English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

In many settings, interventions may be more effective for some individualsthan others, so that targeting interventions may be beneficial. We analyze thevalue of targeting in the context of a large-scale field experiment with over53,000 college students, where the goal was to use "nudges" to encouragestudents to renew their financial-aid applications before a non-bindingdeadline. We begin with baseline approaches to targeting. First, we targetbased on a causal forest that estimates heterogeneous treatment effects andthen assigns students to treatment according to those estimated to have thehighest treatment effects. Next, we evaluate two alternative targetingpolicies, one targeting students with low predicted probability of renewingfinancial aid in the absence of the treatment, the other targeting those withhigh probability. The predicted baseline outcome is not the ideal criterion fortargeting, nor is it a priori clear whether to prioritize low, high, orintermediate predicted probability. Nonetheless, targeting on low baselineoutcomes is common in practice, for example because the relationship betweenindividual characteristics and treatment effects is often difficult orimpossible to estimate with historical data. We propose hybrid approaches thatincorporate the strengths of both predictive approaches (accurate estimation)and causal approaches (correct criterion); we show that targeting intermediatebaseline outcomes is most effective, while targeting based on low baselineoutcomes is detrimental. In one year of the experiment, nudging all studentsimproved early filing by an average of 6.4 percentage points over a baselineaverage of 37% filing, and we estimate that targeting half of the studentsusing our preferred policy attains around 75% of this benefit.

Machine Learning Who to Nudge: Causal vs Predictive Targeting in a Field Experiment on Student Financial Aid Renewal