Within professional basketball, each player, game, team, and season produces massive amounts of data. Data analytics has changed the strategic goals made by players, coaches, general management, and even fans.  By creating a model that can predict maximum winning based on talent, teams can evaluate their managers’ performance and therefore make actions to achieve strategic goals. Finding a reliable regression model to predict team wins each season has proven to be a very difficult task. Since the early 2000s, basketball has seen a lot of change and sports analysts and economists alike have tried to make more accurate models. My research used an expanded regression model based off Dean Oliver’s Four Factors model to predict NBA and WNBA teams’ wins.  Compiling regular season statistics for the 10 years between 2013 to 2022 and using 8 variables, my goal is to evaluate the model’s effectiveness in predicting WNBA wins compared to NBA wins. This area of study, especially regarding comparing differences between NBA and WNBA, has a lot of opportunity for further expansion. The model showed statistically significant results for both the NBA and the WNBA over the analyzed time period, with more accurate predictability for the WNBA. The implications of these results may impact game day decisions or the evaluation of marginal value contributions from players allowing for continued study in this field.

Kylie would like to thank her economics professor and mentor, Dave Sanders. Kylie got the opportunity to take Professor Sanders’ Sports Economics class in the Fall of 2022, where she began her research. Professor Sanders has informed her of best practices in economics research and supported her in her research with encouragement and guidance.