On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,657 papers · 148 categories

Trend · papers per month

count % of corpus

3 results for “Value-Add”

Benchmarking M6 Competitors: An Analysis of Financial Metrics and Discussion of Incentivesq-fin.PM

The study compares M6 competitors' performance to industry benchmarks and discusses incentives for investment managers.

problem Investors seek to understand the performance and skill of M6 competitors beyond the competition's metrics.

method Comparative analysis using financial metrics, factor models, and new strategies.

result Most competitors do not generate significant out-performance compared to industry benchmarks, but some show skill in recent performance.

M6 Competition Financial Metrics Incentives Competitors Performance Value-Add

2024-06-27abs ↗pdf ↗

Batch Universal Predictioncs.IT

New method evaluates LLMs fairness in universal prediction.

problem Evaluating fairness of large language models in universal prediction.

method Introducing batch regret as a modification of average regret for LLMs.

result Asymptotical value of batch regret for add-constant predictors on memoryless and first-order Markov sources.

large language models universal prediction batch regret asymptotical value add-constant predictors

2024-02-06abs ↗pdf ↗

Random matrix theory and nested clustered portfolios on Mexican marketsq-fin.ST

The paper proposes a new portfolio allocation method combining RMT and machine learning.

problem Optimal allocation instability in high-dimensional portfolios.

method Combines Random Matrix Theory covariance estimators with Nested Clustered Optimization.

result The modified NCO algorithm achieves stable allocations without risky short positions.

portfolio theory Random Matrix Theory Nested Clustered Optimization Mexican markets machine learning

2023-06-09abs ↗pdf ↗