Articolo su International Journal of Data Science and Analytics
ร stato publicato in open access sulla rivista ๐๐ป๐๐ฒ๐ฟ๐ป๐ฎ๐๐ถ๐ผ๐ป๐ฎ๐น ๐๐ผ๐๐ฟ๐ป๐ฎ๐น ๐ผ๐ณ ๐๐ฎ๐๐ฎ ๐ฆ๐ฐ๐ถ๐ฒ๐ป๐ฐ๐ฒ ๐ฎ๐ป๐ฑ ๐๐ป๐ฎ๐น๐๐๐ถ๐ฐ๐ (Springer) l’articolo โ๐๐ฑ๐ต๐ช๐ฎ๐ข๐ญ ๐ฑ๐ฐ๐ญ๐ช๐ค๐บ ๐ญ๐ฆ๐ข๐ณ๐ฏ๐ช๐ฏ๐จ ๐ธ๐ช๐ต๐ฉ ๐ฐ๐ฃ๐ด๐ฆ๐ณ๐ท๐ข๐ต๐ช๐ฐ๐ฏ๐ข๐ญ ๐ฅ๐ข๐ต๐ข ๐ช๐ฏ ๐ฎ๐ถ๐ญ๐ต๐ช-๐ข๐ค๐ต๐ช๐ฐ๐ฏ ๐ด๐ค๐ฆ๐ฏ๐ข๐ณ๐ช๐ฐ๐ด: ๐ฆ๐ด๐ต๐ช๐ฎ๐ข๐ต๐ช๐ฐ๐ฏ, ๐ณ๐ช๐ด๐ฌ ๐ฑ๐ณ๐ฆ๐ง๐ฆ๐ณ๐ฆ๐ฏ๐ค๐ฆ, ๐ข๐ฏ๐ฅ ๐ฑ๐ฐ๐ต๐ฆ๐ฏ๐ต๐ช๐ข๐ญ ๐ง๐ข๐ช๐ญ๐ถ๐ณ๐ฆ๐ดโ curato da Giovanni Cerulli.
The paper discusses: Offline and online Optimal Policy Learning (OPL) | Multi-action decision settings | Risk-adjusted policy learning | Regret minimization | The role of overlap and unconfoundedness |ย Applications to data-driven public policy design
