Data Storytelling Techniques

DATA STORYTELLING STRUCTURE:

1. SITUATION (What is the context?)
   "We tracked monthly revenue through 2024"

2. COMPLICATION (What changed or is problematic?)
   "Revenue declined 23% in Q3 despite no change in pricing"

3. KEY INSIGHT (The pivotal data point)
   "East region caused 80% of the decline — we lost 3 major accounts"

4. RESOLUTION (Recommended action)
   "Re-engage East region top accounts with retention offers"

5. CALL TO ACTION
   "Approve $50K retention budget — modeled ROI: 8x"

Chart-specific storytelling:
  Line chart: "The Unexpected Dip" → annotate the drop and its cause
  Bar chart:  "The 80/20 Finding" → highlight the dominant category
  Scatter:    "The Outlier Story" → circle and name key outliers
  Map:        "The Regional Gap" → darken the underperforming region

import matplotlib.pyplot as plt
import matplotlib.patches as mpatches
import numpy as np
import pandas as pd

np.random.seed(42)
months = pd.date_range('2023-01', periods=24, freq='MS')
revenue = [82000, 85000, 88000, 86000, 90000, 95000, 93000, 97000,
           102000, 98000, 105000, 110000, 108000, 112000, 115000,
           89000, 78000, 71000, 80000, 87000, 95000, 103000, 110000, 118000]

fig, ax = plt.subplots(figsize=(14, 7))

# Grey background context
ax.fill_between(months, revenue, alpha=0.05, color='blue')
ax.plot(months, revenue, '-', color='#1565C0', linewidth=2.5)
ax.plot(months, revenue, 'o', color='#1565C0', markersize=5)

# STORY ELEMENT 1: Growth period (grey rectangle)
ax.axvspan(months[0], months[12], alpha=0.04, color='green', label='Growth Phase 2023')

# STORY ELEMENT 2: Crisis (red rectangle)
ax.axvspan(months[13], months[18], alpha=0.08, color='red', label='Crisis Period')

# STORY ELEMENT 3: Recovery
ax.axvspan(months[18], months[-1], alpha=0.05, color='blue', label='Recovery 2024')

# Annotation: Start of crisis
ax.annotate('Account loss\n(East Region)', xy=(months[15], revenue[15]),
             xytext=(months[14], revenue[15] - 20000),
             arrowprops=dict(arrowstyle='->', color='#E53935', lw=2),
             fontsize=11, color='#E53935', fontweight='bold',
             bbox=dict(boxstyle='round', facecolor='#FFEBEE', alpha=0.8))

# Annotation: Recovery
ax.annotate('Retention campaign\nlaunched', xy=(months[18], revenue[18]),
             xytext=(months[17], revenue[18] + 15000),
             arrowprops=dict(arrowstyle='->', color='#2E7D32', lw=2),
             fontsize=11, color='#2E7D32', fontweight='bold',
             bbox=dict(boxstyle='round', facecolor='#E8F5E9', alpha=0.8))

# KPI callout box
ax.text(0.02, 0.95,
         '📊 KEY INSIGHT\nQ3 2024 decline: 23%\nEast Region: 80% cause\nTop 3 accounts churned',
         transform=ax.transAxes, fontsize=11, va='top',
         bbox=dict(boxstyle='round', facecolor='#FFF8E1', edgecolor='#FFB300', linewidth=1.5))

import matplotlib.dates as mdates
ax.xaxis.set_major_formatter(mdates.DateFormatter('%b %Y'))
ax.xaxis.set_major_locator(mdates.MonthLocator(bymonth=[1, 4, 7, 10]))
plt.setp(ax.get_xticklabels(), rotation=30, ha='right')

ax.set_title('Revenue Story: Growth → Crisis → Recovery\n2023-2024',
              fontsize=14, fontweight='bold')
ax.set_ylabel('Monthly Revenue ($)')
ax.yaxis.set_major_formatter(plt.FuncFormatter(lambda x, _: f'${x/1000:.0f}K'))
ax.legend(loc='lower right')
ax.grid(True, alpha=0.2)
ax.spines['top'].set_visible(False)
ax.spines['right'].set_visible(False)
plt.tight_layout()
plt.savefig('story_chart.png', dpi=150, bbox_inches='tight')
plt.show()

# Highlight the dominant segment — "Pareto Story"
products = ['Product A', 'Product B', 'Product C', 'Product D', 'Product E',
            'Product F', 'Product G', 'Product H', 'Product I', 'Product J']
revenue = [425000, 318000, 189000, 142000, 98000, 76000, 54000, 38000, 22000, 15000]
cumulative = np.cumsum(revenue) / sum(revenue) * 100

fig, (ax1, ax2) = plt.subplots(1, 2, figsize=(14, 6))

# Left: Highlight story — top 3 = 80% of revenue
colors = [&#039;#1565C0' if i < 3 else '#B0BEC5' for i in range(len(products))]
bars = ax1.bar(products, [r/1000 for r in revenue], color=colors, edgecolor=&#039;white')
ax1.set_xticklabels(products, rotation=35, ha=&#039;right')
ax1.set_ylabel(&#039;Revenue ($K)')
top3_total = sum(revenue[:3]) / sum(revenue) * 100
ax1.text(0.98, 0.96, f&#039;Top 3 products = {top3_total:.0f}%\nof total revenue',
          transform=ax1.transAxes, ha=&#039;right', va='top', fontsize=12, fontweight='bold',
          color=&#039;#1565C0', bbox=dict(boxstyle='round', facecolor='#E3F2FD'))
ax1.set_title("80/20 Insight: 3 Products Drive 73% of Revenue", fontweight=&#039;bold')

# Right: Pareto chart
ax2.bar(products, [r/1000 for r in revenue], color=colors, edgecolor=&#039;white')
ax2r = ax2.twinx()
ax2r.plot(products, cumulative, &#039;r-o', linewidth=2, label='Cumulative %')
ax2r.axhline(y=80, color=&#039;orange', linestyle='--', linewidth=1.5, label='80% line')
ax2r.set_ylabel(&#039;Cumulative Revenue (%)', color='red')
ax2r.set_ylim(0, 110)
ax2.set_title("Pareto Chart (80/20 Rule)", fontweight=&#039;bold')
ax2.set_xticklabels(products, rotation=35, ha=&#039;right')

for ax in [ax1, ax2]:
    ax.spines[&#039;top'].set_visible(False)
    ax.grid(True, axis=&#039;y', alpha=0.3)

plt.tight_layout()
plt.savefig(&#039;pareto_story.png', dpi=150, bbox_inches='tight')
plt.show()