Professor Aven


Tutorial Overview

This tutorial guides students through a structured LinkedIn network analysis using AI-assisted tools (Microsoft Copilot, ChatGPT, or similar - just be cautious with your data) to diagnose their professional network positioning, identify strategic gaps, and develop a targeted network growth plan.

Module Context

Module 2 of the final project: Professional Network Analysis (LinkedIn)

This is the first of five diagnostic modules that build toward your comprehensive leadership profile:

  1. Class Network Analysis
  2. Professional Network Analysis (LinkedIn) ← You are here
  3. Organizational Structure Diagnostic
  4. Cultural Environment Audit
  5. Strategic Leadership Synthesis

Quick Facts

Tools Required:

  • LinkedIn account with downloadable contact data
  • AI Tool: Microsoft Copilot (via M365) or ChatGPT Plus
  • Excel or Google Sheets

Deliverable: Analysis + visuals for Section 2 of final project

Learning Objectives

By completing this analysis, students will be able to:

  1. Export and clean professional network data from LinkedIn
  2. Diagnose network composition across industries, companies, and roles
  3. Identify structural gaps relative to career goals
  4. Map network positioning using industry classification systems (NAICS/GICS)
  5. Design strategic interventions to build a more effective professional network
  6. Apply social network concepts (structural holes, brokerage, homophily) to personal career strategy

Theoretical Foundation

Social Capital Theory

Networks as strategic assets

  • Strength of weak ties (Granovetter, 1973)
  • Structural holes and brokerage (Burt, 1992)

Network Composition

  • Homophily: Tendency to connect with similar others
  • Network diversity and access to novel information
  • Industry clustering and career mobility

Strategic Networking

  • Intentional vs. emergent network formation
  • Network maintenance costs
  • Boundary spanning and cross-industry ties

Step-by-Step Tutorial

Step 1: Export Your LinkedIn Connections

  1. Log into LinkedIn
  2. Navigate to Settings & Privacy → Data Privacy → Get a copy of your data
  3. Select “Connections” only (faster download)
  4. Click “Request archive”
  5. LinkedIn will email you a download link (usually within 10 minutes)
  6. Download the Connections.csv file

Expected format:

First Name, Last Name, Email Address, Company, Position, Connected On

Important Notes:

  • You’ll have ~1,000-3,000+ contacts typically
  • Many entries will have missing company or position data
  • Email addresses are rarely populated (LinkedIn privacy)

Step 2: Upload to AI Tool and Initial Cleaning

Prompt 1: Data Cleaning & Basic Analysis
Help me clean and analyze my LinkedIn Contacts. 

To clean: 
1) Clean names of special characters
2) Normalize Company names (e.g., "Amazon.com" → "Amazon", 
   "CMU" → "Carnegie Mellon University")

To analyze: 
1) Count the number of contacts per Company and provide 
the top 5 companies with the most contacts
2) Look up the top 10 companies and research what industries 
they belong to
3) Count the unique job types by the number of contacts and 
provide the top 5 job titles

What to Expect

  • AI will clean special characters (é, ñ, symbols in names)
  • Company name normalization (consolidating variations)
  • Summary tables showing:
    • Top 5 companies by contact count
    • Top 10 companies with industry classifications
    • Top 5 job titles/positions in your network

Example Output Structure

Example: Top 5 Companies by Contact Count
Rank Company Contacts
1 Amazon 63
2 Carnegie Mellon University - Tepper School of Business 52
3 Unknown 40
4 Carnegie Mellon University 28
5 Microsoft 25

Interpretation Guide

Pattern Observed Implication
High concentration in one company May indicate limited network diversity
Academic institutions dominant Network may be research-focused
Tech companies clustering Industry-specific network structure
Many “Unknown” entries Data quality issues or unemployed/student contacts

Key Questions to Ask:

  • High concentration in one company? → May indicate limited network diversity
  • Academic institutions dominant? → Network may be research-focused
  • Tech companies clustering? → Industry-specific network structure
  • Many “Unknown” entries? → Data quality issues or network decay

Step 2.2: Industry Sector Classification

Prompt 2: Deep Industry Analysis

Show industry sectors for the top 10 companies in my network. 
Use official classification systems like NAICS (North American Industry 
Classification System) and GICS (Global Industry Classification Standard).

What to Expect

  • Detailed industry breakdown with official codes
  • Sector classifications (Technology, Financial Services, Education, Healthcare, etc.)
  • Understanding of which economic sectors you’re embedded in

Example Output

Example: Industry Classification with Official Codes
Company NAICS GICS Sector
Amazon 518210 Internet & Direct Marketing Retail Technology
Microsoft 511210 Software Technology
PwC 541611 Professional Services Consulting
Carnegie Mellon University 611310 Education Services Education

Why This Matters

Career mobility: Tech-to-Finance transitions are harder than Tech-to-Tech

Information access: Homogeneous networks = redundant information

Opportunity risk: Over-concentration in declining industries

Step 2.3: Complete Sector Mapping

Prompt 3: Full Network Classification

Generate a complete list of all unique normalized companies in my network and their respective sectors. 
Provide this as a downloadable CSV file.

