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.
In general, underestimation of risk is something which should be avoided as far as possible. Especially in financial asset management, equity risk is typically characterized by the measure of portfolio variance, or indirectly by quantities which are derived from it. Since there is a linear dependency of the variance an…
Machine learning algorithms can misrepresent training data, study finds.
Paper addresses underestimation bias in double Q-learning, proposing a method to improve learning performance.
A new Q-learning variant reduces underestimation bias in deep reinforcement learning.
A novel Q-learning variant reduces underestimation bias in deep actor-critic methods for reinforcement learning.
Smaller actor-critic models lead to performance degradation and overfitting, highlighting the critic's role in value underestimation.
The paper analyzes how factorized Gaussian approximations underestimate uncertainty in variational inference.
The paper examines skill estimation and variance under model misspecification in IRT.
The study uses a multi-armed bandit model to analyze and mitigate hiring discrimination.
New model improves volatility forecasting by reducing overestimation and underestimation.
When using the K-nearest neighbors method, one often ignores uncertainty in the choice of K. To account for such uncertainty, Holmes and Adams (2002) proposed a Bayesian framework for K-nearest neighbors (KNN). Their Bayesian KNN (BKNN) approach uses a pseudo-likelihood function, and standard Markov chain Monte Carlo (…
MFVI can overestimate predictive variance compared to the exact posterior
Typically, operational risk losses are reported above some threshold. This paper studies the impact of ignoring data truncation on the 0.999 quantile of the annual loss distribution for operational risk for a broad range of distribution parameters and truncation levels. Loss frequency and severity are modelled by the P…
This article presents results from the first statistically significant study of cost escalation in transportation infrastructure projects. Based on a sample of 258 transportation infrastructure projects worth US$90 billion and representing different project types, geographical regions, and historical periods, it is fou…
Improved noise estimation in latent neural SDEs enhances model accuracy.
Research shows bias in machine learning can be due to algorithmic flaws, not just data.
Importance-weighting is a popular and well-researched technique for dealing with sample selection bias and covariate shift. It has desirable characteristics such as unbiasedness, consistency and low computational complexity. However, weighting can have a detrimental effect on an estimator as well. In this work, we empi…
We investigate the possible drawbacks of employing the standard Pearson estimator to measure correlation coefficients between financial stocks in the presence of non-stationary behavior, and we provide empirical evidence against the well-established common knowledge that using longer price time series provides better, …
In recent years research on credit risk modelling has mainly focused on default probabilities. Recovery rates are usually modelled independently, quite often they are even assumed constant. Then, however, the structural connection between recovery rates and default probabilities is lost and the tails of the loss distri…
There is an extensive historical dataset on real GDP per capita prepared by Angus Maddison. This dataset covers the period since 1870 with continuous annual estimates in developed countries. All time series for individual economies have a clear structural break between 1940 and 1950. The behavior before 1940 and after …
Predictive models ground many state-of-the-art developments in statistical brain image analysis: decoding, MVPA, searchlight, or extraction of biomarkers. The principled approach to establish their validity and usefulness is cross-validation, testing prediction on unseen data. Here, I would like to raise awareness on e…
This note investigates the causes of the quality anomaly, which is one of the strongest and most scalable anomalies in equity markets. We explore two potential explanations. The "risk view", whereby investing in high quality firms is somehow riskier, so that the higher returns of a quality portfolio are a compensation …
We show that different rates should be used for borrowing and discount rates, and that the risk-free rate should be used for discounting when assessing and comparing the cost of energy accross diffferent producers and technologies, on the example of photovoltaics. Recent quantitative models using the same rate for borr…
The inability to see and quantify systemic financial risk comes at an immense social cost. Systemic risk in the financial system arises to a large extent as a consequence of the interconnectedness of its institutions, which are linked through networks of different types of financial contracts, such as credit, derivativ…
New theory shows how learning algorithms can create a bias towards negative outcomes.
