Data Analysis

BPL Player Type Price Optimization

British Premier League Player Type Price Optimization

This project seeks to explore the frequent line-ups of successful & unsuccessful clubs constrained by finances. To investigate this problem, the researchers (1) built a game week over game week linear optimized model, (2) used actual club squad rosters, and conducted (3) dissimilarity analysis by drawing a network exhibiting the distance between maximized frequent itemsets and minimized itemsets.

The researchers clustered the players based on position, market value, & season points contributed; thus, appropriating a Gold, Silver, or Bronze tier to each player in a given season.

  1. The researchers built a maximization & minimization model to build an optimal, budgetconstrained squad. Then, the researchers will conduct Apriori analysis on the maximization and minimized game week transactions.
  2. Next, the researchers identified the top 25% and bottom 25% of teams in each season. Then, the researchers created squad transactions by identifying if a player played for a top or bottom club in the week. Then, the researchers conducted Apriori analysis on the top & worst teams in the season.
  3. Lastly, the researchers drew a dissimilarity network between the maximized and minimized frequent itemsets.

Results

  1. Invest in a strong gold tiered midfield accompanied by at least one strong wing back
  2. Tactically focus on transitional moments relative to establishing defense
  3. Above average Gold Midfielders score the expected value of Gold Forwards & provide more assists
  4. Gold Midfielders reap the highest return on capital investment
  5. Ensure tactics conform to the player combinations to generate fortunate results
  6. Although a team may contain the same quality line up combinations as top-flight clubs, it may perform as a relegation class team due to mismanagement.

Project Action

Github Project Link