What to Expect

  • Complete company-to-sector mapping
  • Downloadable file for further analysis
  • Foundation for visualization and gap analysis

Action Item

  • Download the CSV file
  • Save it with your assignment materials
  • You’ll use this for sector distribution analysis

Step 3: Network Composition Visualization

Prompt 4: Visual Analysis & Trend Insights
Create a visual summary of sector distribution in my network 
(e.g., pie chart or bar chart).

Then provide insights on:
1) Which sectors dominate my network
2) Which sectors are underrepresented
3) What this distribution reveals about my network's strategic positioning

What to Expect

  • Visual representation (pie chart or bar chart) showing % of contacts by sector
  • Narrative analysis of your network composition
  • Identification of homophily patterns (e.g., “80% of your network is in Technology”)

Example Visualization

Example: Sector Distribution in Professional Network

Example: Sector Distribution in Professional Network

Interpretation Framework

How to Interpret Network Composition
Sector Dominance Implication Risk
>50% in one sector Deep industry embeddedness Limited cross-industry mobility; echo chamber
Balanced across 4-5 sectors Diverse information access May lack depth in any single domain
Heavy in Education/Academia Research-oriented network May lack industry connections for commercialization

Strategic Benchmarking

Step 4: Ideal Network Composition

Prompt 5: Personalized Benchmark
As a [YOUR ROLE: e.g., "MBA student interested in product management at tech companies" OR "consultant transitioning to venture capital"] What would be the ideal composition of LinkedIn contacts across industries?

Provide:
1) Recommended % distribution across sectors
2) Rationale for each sector
3) Key roles/titles I should prioritize in each sector

What to Expect

  • AI will generate an “ideal” network composition tailored to your career goals
  • Percentage targets for each industry sector
  • Rationale explaining why each sector matters for your trajectory

Example Output for Different Career Paths

Example Ideal Network Compositions by Career Goal (%)
Career Goal Tech Consulting Finance Target Industry Academia Other
Tech PM 40 10 5 30 15 0
VC Investor 30 15 20 25 10 0
Healthcare Exec 15 20 10 40 15 0
Professor (R1) 20 10 5 20 45 0
Management Consultant 20 35 10 15 10 10

Customize This Prompt

Students should adapt the prompt to their specific goals:

  • MBA → Consulting: Heavier in Professional Services, lighter in Academia
  • Engineer → Startup: Heavier in VC/Entrepreneurship, lighter in Corporate
  • Consultant → Corporate Strategy: Balance between Consulting and target industry

Step 5: Gap Analysis & Recommendations

Prompt 6: Visual Comparison & Action Plan

Create a visual comparison showing:
1) My CURRENT network composition by sector (%)
2) My IDEAL network composition by sector (%)
3) The GAP between current and ideal

Then provide actionable recommendations:
- Which sectors should I expand in
- Specific companies and roles to target
- LinkedIn strategies to close these gaps
- A 12-month network growth roadmap

What to Expect

  • Side-by-side comparison (bar chart or table)
  • Clear identification of over/underrepresented sectors
  • Specific, tactical recommendations

Example Gap Analysis

Example: Current vs. Ideal Network Composition

Example: Current vs. Ideal Network Composition

Example Gap Analysis Table

Gap Analysis Summary: Where to Focus Network Building
Sector Current Ideal Gap Action
Education 45% 40% +5% ⚠️ Overrepresented - Diversify away
Technology 20% 25% -5% ✅ Target: Add 50+ tech contacts
Policy/Nonprofit 1% 5% -4% ✅ Critical gap - Add 20+ contacts
Healthcare 5% 10% -5% ✅ Strategic priority - Add 30 contacts
Professional Services 12% 10% +2% ⚠️ Slight overweight
Financial Services 8% 5% +3% ⚠️ Slight overweight

Tactical Recommendations Example

Underrepresented Sectors to Target:

Policy & Nonprofit (Critical Gap: -4%)

  • Companies to target: Brookings Institution, RAND Corporation, World Bank, local government agencies
  • Roles to connect with: Policy Analyst, Program Director, Research Fellow
  • How to connect: Join LinkedIn groups like “Public Policy Network,” attend policy conferences

Healthcare (Moderate Gap: -3%)

  • Companies to target: Mayo Clinic, Cleveland Clinic, UPMC
  • Roles to connect with: Chief Medical Officer, Healthcare Operations Manager, HR Leadership
  • How to connect: Leverage CMU alumni in healthcare, engage with Healthcare Leadership Network

12-Month Network Growth Roadmap

Example: 12-Month Network Growth Roadmap
Timeframe Focus Area Specific Actions Target #
Months 1-3 Audit & Clean Remove inactive contacts; reclassify ‘Other’ category -50 contacts
Months 4-6 Expand Policy & Nonprofit Join 2 policy-focused LinkedIn groups; attend 1 conference +20 contacts
Months 7-9 Deepen Tech & Healthcare Connect with alumni in target companies; engage thought leaders +45 contacts
Months 10-12 Thought Leadership Publish 3 LinkedIn articles; speak at 1 conference +30 contacts

What to Submit: LinkedIn Professional Network Analysis

2.1 LinkedIn Network Overview

  • Table: Top 10 companies by number of contacts
  • Table: Top 10 job titles/positions in your network
  • Visualization: Sector distribution (pie chart or bar chart)

Narrative interpretation:

  • What patterns do you observe?
  • What does this reveal about your network’s current structure?