In the presence of a layer of metaprobabilities (from uncertainty concerning the parameters), the asymptotic tail exponent corresponds to the lowest possible tail exponent regardless of its probability. The problem explains "Black Swan" effects, i.e., why measurements tend to chronically underestimate tail contribution…
To obtain uncertainty estimates with real-world Bayesian deep learning models, practical inference approximations are needed. Dropout variational inference (VI) for example has been used for machine vision and medical applications, but VI can severely underestimates model uncertainty. Alpha-divergences are alternative …
Empirical study finds IT project costs follow a power-law distribution, exposing risk underestimation.
We correct a mistake in the published version of our paper. Our new conclusion is that the "implied leverage effect" for single stocks is underestimated by option markets for short maturities and overestimated for long maturities, while it is always overestimated for OEX options, except for the shortest maturities wher…
New method corrects risk estimation bias, improving backtesting results.
New algorithm corrects risk estimation bias for heavy-tailed data.
The CLT fails for LLM evaluations with small data, leading to underestimation of uncertainty.
New research shows CI in few-shot learning is misleading due to sampling with replacement.
Bayesian regression underestimates parameter uncertainties in noisy models.
A possible data source for the estimation of asset correlations is default time series. This study investigates the systematic error that is made if the exposure pool underlying a default time series is assumed to be homogeneous when in reality it is not. We find that the asset correlation will always be underestimated…
Based on the work of Suzuki (2002), we consider a generalization of Merton's asset valuation approach (Merton, 1974) in which two firms are linked by cross-ownership of equity and liabilities. Suzuki's results then provide no arbitrage prices of firm values, which are derivatives of exogenous asset values. In contrast …
We discuss the systemic risk implied by the interbank exposures reconstructed with the maximum entropy method. The maximum entropy method severely underestimates the risk of interbank contagion by assuming a fully connected network, while in reality the structure of the interbank network is sparsely connected. Here, we…
New framework identifies hidden risks and optionality in American options.
LatentNN corrects neural network attenuation bias in astronomical data.
We propose a robust risk measurement approach that minimizes the expectation of overestimation plus underestimation costs. We consider uncertainty by taking the supremum over a collection of probability measures, relating our approach to dual sets in the representation of coherent risk measures. We provide results that…
The article first describes characteristics of major infrastructure projects. Second, it documents a much neglected topic in economics: that ex ante estimates of costs and benefits are often very different from actual ex post costs and benefits. For large infrastructure projects the consequence is cost overruns, benefi…
Traders underestimated risk-free rates, leading to poor investments.
Information theoretic criteria (ITC) have been widely adopted in engineering and statistics for selecting, among an ordered set of candidate models, the one that better fits the observed sample data. The selected model minimizes a penalized likelihood metric, where the penalty is determined by the criterion adopted. Wh…
Artificial Intelligence (AI) is an important driving force for the development and transformation of the financial industry. However, with the fast-evolving AI technology and application, unintentional bias, insufficient model validation, immature contingency plan and other underestimated threats may expose the company…
Variational Bayes (VB) is a recent approximate method for Bayesian inference. It has the merit of being a fast and scalable alternative to Markov Chain Monte Carlo (MCMC) but its approximation error is often unknown. In this paper, we derive the approximation error of VB in terms of mean, mode, variance, predictive den…
This work presents a theoretical and empirical evaluation of Anderson-Darling test when the sample size is limited. The test can be applied in order to backtest the risk factors dynamics in the context of Counterparty Credit Risk modelling. We show the limits of such test when backtesting the distributions of an intere…
This paper compares VaR estimation methods under tail misspecification, finding importance sampling underestimates VaR.
The risk of a credit portfolio depends crucially on correlations between the probability of default (PD) in different economic sectors. Often, PD correlations have to be estimated from relatively short time series of default rates, and the resulting estimation error hinders the detection of a signal. We present statist…