_export.xlsx')
performance_data = pd.read_csv('performance_metrics.csv')

merged_data = client_data.merge(salesforce_data, on='client_id', how='left')

Progress:

• Data Discovery: Catalog all available sources and data quality
• Executive Interview: Confirm key questions and success metrics
• Data Integration: Clean, standardize, and merge disparate sources
• Analysis Framework: Apply banking KPIs (AUM growth, fee income, risk metrics)
• Insight Generation: Identify trends, anomalies, and opportunities
• Visualization Design: Create executive-level charts and dashboards
• Narrative Construction: Build compelling story with data evidence
• Executive Review: Present findings and refine recommendations

Example 1: Client Concentration Risk Analysis Input: Client portfolio data, transaction history, market data Output: "Top 10 clients represent 47% of AUM ($2.3B), with 3 clients showing 15%+ portfolio volatility. Recommend diversification strategy targeting $500M in new mid-tier acquisitions."

Example 2: Revenue Opportunity Assessment Input: Salesforce pipeline, fee structures, client interactions Output: "Underutilized advisory services across 340 high-net-worth clients represent $12M annual revenue opportunity. Current penetration: 23% vs. peer average of 41%."

Data Integration:

• Establish master client ID mapping across all systems
• Document data lineage and refresh frequencies
• Flag data quality issues prominently in reports

Executive Communication:

• Lead with 3-bullet executive summary
• Use banking terminology (AUM, NAV, alpha, Sharpe ratio)
• Quantify everything in dollars and basis points
• Include confidence intervals for projections

Visual Standards:

• Limit to 5 colors maximum
• Use horizontal bar charts for rankings
• Include trend arrows and variance indicators
• Standardize on monthly/quarterly time periods

• Don't present raw correlation matrices to executives
• Don't use technical jargon (API calls, data schemas) in reports
• Don't show more than 7 items in any single chart
• Don't forget to adjust for market conditions in performance comparisons
• Don't present recommendations without clear ROI calculations
• Don't ignore regulatory implications (privacy, compliance requirements)