{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T16:43:44Z","timestamp":1782924224239,"version":"3.54.5"},"reference-count":10,"publisher":"Association for Computing Machinery (ACM)","issue":"2","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/publication-rights-and-licensing-policy"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["SIGecom Exch."],"published-print":{"date-parts":[[2026,1,1]]},"abstract":"\n This letter provides an overview of our recent work on \"Learning Treatment Effects While Treating Those in Need\" (published at the 2025 ACM Conference on Economics and Computation) as well as a more general perspective on design goals for algorithmic systems that are used to allocate limited resources in policy settings. Our motivation is the kind of algorithms that are used widely at present to prioritize candidates for various kinds of social interventions: public housing assistance, drop-out prevention programs in education, unconditional cash transfers in development, or a variety of other social services. By far the most common way of constructing such systems is the lens of\n predictive allocation<\/jats:italic>\n : the algorithm designer identifies an outcome that the program seeks to alter (long-term home-lessness, dropping out of school, etc) and constructs a predictive model for that outcome [Vaithianathan and Kithulgoda 2020; Aiken et al. 2022; Pan et al. 2017; Toros and Flaming 2017]. Candidates are ranked by predictions of risk so that, e.g., limited spots in a housing program might be offered to those at greatest predicted risk of long-term homelessness.\n <\/jats:p>","DOI":"10.1145\/3817099.3817103","type":"journal-article","created":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T15:43:59Z","timestamp":1782920639000},"page":"59-65","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Balancing Learning and Targeting in Predictive Allocation"],"prefix":"10.1145","volume":"23","author":[{"given":"Bryan","family":"Wilder","sequence":"first","affiliation":[{"name":"Carnegie Mellon University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pim","family":"Welle","sequence":"additional","affiliation":[{"name":"Allegheny County Department of Human Services"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,7,1]]},"reference":[{"key":"e_1_2_1_1_1","doi-asserted-by":"crossref","unstructured":"Aiken E. Bellue S. Karlan D. Udry C. and Blumenstock J. E. 2022. Machine learning and phone data can improve targeting of humanitarian aid. Nature 603 7903 864\u2013870.","DOI":"10.1038\/s41586-022-04484-9"},{"key":"e_1_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.3982\/ECTA15732"},{"key":"e_1_2_1_3_1","unstructured":"Chernozhukov V. Demirer M. Lewis G. and Syrgkanis V. 2019. Semi-parametric efficient policy learning with continuous actions. Advances in Neural Information Processing Systems 32."},{"key":"e_1_2_1_4_1","doi-asserted-by":"crossref","unstructured":"Hahn J. 1998. On the role of the propensity score in efficient semiparametric estimation of average treatment effects. Econometrica 315\u2013331.","DOI":"10.2307\/2998560"},{"key":"e_1_2_1_5_1","doi-asserted-by":"crossref","unstructured":"Pan I. Nolan L. B. Brown R. R. Khan R. van der Boor P. Harris D. G. and Ghani R. 2017. Machine learning for social services: a study of prenatal case management in illinois. American journal of public health 107 6 938\u2013944.","DOI":"10.2105\/AJPH.2017.303711"},{"key":"e_1_2_1_6_1","volume-title":"The Thirteenth International Conference on Learning Representations.","author":"Sharma V.","unstructured":"Sharma, V. and Wilder, B. 2025. Comparing targeting strategies for maximizing social welfare with limited resources. In The Thirteenth International Conference on Learning Representations."},{"key":"e_1_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.5555\/2789272.2886805"},{"key":"e_1_2_1_8_1","doi-asserted-by":"crossref","unstructured":"Toros H. and Flaming D. 2017. Prioritizing which homeless people get housing using predictive algorithms. Available at SSRN 2960410.","DOI":"10.2139\/ssrn.2960410"},{"key":"e_1_2_1_9_1","unstructured":"Vaithianathan R. and Kithulgoda C. I. 2020. Using predictive risk modeling to prioritize services for people experiencing homelessness in allegheny county: Methodology update."},{"key":"e_1_2_1_10_1","volume-title":"The 41st Conference on Uncertainty in Artificial Intelligence.","author":"Yamin K.","unstructured":"Yamin, K., Kennedy, E., and Wilder, B. 2025. Dependent randomized rounding for budget constrained experimental design. In The 41st Conference on Uncertainty in Artificial Intelligence."}],"container-title":["ACM SIGecom Exchanges"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3817099.3817103","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T15:44:15Z","timestamp":1782920655000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3817099.3817103"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,1]]},"references-count":10,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2026,1,1]]}},"alternative-id":["10.1145\/3817099.3817103"],"URL":"https:\/\/doi.org\/10.1145\/3817099.3817103","relation":{},"ISSN":["1551-9031"],"issn-type":[{"value":"1551-9031","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1,1]]},"assertion":[{"value":"2026-07-01","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}