2.2 Strategic Gap Analysis

  • Table or Chart: Current vs. Ideal network composition

Identification of gaps:

  • Which sectors are overrepresented? Why might this be?
  • Which sectors are underrepresented? What opportunities are you missing?

Structural implications:

  • How does your current composition affect information access?
  • Where are structural holes you could bridge?
  • What career risks does your composition create?

2.4 Network Growth Strategy

  • Specific targets: 3-5 sectors/companies/roles to prioritize
  • Tactical plan: How will you strategically add connections in the next 6-12 months?
  • Maintenance plan: How will you avoid network decay?

Common Pitfalls & Solutions

Pitfall #1: “My network looks fine”

Problem: Students accept their current network without critical analysis

Solution: Force the comparison—ask “Compared to whom?” and “For what goal?”

Pitfall #2: Treating all connections equally

Problem: Not distinguishing between strong ties, weak ties, and dormant ties

Solution: While LinkedIn data doesn’t show tie strength, reflect on: How many of your contacts would respond if you messaged them today?

Pitfall #3: Quantity over quality

Problem: Focusing on total number of connections rather than strategic positioning

Solution: Emphasize network architecture (diversity, brokerage potential) over network size

Pitfall #4: Static analysis

Problem: Treating network analysis as a one-time exercise

Solution: Frame this as a repeatable diagnostic students can run annually

Pitfall #5: Over-relying on AI without interpretation

Problem: Copy-pasting AI outputs without critical thinking

Solution: Every AI-generated insight must be interrogated: “Why does the AI recommend this? Does this align with network theory? Does this fit MY goals?”

Potential Issues

Problem #1: Too many “Unknown” companies in my data

Solution: This is normal (people change jobs, leave fields blank). Focus analysis on contacts with complete data. Reflect on why so many are unknown—recent connections? Network decay?

Problem #2: AI tool hallucinates industry classifications

Solution: Spot-check AI’s NAICS/GICS codes against official sources (census.gov, msci.com).

Problem #3: My network is 90% in one sector—is this bad?

Solution: Not inherently! Depends on your goals. Deep sector expertise vs. cross-industry brokerage are different strategies. Analyze the opportunity cost of your current structure.

Problem #4: I don’t know what my “ideal” network should look like

Solution: Research 3-5 people in roles you aspire to. Look at their LinkedIn profiles (if public). Reverse-engineer their network composition.

Connection to Class Concepts

Brokerage

Are you positioned to bridge across industries?

Strategic Implications

Concept Application to LinkedIn Analysis
Information diversity Homogeneous networks = redundant information
Career mobility Network composition predicts job search success
Risk exposure Over-concentration = vulnerability to industry downturns

Appendix: Complete Prompt Library

PROMPT 1: Data Cleaning & Initial Analysis

Help me clean and analyze my LinkedIn Contacts. To clean: 1) Clean names 
of special characters; 2) Normalize Company names. To analyze: 1) count 
the number of contacts per Company and provide the top 5 companies with 
the most contacts; 2) look up the top 10 companies and research what 
industries; 3) count the unique job types by the number of contacts and 
provide the top 5

PROMPT 2: Industry Classification

Show industry sectors for top 10 companies using official NAICS and GICS 
classification systems.

PROMPT 3: Full Network Mapping

Generate a complete list of all unique normalized companies and their 
respective sectors. Provide as a downloadable CSV.

PROMPT 4: Visualization & Insights

Create a visual summary (e.g., pie chart of sector distribution). Enhance 
the mapping with official NAICS/GICS codes for top companies. Provide 
insights on sector trends in my network.

PROMPT 5: Ideal Benchmark (CUSTOMIZE THIS)

As a [YOUR SPECIFIC ROLE/GOAL] what would be the ideal composition of 
contacts across industries? Provide recommended % distribution and rationale.

PROMPT 6: Gap Analysis & Strategy

Create a visual comparison showing my current vs ideal network composition. 
Provide actionable recommendations including: which sectors to expand, 
specific companies and roles to target, LinkedIn strategies, and a 
12-month network growth roadmap.

Key Takeaways

By the end of this assignment, you should be able to answer:

  1. Diagnostic: How is my professional network currently structured?
  2. Comparative: How does my network compare to what I need for my career goals?
  3. Analytical: What do network theories (structural holes, weak ties, homophily) reveal about my positioning?
  4. Strategic: What specific actions will I take to architect a more effective network?
  5. Reflective: How does my network reflect my values, biases, and past experiences?

Document Version: 1.0
Last Updated: December 2025
Course: Leading by Design - People Analytics Diagnostic
Institution: Carnegie Mellon University, Tepper School of Business