┌─────────────────────────────────────────────────────────────────────────────┐
│                    CHANNEL PREFERENCES BY SEGMENT                         │
├─────────────────────────────────────────────────────────────────────────────┤
│                                                                             │
│  ┌──────────────────────────────────────────────────────────────────────┐   │
│  │                    DIGITAL NATIVES (18-35)                          │   │
│  │  Mobile First | Chatbots | Social Media | Voice                    │   │
│  └──────────────────────────────────────────────────────────────────────┘   │
│                                                                             │
│  ┌──────────────────────────────────────────────────────────────────────┐   │
│  │                    DIGITAL ADOPTERS (36-55)                         │   │
│  │  Mobile + Web | Email | Some Branch/ATM                           │   │
│  └──────────────────────────────────────────────────────────────────────┘   │
│                                                                             │
│  ┌──────────────────────────────────────────────────────────────────────┐   │
│  │                    DIGITAL IMMIGRANTS (56+)                         │   │
│  │  Branch | Web | Phone | Some Mobile                                │   │
│  └──────────────────────────────────────────────────────────────────────┘   │
│                                                                             │
│  ┌──────────────────────────────────────────────────────────────────────┐   │
│  │                    SMALL BUSINESSES                                 │   │
│  │  Web | Mobile | Contact Centre | Branch                            │   │
│  └──────────────────────────────────────────────────────────────────────┘   │
│                                                                             │
│  ┌──────────────────────────────────────────────────────────────────────┐   │
│  │                    CORPORATE CLIENTS                                │   │
│  │  Web | API | Contact Centre | Relationship Manager                 │   │
│  └──────────────────────────────────────────────────────────────────────┘   │
│                                                                             │
└─────────────────────────────────────────────────────────────────────────────┘

┌─────────────────────────────────────────────────────────────────────────────┐
│                    CHANNEL MIGRATION PATTERNS                             │
├─────────────────────────────────────────────────────────────────────────────┤
│                                                                             │
│  Stage 1           Stage 2           Stage 3           Stage 4             │
│  ┌─────────┐      ┌─────────┐      ┌─────────┐      ┌─────────┐          │
│  │ Branch  │      │ Online  │      │ Mobile  │      │ Mobile  │          │
│  │ First   │ ──→  │ Banking │ ──→  │ Banking │ ──→  │ + AI    │          │
│  │ (70%)   │      │ (60%)   │      │ (50%)   │      │ (70%)   │          │
│  └─────────┘      └─────────┘      └─────────┘      └─────────┘          │
│                                                                             │
│  Traditional       Digital            Mobile             AI-Powered        │
│  Dominance         Adoption           Dominance          Personalisation   │
│                                                                             │
└─────────────────────────────────────────────────────────────────────────────┘

# ===================================================================
# MODULE 2, LESSON 1: CHANNEL ANALYTICS DASHBOARD
# ===================================================================

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns
from datetime import datetime, timedelta
import warnings
warnings.filterwarnings('ignore')

print("="*70)
print("DIGITAL BANKING CHANNELS – ANALYTICS DASHBOARD")
print("="*70)

# ----------------------------------------------------------------
# PART A: CHANNEL ADOPTION DATA
# ----------------------------------------------------------------

print("\n" + "-"*60)
print("PART A: Channel Adoption Data")
print("-"*60)

# Define channel adoption data
channels = ['Mobile App', 'Online Banking', 'Branch', 'Contact Centre', 'ATM', 'Chatbot', 'Voice Banking', 'Wearable']
adoption_2024 = [75, 65, 35, 25, 60, 25, 8, 5]
adoption_2028 = [88, 72, 25, 28, 55, 55, 25, 15]
growth = [(adoption_2028[i] - adoption_2024[i]) / adoption_2024[i] * 100 for i in range(len(adoption_2024))]

channel_df = pd.DataFrame({
    'Channel': channels,
    '2024 Adoption (%)': adoption_2024,
    '2028 Adoption (%)': adoption_2028,
    'Growth (%)': growth
}).sort_values('Growth (%)', ascending=False)

print("Channel Adoption Forecast:")
print(channel_df.to_string(index=False))

# ----------------------------------------------------------------
# PART B: CHANNEL PREFERENCE BY AGE GROUP
# ----------------------------------------------------------------

print("\n" + "-"*60)
print("PART B: Channel Preference by Age Group")
print("-"*60)

