Skip to content
pasted_image_0_(1)
Nicholas Fairnak - Business Analytics

This portfolio showcases a curated selection of data-driven projects that reflect my technical capabilities, problem-solving mindset, and focus on real-world impact.

  • Project 1 – NFL Season Optimization
  • Project 2 – Housing Market Trend Analysis
  • Project 3 – Competitive Strategy Simulation

Each project combines analytical thinking with practical execution, highlighting my skills in Python, R, SQL, Power BI, and optimization modeling. Please scroll down the page for more information.

 

NFL 2025 Season Optimization: Minimizing Travel

Built an NFL scheduling optimization model to minimize total team travel across the 2025–26  regular season. Using AMPL and Python in  Google Colab, we modeled 272 games with  real-world constraints, including bye weeks,  home/away limits, and matchup rules.

  • Developed a binary integer program with a travel-minimizing objective
  • Implemented a 6-7-4 matchup format to simplify standings-based scheduling
  • Enforced logic constraints (e.g., no duplicates, no teams playing themselves)
  • Created visualizations with Matplotlib and Seaborn to present insights
  • Delivered a presentation communicating technical results to a non-technical audience
Why this matters?
Why this matters!
•$12B+ in NFL Revenue (2022)
•Packers reported $541M in team expenses that year.
•Travel = Major Hidden Cost
•Commercial Airlines Avoid the NFL
•Small travel reduction = big savings + lower fatigue.
Building the Model

Building the Model

AMPL Coding for the models parameters, binary variables, and objective function.

Constraints

• Each team plays exactly 17 games across 18 weeks
• 6 divisional games per team (home and away against each rival)
• One game per team per week, plus one designated bye week
• Division rivals must face off exactly twice
• Teams receive 8 or 9 home games to match NFL policy
• No more than 32 total games scheduled per week
These are just a few of the constraints used to ensure the schedule remains fair, realistic, and aligned with NFL rules.

Travel Heatmap
•Weekly travel for every team across the season
•Red cells = high mileage weeks
•Identify fatigue risk
•No team has extreme travel
•Confirms our model promotes fair distribution of distance.
Optimal Solution

Output for Week 1. The model generates all 18 weeks at once.

Optimal Solution: 301,442 miles traveled. This is mulitplied by 2 to account for flights back. 

Weekly Travel Load
•Most weeks are balanced in terms of travel
•Outliers show long distance matches
•Helps identify potential fatigue or unfairness
Travel Map

Travel Map

One-way travel for all 32 teams across the season, created with Python packages.

Housing Market Trends: Analysis

This project analyzed housing and rental market trends using Zillow House Value Index (ZHVI) data across Wake County, North Carolina metro areas, and select national markets.

Using R and Tidyverse tools, I explored how property values have changed over the past decade, identified regional differences, and built visualizations to highlight both historical patterns and future projections.

  • Identified overall price trends, market dips, and affordability differences between high- and low-cost regions.
  • Compared national metro markets (Chicago, Denver, Houston, New York) to highlight stability, volatility, and affordability gaps.
  • Produced forecast models projecting short- and long-term housing value changes, revealing a broad dip in 2023 with New York expected to lead future growth.
Screenshot 2025-09-04 at 11.08.45 AM
Wake County Home Sales (2013-2023)
• Shows the rising trend of home values across towns in Wake County.
 
• Identifies the peak in 2022 followed by a dip in 2023
 
• Cary stands out as the most expensive area, Zebulon as the least
Screenshot 2025-09-04 at 11.09.16 AM

Rental Costs in NC (2015-2023)

• Displays average rental cost growth in Asheville, Charlotte, Durham, Fayetteville, Raleigh, and Wilmington.

• Every city shows a sharp increase, with Asheville highest and Fayetteville lowest.

Screenshot 2025-09-04 at 11.06.54 AM-1

Home Values in NC Metro Areas (2013-2023)

• Violin and box plots comparing Asheville, Charlotte, Raleigh-Cary, and Wilmington. 

• Charlotte-Concord-Gastonia has the lowest median home value; Wilmington shows the highest outliers (luxury homes).

• Asheville has the densest cluster around its median. 

Screenshot 2025-09-04 at 11.07.50 AM
National Home Sales Comparison (2013-2023) 
• Trends in Chicago, Denver, Houston, and New York.
 
• Houston most affordable, New York least affordable.
 
• Denver and New York had the largest price increases, while Chicago remained stable.
 
• In 2023, values dipped in New York, Denver, and Chicago but held steady in Houston.
 
 
Screenshot 2025-09-04 at 12.49.10 PM

 Future Home Value Projections (2024-2025) 

• Forecasts short- and long-term home value changes for Chicago, Denver, Houston, and New York.
 
• Short-term projections show slight decreases across all cities, especially Chicago and Denver.
 
• Over 12 months, New York is projected to see the largest percentage increase 

Competitive Strategy Simulation

For my undergraduate capstone project I served as the Research and Development lead in our Capsim Business Simulation. For 8 weeks our team competed across five market segments, forecasting sales and adjusting products, pricing, marketing, and production each week.

My role focused on repositioning products meet consumer demands while ensuring long-term profitability and competitive advantage. 

  • Provided the best product in each segment (Broad Differentiation Strategy)
  • Segmentation & Forecasting: Analyzed customer demand and sales data across 5 market segments to reposition products and anticipate competitor moves.
  • Key Takeaways: This project required critical thinking and team based problem solving. By adapting strategies in response to weekly results, our team achieved 2nd place overall.
Screenshot 2025-09-04 at 9.10.40 AM
Perceptual Map (Round 3)
●Provide the best product each segments

 

●Increase reliability to block competitor strategies.

 

●Blend short term wins with long term gains.
 
Screenshot 2025-09-04 at 10.39.26 AM

Managing Product Drift
In the simulation, each product’s ideal position within its segment would shift every round, reflecting changing consumer preferences.

Determined when to reposition products versus when to maintain their current trajectory. This required balancing trade-offs:

● Strategic Timing: Sometimes moving a product early captured market share before competitors could adjust.

 

● Critical Thinking: Every decision demanded weighing short-term sales impact against long-term profitability and segment dominance.

Screenshot 2025-09-04 at 9.09.38 AM

Tactical Decisions

●Repositioned products

●Launched new low-end product
 
●Minimized revisions, shifted spending to TQM
Screenshot 2025-09-04 at 10.47.29 AM
Financial Results at end of project