MétaCan
Menu
Back to cohort

Cutting Through the Noise: Machine Learning Proxies for High Dimensional Nested Simulation

2023· article· en· W4391381539 on OpenAlexaff
Xintong Li, Mingbin Feng, Tony S. Wirjanto

Bibliographic record

Venuenot available
Typearticle
Languageen
FieldSocial Sciences
TopicInsurance, Mortality, Demography, Risk Management
Canadian institutionsUniversity of Waterloo
Fundersnot available
KeywordsInterpretabilityComputer scienceTransparency (behavior)Deep learningMachine learningArtificial intelligenceStability (learning theory)Data modelingNoise (video)Reliability (semiconductor)Computer security

Abstract

fetched live from OpenAlex

Deep learning models have gained great success in many applications, but their adoption in financial and actuarial applications have been received by regulators with some trepidation. The lack of transparency and interpretability of these models leads to skepticism about their resilience and reliability, which are important factors to ensure financial stability and insurance benefit fulfillment. In this study, we use stochastic simulation as a data generator to examine deep learning models under controlled settings. Our study shows interesting findings in fundamental questions like "What do deep learning models learn from noisy data?" and "How well do they learn from noisy data?". Based on our findings, we propose an efficient nested simulation procedure that uses deep learning models as proxies to estimate tail risk measures of hedging errors for variable annuities. The proposed procedure uses deep learning models to concentrate simulation budget on tail scenarios while maintaining transparency in the estimation.

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 machine prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.

metaresearch head score (Codex)0.012
metaresearch head score (Gemma)0.104
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: Simulation or modeling
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.012
Threshold uncertainty score0.066

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0120.104
Meta-epidemiology (narrow)0.0010.001
Meta-epidemiology (broad)0.0010.001
Bibliometrics0.0010.001
Science and technology studies0.0010.004
Scholarly communication0.0020.004
Open science0.0030.005
Research integrity0.0020.004
Insufficient payload (model declined to judge)0.0030.000

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 head0.040
GPT teacher head0.344
Teacher spread0.303 · 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 source (direct Gemma or distilled Codex), not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designSimulation or modeling
Domainnot available
GenreEmpirical

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
Published2023
Admission routes1
Has abstractyes

Explore more

Same topicInsurance, Mortality, Demography, Risk ManagementFrench-language works237,207