Zusammenfassung:
We use administrative microdata and statistical learning methods to analyze how personal characteristics and the consumption of healthcare services help predict the first-time receipt of "long-term care allowance" (LTCA), a needs-tested cash-for-care benefit in Austria. Our findings suggest that short-term information from the healthcare sector, particularly in the quarter prior to LTCA enrollment, provides substantial explanatory power. Apart from old age, the most influential predictors include the frequency of doctor visits and hospital stays as well as diagnoses such as dementia, cerebral infarction, and hypertension. Our findings emphasize the importance of datadriven approaches in anticipating the uptake of long-term care benefits and informing policy, especially against the background of the demographic transition.