{"ok":true,"nota":{"id":"6a44d02e06ffd7d6","slug":"un-modelo-de-lenguaje-simulando-216-inversores-muestra-que-las-noticia-6a44d0","titulo":"Un modelo de lenguaje simulando 216 inversores muestra que las noticias sociales generan más desacuerdo que la","resumen":"Los investigadores asignaron perfiles de inversores a un modelo de inteligencia artificial y le pidieron opinar sobre 1,25 millones de titulares del S&P 500. Midieron qué tan dispersas fueron las respuestas y lo compararon con el volumen de operaciones posterior.","fuente":"econstor","fuenteNombre":"EconStor · Economía","color":"#9a6b1f","autor":"Bhagwat, Vineet, Cookson, J. Anthony, Dim, Chukwuma Chijioke","url":"https://hdl.handle.net/10419/344253","imagen":"/hoy/portada/6a44d02e06ffd7d6","tema":"tecnologia","subtemas":["modelos de lenguaje","mercado de valores","inversores","volumen de operaciones","inteligencia artificial"],"entidades":["EconStor","S&P 500"],"formato":"dato","entretenimiento":false,"pubTs":"2026-10-23T15:00:32.000Z","indexTs":"2026-10-23T22:31:31.924Z","hash":"49af3e9209ee358b4673d7d7a69bb5905f2c70ce5a01102f9defe1581c387407","tsa":{"time":"Oct 23 22:32:31 2026 GMT","provider":"freetsa.org","sobre":"sello"},"stats":{"views":2,"likes":0,"clicks":0,"dwell":0},"tipo":"motor","registro":"hallazgo","porQueImporta":"Los titulares sobre temas sociales dividieron más a los inversores simulados que los de balances o resultados, y esa división se asoció con más compra y venta de acciones al día siguiente. Para alguien que ahorra o invierte desde Argentina, esto muestra que buena parte del movimiento de los mercados nace de diferencias de edad, ingreso y opinión, no solo de los números. El límite serio es que los inversores son simulados por una IA, así que el estudio sugiere patrones que todavía deben confirmarse con gente real.","quienFirma":"EconStor","confianza":"preprint","consulta":{"pregunta":"¿Las noticias sociales mueven más el mercado que los balances?"}},"sello":{"hash":"49af3e9209ee358b4673d7d7a69bb5905f2c70ce5a01102f9defe1581c387407","sello":"f0605f397266c28bb7e177cd76aded974d4c873e0e2d2bf0c230e7ac87ba0a54","beacon":{"drand":{"cadena":"8990e7a9aaed2ffed73dbd7092123d6f289930540d7651336225dc172e51b2ce","ronda":6578790,"aleatorio":"c4d4738914627cb599c4c0726095d0ca65d7e18b339aad7019f74f0cf22914d9","tiempo":"2026-10-23T22:32:00.000Z"},"nist":{"cadena":2,"pulso":1996588,"salida":"1AB33E4D4D8827C21F7F3557C5995F2A7803790AA889B11FBC3E8A1AAE593D51C4D6AF8D679624359D1D1868187DF78129DBF70BD659B8A94EB4847855F1EB6E","tiempo":"2026-10-23T22:31:00.000Z"},"noAntes":"2026-10-23T22:32:00.000Z"},"verificacion":{"drand":true,"nist":true},"tsa":{"time":"Oct 23 22:32:31 2026 GMT","provider":"freetsa.org","sobre":"sello"},"original":{"titulo":"The market's mirror: Revealing investor disagreement with LLMS","descripcion":"Can large language models (LLMs) reveal how investors disagree? We endow an LLM with 216 representative investor personas, elicit buy/hold/sell responses to 1.25 million S&P 500 news headlines, and measure disagreement as within-headline dispersion of responses. Disagreement is highest for socially oriented news and lowest for fundamentals, and predicts elevated same- and next-day abnormal trading volume, even after the LLM's training cutoff. Disagreement rooted in income, education, and age is most strongly related to trading, whereas political disagreement, though largest, is least related. Persona responses reflect non-pecuniary rationales, align with human-survey benchmarks, and are stable across prompt variations.","pubDate":"2026-10-23T15:00:32Z","url":"https://hdl.handle.net/10419/344253"},"indexado":"2026-10-23T22:31:31.924Z"}}