About Our Work

The Oyster Model

Our models use MiLB performance, biographical, and draft data to predict prospects’ likelihood of making MLB, becoming a “regular” (at least 2 fWAR total, 1 per 600 PA) and a “star” (5 fWAR total, 2.5 per 600 PA). Our models are the first we’ve seen to assign probabilities to each player, and our visualizations allow users to check out every player from the DSL to Triple-A Our models are heavily based on a player’s offensive body of work in the minors and intentionally de-emphasize pedigree and hype.

Needless to say, they are comprehensive and completely infallible. Well, no, obviously not. While our models are unique and robust, there is of course no perfect way to predict prospect outcomes, so we are constantly updating our methodology and data to generate even stronger projections.

Our dashboard features all active hitters in MiLB. Check it out yourself and Tweet us to let us know how full of it we are!

Our Research at Down on the Farm

Since January 2025, we’ve been writing (at least) weekly articles for the Down on the Farm Substack. This is where we go deeper into our prospect evaluations and publish our wider ranger research projects. Some of our favorite research deep dives have been our analyses into how caution is costing teams on the base paths, ABS-related strategy, and where money is best spent in amateur player acquisition. You can also check out our pre-season top 50 hitting prospects, self-audits of our previous hot takes, and Beatles-themed prospect evaluations.

Subscribe to the Substack here, and give Down on the Farm a follow on Twitter and Blue Sky!