
Human Decisions and Machine Predictions in Multistage Systems
This paper evaluates predictive algorithms within multistage decision systems, focusing specifically on Child Protective Services (CPS) screening and investigation processes. Traditional algorithm evaluations typically examine a single stage in isolation, which fails to capture how downstream human actors respond to algorithmic recommendations or how later-stage workers gather new information that alters outcomes. To address this limitation, the authors develop an econometric framework using large language models to analyze unstructured investigator case notes, successfully identifying crucial narrative themes that capture significant predictive signal beyond standard administrative data. Ultimately, the research demonstrates that deploying algorithms in multistage systems requires understanding human-algorithm complementarities, revealing that human investigators add distinct value by collecting new field evidence rather than merely replicating automated risk predictions.
More episodes from "Best AI papers explained"



Don't miss an episode of “Best AI papers explained” and subscribe to it in the GetPodcast app.