# Simulate channel preference data by age group
age_groups = ['18-25', '26-35', '36-45', '46-55', '56-65', '65+']
channel_pref = {
    'Mobile App': [92, 88, 78, 65, 45, 25],
    'Online Banking': [45, 55, 65, 70, 68, 55],
    'Branch': [12, 18, 28, 38, 52, 65],
    'Contact Centre': [8, 12, 18, 25, 35, 45],
    'Chatbot': [45, 40, 30, 20, 10, 5]
}

pref_df = pd.DataFrame(channel_pref, index=age_groups)
print("Channel Preference by Age Group (%):")
print(pref_df)

# Visualise
fig, ax = plt.subplots(figsize=(12, 6))
pref_df.plot(kind='bar', ax=ax, linewidth=2)
ax.set_xlabel('Age Group')
ax.set_ylabel('Preference (%)')
ax.set_title('Channel Preference by Age Group')
ax.legend(loc='best')
ax.grid(True, alpha=0.3)
plt.tight_layout()
plt.savefig('channel_preference.png', dpi=300, bbox_inches='tight')
plt.show()
print("Channel preference visualisation saved as 'channel_preference.png'")

# ----------------------------------------------------------------
# PART C: CHANNEL PERFORMANCE METRICS
# ----------------------------------------------------------------

print("\n" + "-"*60)
print("PART C: Channel Performance Metrics")
print("-"*60)

# Simulate channel performance data
performance_data = {
    'Channel': ['Mobile App', 'Online Banking', 'Branch', 'Contact Centre', 'ATM', 'Chatbot'],
    'Usage (%)': [75, 60, 35, 25, 60, 20],
    'Satisfaction (CSAT)': [88, 82, 78, 72, 85, 80],
    'Effort Score (CES)': [1.8, 2.2, 2.8, 3.0, 2.0, 1.6],
    'Cost per Transaction ($)': [0.25, 0.50, 4.50, 3.00, 1.00, 0.15],
    'Conversion Rate (%)': [72, 65, 55, 48, 60, 58]
}

perf_df = pd.DataFrame(performance_data)
print("Channel Performance Metrics:")
print(perf_df.to_string(index=False))

# Visualise performance
fig, axes = plt.subplots(1, 3, figsize=(15, 5))

# Satisfaction
ax = axes[0]
ax.bar(perf_df['Channel'], perf_df['Satisfaction (CSAT)'], color='green', alpha=0.7)
ax.axhline(y=80, color='red', linestyle='--', label='Target (80%)')
ax.set_ylabel('CSAT (%)')
ax.set_title('Channel Satisfaction')
ax.legend()
ax.grid(True, alpha=0.3)

# Cost per Transaction
ax = axes[1]
ax.bar(perf_df['Channel'], perf_df['Cost per Transaction ($)'], color='blue', alpha=0.7)
ax.set_ylabel('Cost per Transaction ($)')
ax.set_title('Channel Cost')
ax.grid(True, alpha=0.3)

# Conversion Rate
ax = axes[2]
ax.bar(perf_df['Channel'], perf_df['Conversion Rate (%)'], color='orange', alpha=0.7)
ax.axhline(y=70, color='red', linestyle='--', label='Target (70%)')
ax.set_ylabel('Conversion Rate (%)')
ax.set_title('Channel Conversion')
ax.legend()
ax.grid(True, alpha=0.3)

plt.tight_layout()
plt.savefig('channel_performance.png', dpi=300, bbox_inches='tight')
plt.show()
print("Channel performance visualisation saved as 'channel_performance.png'")

# ----------------------------------------------------------------
# PART D: CHANNEL MIGRATION ANALYSIS
# ----------------------------------------------------------------

print("\n" + "-"*60)
print("PART D: Channel Migration Analysis")
print("-"*60)

# Simulate channel migration over time
years = ['2020', '2021', '2022', '2023', '2024']
migration_data = {
    'Mobile App': [45, 52, 60, 68, 75],
    'Online Banking': [55, 57, 58, 59, 60],
    'Branch': [55, 48, 42, 38, 35],
    'Contact Centre': [35, 32, 28, 26, 25],
    'ATM': [60, 62, 63, 64, 65],
    'Chatbot': [2, 5, 8, 11, 15]
}

migration_df = pd.DataFrame(migration_data, index=years)
print("Channel Migration Data (% usage):")
print(migration_df)

