Using lpSolve in R to Optimize Picks in a 2023 NFL Survivor Pool

<h2>What is a NFL Survivor Pool?</h2> <p>In a survivor pool you pick one NFL team to win (no spreads) each week, and if your team wins you move on, if they lose or tie you are eliminated. The catch is you can only pick a team once. The last person/people standing at the end of the 18 week regular season will be winners and take home the money.</p> <h2>Our Problem to be Optimized</h2> <p>We want to select teams to win each week that gives us the best chance of winning over the entire season, not just looking at weeks individually. What do I mean by this? Say in week 1, Team A is 10 point favorites and the next biggest favorite is Team B who are 7 point favorites. Logically you would say we choose Team A in week 1, which might be accurate. However, what if Team A is 13 point favorites in week 10 and Team B is never more than 3 point favorites again in the season? Wouldn’t it make sense to choose Team B week 1 and maybe wait to week 10 to choose Team A? This gets further complicated by the fact that there are 32 teams and 18 weeks of regular season. Toss in injuries and you have a very complex mathematical problem.</p> <h2>Team Rankings and Optimizer</h2> <p>Last year I used <a href="https://medium.com/@drewjosselyn/using-linear-programming-to-optimize-picks-in-a-nfl-survivor-pool-79e9cdbdc81e" rel="noopener">Excel Solver</a> to optimize my picks in a 2022 Survivor Pool. Unfortunately, Excel Solver is limited to ≤ 200 variables, which only allowed me to optimize based on a five-week window. So how did I do? I lost Week 1… Now you might ask me, why should we listen to your picks in 2023 if you were terrible in 2022? My answer is, <strong>you shouldn’t</strong>. BUT, last year I used the <a href="https://www.espn.com/nfl/fpi" rel="noopener ugc nofollow" target="_blank">NFL Football Power Index</a> (FPI) to rank my teams. This is a purely data based metric, which means I was using a pure data approach to make my selections. Any good Data Analyst will tell you, you need a human’s knowledge in combination with data to make good, informed, data driven decisions, never just data alone.</p> <p><strong>Read More</strong></p>