Metraipolis › archive › dc_362dfb82b646

Are LLMs Good Financial User Simulators? Multi-view Investor Logic Alignment (MILA) — arXiv:2609.15727

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.15727
License (as archived)
CC0-1.0
Archived
2026-10-15T22:48:05.241Z
SHA-256 of the archived text
74e4928d0b696d63fa55dab77a094621f233a40a8f4cfb5173ecd11aa2d8bfbc
Stable URL of this page
https://metraipolis.com/documento/dc_362dfb82b646

How to cite

Are LLMs Good Financial User Simulators? Multi-view Investor Logic Alignment (MILA) — arXiv:2609.15727 — arXiv (en), https://arxiv.org/abs/2609.15727 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_362dfb82b646 (Metraipolis archive dc_362dfb82b646, sha256 74e4928d0b696d63fa55dab77a094621f233a40a8f4cfb5173ecd11aa2d8bfbc)
BibTeX
@misc{dc362dfb82b646,
  title = {Are LLMs Good Financial User Simulators? Multi-view Investor Logic Alignment (MILA) — arXiv:2609.15727},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.15727},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_362dfb82b646; sha256 74e4928d0b696d63fa55dab77a094621f233a40a8f4cfb5173ecd11aa2d8bfbc},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.15727. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Large language models (LLMs) are increasingly used as user simulators, yet it remains unclear whether their predictions faithfully reproduce the evolving decisions of individual users. We investigate this question in a controlled longitudinal paper-trading study with 80 participants, where user interactions, simulated transactions, virtual portfolio states, and point-in-time market information are aligned under a rolling next-day prediction protocol. We evaluate behavioral fidelity hierarchically, from trade occurrence to action structure, asset selection, and downstream portfolio consequences. Across 1,239 aligned user-days, no evaluated LLM reliably outperforms a simple recent-activity persistence baseline for predicting whether a user trades. Fidelity further deteriorates at finer levels: models struggle to recover buy--sell structure and traded assets, and similar activity-level predictions can lead to substantially different portfolio trajectories. Controlled evidence ablations show that recent trading history strongly governs activity prediction, whereas asset selection is substantially more sensitive to the available evidence. An observational analysis further finds that intensified ticker-specific research predicts imminent trading, but diagnostic tests do not support a causal interpretation. These findings suggest that current LLMs capture useful short-term behavioral regularities without yet recovering a stable individual decision mechanism.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-15 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Computers and Society (cs.CY); Human-Computer Interaction (cs.HC).
Pagina del lavoro: https://arxiv.org/abs/2609.15727 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-15T22:29:03.353Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-15?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).