# Visualise migration
fig, ax = plt.subplots(figsize=(12, 6))
migration_df.plot(kind='line', marker='o', ax=ax, linewidth=2, markersize=8)
ax.set_xlabel('Year')
ax.set_ylabel('Usage (%)')
ax.set_title('Channel Migration Over Time')
ax.legend(loc='best')
ax.grid(True, alpha=0.3)
plt.tight_layout()
plt.savefig('channel_migration.png', dpi=300, bbox_inches='tight')
plt.show()
print("Channel migration visualisation saved as 'channel_migration.png'")

# ----------------------------------------------------------------
# PART E: CHANNEL ANALYTICS DASHBOARD
# ----------------------------------------------------------------

print("\n" + "-"*60)
print("PART E: Channel Analytics Dashboard")
print("-"*60)

# Create a summary dashboard
dashboard = pd.DataFrame({
    'Metric': [
        'Total Digital Users',
        'Mobile App Users',
        'Digital Penetration',
        'Mobile Transaction Share',
        'Average Session Duration (Mobile)',
        'Average Session Duration (Web)',
        'Digital Sales %',
        'Digital NPS',
        'Channel Cost Efficiency'
    ],
    'Value': [
        '4.2M',
        '3.1M',
        '78%',
        '62%',
        '8.5 min',
        '12.3 min',
        '54%',
        '72',
        '2.3x improvement'
    ],
    'Trend': ['📈', '📈', '📈', '📈', '📈', '📊', '📈', '📈', '📈'],
    'Target': ['5.0M', '4.0M', '85%', '70%', '10 min', '10 min', '60%', '75', '3.0x']
})

print("Channel Analytics Dashboard:")
print(dashboard.to_string(index=False))

# ----------------------------------------------------------------
# PART F: CHANNEL STRATEGY RECOMMENDATIONS
# ----------------------------------------------------------------

print("\n" + "-"*60)
print("PART F: Channel Strategy Recommendations")
print("-"*60)

strategy = {
    "Mobile App": {
        "Priority": "High",
        "Strategy": "Invest in AI-powered personalisation, push notifications, and mobile-first features.",
        "Actions": [
            "Implement predictive analytics for personalised offers.",
            "Add biometric authentication for security.",
            "Integrate chatbot for instant support."
        ]
    },
    "Online Banking": {
        "Priority": "Medium",
        "Strategy": "Optimise for complex transactions and financial planning.",
        "Actions": [
            "Enhance reporting and analytics features.",
            "Improve UX for financial planning tools.",
            "Add portfolio management capabilities."
        ]
    },
    "Branch": {
        "Priority": "Medium",
        "Strategy": "Transform from transactional to advisory role.",
        "Actions": [
            "Train staff for advisory services.",
            "Implement appointment scheduling.",
            "Add video conferencing capabilities."
        ]
    },
    "Chatbot/AI": {
        "Priority": "High",
        "Strategy": "Expand capabilities with generative AI.",
        "Actions": [
            "Implement generative AI for complex queries.",
            "Add multilingual support.",
            "Integrate with all banking services."
        ]
    },
    "Voice/Wearable": {
        "Priority": "Low",
        "Strategy": "Experiment and prepare for future adoption.",
        "Actions": [
            "Pilot voice banking.",
            "Develop wearable banking app.",
            "Monitor adoption and feedback."
        ]
    }
}

print("Channel Strategy Recommendations:")
for channel, details in strategy.items():
    print(f"\n{channel}:")
    print(f"  Priority: {details['Priority']}")
    print(f"  Strategy: {details['Strategy']}")
    print("  Actions:")
    for action in details['Actions']:
        print(f"    • {action}")

# ----------------------------------------------------------------
# PART G: SUMMARY AND RECOMMENDATIONS
# ----------------------------------------------------------------

print("\n" + "="*70)
print("PART G: Summary and Recommendations")
print("="*70)

print("""
Digital Banking Channels – Key Takeaways:

1. Digital channels include mobile app, online banking, chatbots, voice, wearables, and more.
2. Mobile banking is the dominant channel with the highest growth.
3. Channel adoption varies by age group and customer segment.
4. Key metrics: adoption, satisfaction, cost, conversion, and migration.
5. Channel migration is shifting customers from high-cost to low-cost channels.
6. AI and personalisation are key differentiators for digital channels.
7. Channel strategy must balance investment across channels.

Recommendations:
  - Invest in mobile app and chatbot capabilities.
  - Transform branches from transactional to advisory.
  - Implement AI-powered personalisation.
  - Measure and optimise channel performance.
  - Prepare for emerging channels (voice, wearables, metaverse).
""")

print("="*70)
print("END OF LESSON 1 – MODULE 2")
print("="*70)