┌─────────────────────────────────────────────────────────────────────────────┐
│                    ONBOARDING IN THE CUSTOMER JOURNEY                     │
├─────────────────────────────────────────────────────────────────────────────┤
│                                                                             │
│  ┌─────────────┐    ┌─────────────┐    ┌─────────────┐    ┌─────────────┐  │
│  │ Awareness   │    │ Consideration│    │ Onboarding  │    │ First       │  │
│  │ (Discover)  │ ──→ │ (Research)   │ ──→ │ (Acquire)   │ ──→ │ Transaction│  │
│  └─────────────┘    └─────────────┘    └─────────────┘    └─────────────┘  │
│                                                                             │
│  ┌──────────────────────────────────────────────────────────────────────┐   │
│  │                    THE ONBOARDING WINDOW                            │   │
│  │  (Critical window for customer engagement and activation)           │   │
│  └──────────────────────────────────────────────────────────────────────┘   │
│                                                                             │
└─────────────────────────────────────────────────────────────────────────────┘

┌─────────────────────────────────────────────────────────────────────────────┐
│                    FRICTIONLESS ONBOARDING FLOW                           │
├─────────────────────────────────────────────────────────────────────────────┤
│                                                                             │
│  Step 1                   Step 2                   Step 3                  │
│  ┌─────────────────┐     ┌─────────────────┐     ┌─────────────────┐      │
│  │ Personal        │     │ Identity        │     │ Account         │      │
│  │ Information     │ ──→ │ Verification    │ ──→ │ Setup           │      │
│  │ (1 min)         │     │ (2 min)         │     │ (1 min)         │      │
│  └─────────────────┘     └─────────────────┘     └─────────────────┘      │
│                                                                             │
│  Step 4                   Step 5                   Step 6                  │
│  ┌─────────────────┐     ┌─────────────────┐     ┌─────────────────┐      │
│  │ Funding         │     │ Card Activation │     │ First           │      │
│  │ Setup           │ ──→ │                 │ ──→ │ Transaction     │      │
│  │ (1 min)         │     │ (1 min)         │     │ (1 min)         │      │
│  └─────────────────┘     └─────────────────┘     └─────────────────┘      │
│                                                                             │
│  Total Time: 7 minutes                                                      │
│                                                                             │
└─────────────────────────────────────────────────────────────────────────────┘

# ===================================================================
# MODULE 2, LESSON 6: DIGITAL ONBOARDING AND CUSTOMER ACQUISITION
# ===================================================================

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 ONBOARDING AND CUSTOMER ACQUISITION")
print("="*70)

# ----------------------------------------------------------------
# PART A: ONBOARDING FUNNEL ANALYSIS
# ----------------------------------------------------------------

print("\n" + "-"*60)
print("PART A: Onboarding Funnel Analysis")
print("-"*60)

# Define onboarding funnel stages
stages = ['Application Started', 'Personal Info Completed', 'Identity Verified', 
          'Approved', 'Account Setup Complete', 'First Transaction']
counts = [10000, 7500, 6200, 4800, 3900, 3100]
conversion_rates = [100, 75, 62, 48, 39, 31]
drop_off = [0, 2500, 1300, 1400, 900, 800]

funnel_df = pd.DataFrame({
    'Stage': stages,
    'Count': counts,
    'Conversion Rate (%)': conversion_rates,
    'Drop-off': drop_off
})

print("Onboarding Funnel:")
print(funnel_df.to_string(index=False))

# Visualise funnel
fig, axes = plt.subplots(1, 2, figsize=(14, 6))

# Funnel bar chart
ax = axes[0]
colors = ['#2ecc71', '#27ae60', '#f1c40f', '#e67e22', '#e74c3c', '#c0392b']
bars = ax.barh(stages, counts, color=colors, alpha=0.7)

for bar, count, rate in zip(bars, counts, conversion_rates):
    ax.text(bar.get_width() + 200, bar.get_y() + bar.get_height()/2, 
            f'{count} ({rate}%)', ha='left', va='center', fontweight='bold')

ax.set_xlabel('Number of Customers')
ax.set_title('Onboarding Funnel')
ax.grid(True, alpha=0.3, axis='x')

# Drop-off analysis
ax = axes[1]
ax.barh(stages[1:], drop_off[1:], color='red', alpha=0.7)
ax.set_xlabel('Drop-off')
ax.set_title('Drop-off by Stage')
ax.grid(True, alpha=0.3, axis='x')

plt.tight_layout()
plt.savefig('onboarding_funnel.png', dpi=300, bbox_inches='tight')
plt.show()
print("Onboarding funnel visualisation saved as 'onboarding_funnel.png'")

