MétaCan
Menu
Back to cohort
Record W7160315630 · doi:10.1109/aixb65684.2025.00015

AI-FINALYST: Multi-Agentic Debating Framework with Confidence-Weighting for Investment Decisions

2025· article· W7160315630 on OpenAlexaff
Ravjot Kaur, Gurasis Singh, Debashis Guha

Bibliographic record

Venuenot available
Typearticle
Language
FieldDecision Sciences
TopicRisk and Portfolio Optimization
Canadian institutionsArtificial Intelligence in Medicine (Canada)
Fundersnot available
KeywordsInvestment (military)Investment decisionsContext (archaeology)Government (linguistics)Work (physics)

Abstract

fetched live from OpenAlex

This paper presents AI-FINALYST, a novel framework for analysing financial information using six agents based on large language models. The agents engage in a multiturn debate that mimics investment decision-making by a team of human analysts. Each agent specialises in one form of equity analysis: fundamental, technical, sentiment, sector, news, and social media. The final call combines the scores awarded by all six agents. The model is back tested on the daily prices of five U.S. stocks for a period of five years for making buy, hold or sell investment decisions at quarterly intervals, and it outperforms buy and hold for four out of five stocks. An equally weighted portfolio of all five stocks based on AI-FINALYST calls achieves a 38% return per annum, exhibiting a drawdown reduction of 15.93%, as compared to the buy-and-hold strategy, which shows a 21.7% return per annum for the same volatility.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

How this classification was reachedexpand

Full frame distilled prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.

metaresearch head score (Codex)0.004
metaresearch head score (Gemma)0.014
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesMetaresearch, Meta-epidemiology (narrow), Science and technology studies, Scholarly communication, Insufficient payload (model declined to judge)
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: none
GenreCandidate signal: Methods · Consensus signal: Methods
Teacher disagreement score0.727
Threshold uncertainty score1.000

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0040.014
Meta-epidemiology (narrow)0.0010.000
Meta-epidemiology (broad)0.0010.000
Bibliometrics0.0010.005
Science and technology studies0.0020.000
Scholarly communication0.0020.001
Open science0.0010.000
Research integrity0.0000.001
Insufficient payload (model declined to judge)0.0010.000

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.105
GPT teacher head0.421
Teacher spread0.317 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one teacher head, not a consensus.

Study designSimulation or modeling
Domainnot available
GenreMethods

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations0
Published2025
Admission routes1
Has abstractyes

Explore more

Same topicRisk and Portfolio OptimizationFrench-language works237,207