# ----------------------------------------------------------------
# PART B: ONBOARDING TIME ANALYSIS
# ----------------------------------------------------------------

print("\n" + "-"*60)
print("PART B: Onboarding Time Analysis")
print("-"*60)

# Simulate onboarding time data
np.random.seed(42)
n_customers = 1000

times = {
    'Personal Info': np.random.gamma(2, 0.5, n_customers).clip(0.5, 5),
    'Identity Verification': np.random.gamma(2, 0.8, n_customers).clip(0.5, 8),
    'Approval': np.random.gamma(1.5, 0.5, n_customers).clip(0.2, 4),
    'Account Setup': np.random.gamma(2, 0.4, n_customers).clip(0.5, 3),
    'First Transaction': np.random.gamma(2, 0.6, n_customers).clip(0.5, 5)
}

time_df = pd.DataFrame(times)

print("Onboarding Time Statistics (minutes):")
print(time_df.describe())

# Visualise
fig, ax = plt.subplots(figsize=(12, 6))
time_df.boxplot(ax=ax)
ax.set_ylabel('Time (minutes)')
ax.set_title('Onboarding Time Distribution by Stage')
ax.grid(True, alpha=0.3)

plt.tight_layout()
plt.savefig('onboarding_time.png', dpi=300, bbox_inches='tight')
plt.show()
print("Onboarding time visualisation saved as 'onboarding_time.png'")

# ----------------------------------------------------------------
# PART C: CUSTOMER SEGMENT ONBOARDING
# ----------------------------------------------------------------

print("\n" + "-"*60)
print("PART C: Customer Segment Onboarding")
print("-"*60)

# Simulate segment onboarding data
segments = ['Digital Natives', 'Digital Adopters', 'Traditional', 'Small Business', 'Corporate']
completion_rates = [78, 68, 45, 65, 55]
avg_times = [4.2, 6.5, 10.2, 7.0, 8.5]
satisfaction = [82, 75, 62, 70, 68]

segment_df = pd.DataFrame({
    'Segment': segments,
    'Completion Rate (%)': completion_rates,
    'Average Time (min)': avg_times,
    'Satisfaction (CSAT)': satisfaction
})

print("Segment Onboarding Performance:")
print(segment_df.to_string(index=False))

# Visualise
fig, axes = plt.subplots(1, 2, figsize=(14, 5))

# Completion Rate
ax = axes[0]
bars = ax.bar(segments, completion_rates, color='teal', alpha=0.7)
ax.axhline(y=70, color='red', linestyle='--', label='Target (70%)')
ax.set_ylabel('Completion Rate (%)')
ax.set_title('Completion Rate by Segment')
ax.legend()
ax.grid(True, alpha=0.3)

# Time vs Satisfaction
ax = axes[1]
scatter = ax.scatter(avg_times, satisfaction, s=100, c=completion_rates, cmap='RdYlGn')
for i, segment in enumerate(segments):
    ax.annotate(segment, (avg_times[i] + 0.1, satisfaction[i] + 0.5))
ax.set_xlabel('Average Time (min)')
ax.set_ylabel('Satisfaction (CSAT)')
ax.set_title('Onboarding Time vs Satisfaction')
plt.colorbar(scatter, ax=ax, label='Completion Rate (%)')
ax.grid(True, alpha=0.3)

plt.tight_layout()
plt.savefig('segment_onboarding.png', dpi=300, bbox_inches='tight')
plt.show()
print("Segment onboarding visualisation saved as 'segment_onboarding.png'")

# ----------------------------------------------------------------
# PART D: ONBOARDING OPTIMISATION STRATEGIES
# ----------------------------------------------------------------

print("\n" + "-"*60)
print("PART D: Onboarding Optimisation Strategies")
print("-"*60)

optimisation = {
    "1. Simplify KYC": {
        "Actions": [
            "Implement AI-powered document verification.",
            "Use biometrics for identity verification.",
            "Enable video KYC for remote verification.",
            "Integrate with government databases."
        ],
        "Impact": "High",
        "Timeline": "0-6 months"
    },
    "2. Reduce Friction": {
        "Actions": [
            "Minimise data entry.",
            "Use progressive disclosure.",
            "Enable save and resume functionality.",
            "Provide real-time validation."
        ],
        "Impact": "High",
        "Timeline": "0-6 months"
    },
    "3. Personalise the Experience": {
        "Actions": [
            "Tailor questions based on customer segment.",
            "Use predictive analytics to pre-fill data.",
            "Provide personalised recommendations.",
            "Offer multi-language support."
        ],
        "Impact": "Medium",
        "Timeline": "6-12 months"
    },
    "4. Improve Communication": {
        "Actions": [
            "Send real-time progress updates.",
            "Provide clear next steps.",
            "Use personalised messaging.",
            "Offer support at each stage."
        ],
        "Impact": "Medium",
        "Timeline": "0-6 months"
    },
    "5. Measure and Optimise": {
        "Actions": [
            "Track funnel metrics.",
            "Monitor completion rates.",
            "A/B test onboarding flows.",
            "Collect and act on feedback."
        ],
        "Impact": "High",
        "Timeline": "Ongoing"
    }
}

for item, details in optimisation.items():
    print(f"\n{item}:")
    for action in details['Actions']:
        print(f"  • {action}")
    print(f"  Impact: {details['Impact']}")
    print(f"  Timeline: {details['Timeline']}")

# ----------------------------------------------------------------
# PART E: ONBOARDING SUCCESS METRICS
# ----------------------------------------------------------------

print("\n" + "-"*60)
print("PART E: Onboarding Success Metrics")
print("-"*60)

success_metrics = pd.DataFrame({
    'Metric': [
        'Completion Rate',
        'Average Time to Complete',
        'Abandonment Rate',
        'First Transaction Rate',
        'NPS (After Onboarding)',
        'CSAT (After Onboarding)',
        'Referral Rate',
        'Activation Rate (30 days)'
    ],
    'Current': [
        '62%',
        '8.5 min',
        '38%',
        '52%',
        '55',
        '72%',
        '8%',
        '45%'
    ],
    'Target': [
        '> 80%',
        '< 5 min',
        '< 20%',
        '> 70%',
        '> 70',
        '> 85%',
        '> 15%',
        '> 60%'
    ],
    'Status': ['🔴', '🔴', '🔴', '🔴', '🔴', '🔴', '🔴', '🔴']
})

print("Onboarding Success Metrics:")
print(success_metrics.to_string(index=False))

# ----------------------------------------------------------------
# PART F: ONBOARDING TECHNOLOGY STACK
# ----------------------------------------------------------------

print("\n" + "-"*60)
print("PART F: Onboarding Technology Stack")
print("-"*60)

tech_stack = {
    "Identity Verification": {
        "Technologies": ["Onfido", "Jumio", "Trulioo", "Idemia"],
        "Capabilities": ["Document verification", "Biometrics", "Liveness detection"]
    },
    "KYC/AML": {
        "Technologies": ["ComplyAdvantage", "LexisNexis", "FICO", "SAS"],
        "Capabilities": ["Sanctions screening", "PEP checks", "Risk scoring"]
    },
    "Application Management": {
        "Technologies": ["Salesforce", "Pega", "Appian"],
        "Capabilities": ["Application orchestration", "Workflow management", "CRM"]
    },
    "Analytics": {
        "Technologies": ["Google Analytics", "Mixpanel", "Amplitude"],
        "Capabilities": ["Funnel analytics", "User behaviour", "A/B testing"]
    },
    "Communication": {
        "Technologies": ["Twilio", "SendGrid", "Braze"],
        "Capabilities": ["Email", "SMS", "Push notifications", "WhatsApp"]
    }
}

print("Onboarding Technology Stack:")
for layer, details in tech_stack.items():
    print(f"\n{layer}:")
    print(f"  Technologies: {', '.join(details['Technologies'])}")
    print(f"  Capabilities: {', '.join(details['Capabilities'])}")

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

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

print("""
Digital Onboarding and Customer Acquisition – Key Takeaways:

1. Digital onboarding is critical for customer acquisition and retention.
2. Key stages: discovery, application, verification, approval, setup, first transaction.
3. Digital KYC (eKYC) includes document verification, biometrics, and liveness detection.
4. Friction reduction: minimal input, auto-fill, real-time validation, progressive disclosure.
5. Regulatory compliance: AML/KYC, GDPR, PSD2, fair lending.
6. Key metrics: completion rate, time to complete, abandonment, activation.
7. Optimisation: simplify KYC, reduce friction, personalise, measure and improve.

Recommendations:
  - Simplify KYC with AI-powered verification.
  - Reduce friction with minimal data entry.
  - Personalise the onboarding experience.
  - Measure and optimise funnel metrics.
  - Ensure regulatory compliance.
  - Use technology to automate and scale.
""")

print("="*70)
print("END OF LESSON 6 – MODULE 2")
print("="*70)