Look-Ahead-Bench evaluates financial LLMs for lookahead bias, revealing significant differences in model performance.
problem Measuring and mitigating lookahead bias in financial LLMs.
method Standardized benchmark evaluating model behavior in practical financial scenarios, analyzing performance decay across market regimes.
result Standard LLMs exhibit significant lookahead bias, while Pitinf models show improved generalization and reasoning abilities.
Model change points in time-series data with neural SDEs and variational autoencoders.
problem Modeling change points in time-series data with neural stochastic differential equations.
method Proposes a novel model formulation and training procedure based on the variational autoencoder framework, alternating between updating neural SDE parameters and change points.
result Demonstrates the expressive power of the proposed model in modeling both classical parametric SDEs and real datasets with distribution shifts.
Generative Networks outperform traditional methods in PiT ESG generation.
problem Generating economic scenarios quickly and flexibly for sudden changes.
method Comparison of nonparametric, parametric, and generative models.
result Conditional Variational Autoencoder (CVAE) performs best.
This paper proposes new get-rich-quick schemes that involve trading in a financial security with a non-degenerate price path. For simplicity the interest rate is assumed zero. If the price path is assumed continuous, the trader can become infinitely rich immediately after it becomes non-constant (if it ever does). If i…
Given a heterogeneous time-series sample, the objective is to find points in time (called change points) where the probability distribution generating the data has changed. The data are assumed to have been generated by arbitrary unknown stationary ergodic distributions. No modelling, independence or mixing assumptions…
In this paper, we consider the optimal portfolio liquidation problem under the dynamic mean-variance criterion and derive time-consistent solutions in three important models. We give adapted optimal strategies under a reconsidered mean-variance subject at any point in time. We get explicit trading strategies in the bas…
Causal processes in biomedicine may contain cycles, evolve over time or differ between populations. However, many graphical models cannot accommodate these conditions. We propose to model causation using a mixture of directed cyclic graphs (DAGs), where the joint distribution in a population follows a DAG at any single…
We build on the work in Fackler and King 1990, and propose a more general calibration model for implied risk neutral densities. Our model allows for the joint calibration of a set of densities at different maturities and dates through a Bayesian dynamic Beta Markov Random Field. Our approach allows for possible time de…
This paper examines the value of a cancellable European option in a finite time horizon setting. The specifications of this generalized European option allow the seller to cancel the option at any point in time for a fixed penalty paid directly to the holder. Here, we provide an explicit valuation formula for the Europ…
This paper presents the construction of a particle filter, which incorporates elements inspired by genetic algorithms, in order to achieve accelerated adaptation of the estimated posterior distribution to changes in model parameters. Specifically, the filter is designed for the situation where the subsequent data in on…
Optimal trade execution in a fluctuating market with stochastic liquidity.
problem Minimizing costs in a market with unpredictable liquidity.
method Developed a recursion to find the least costly trade execution strategy.
result Explicit recursion characterizes the least costly trade execution.
We mathematically analyze a simple market model where trading at each point in time involves only two agents with the sum of their money being conserved and with neither parties resulting with negative money after the interaction process. The exchange involves random re-distribution among the two players of a fixed fra…
Quantum kernels show no advantage in stock return prediction, but differ in stability metrics.
problem Determining if quantum kernels improve stock return prediction.
method Controlled horse race on Chinese A-share market with identical training subsamples and tuning budgets.
result Quantum kernels do not outperform classical RBF controls in cross-sectional stock return prediction.
New filters match advanced composition for adaptive privacy, with practical constants.
problem Limitations of existing adaptive composition methods.
method Constructed new filters and odometers that match advanced composition rates, including constants.
result Achieved fully adaptive privacy with practical filters and odometers.
If a document is about travel, we may expect that short snippets of the document should also be about travel. We introduce a general framework for incorporating these types of invariances into a discriminative classifier. The framework imagines data as being drawn from a slice of a Levy process. If we slice the Levy pr…
The paper stabilizes PD term structures under forecast uncertainty using a Kalman filter with an anchored observation model.
problem Stable estimation of lifetime PDs under forecast uncertainty.
method Reformulated in state-space framework, introduced an anchored observation model.
result Asymptotic stochastic stability of error dynamics, leading to smoother projections.
TAGM models time-varying connections between variables.
problem Inferring temporal relationships between covariates.
method Time Adaptive Gaussian Model (TAGM) using Hidden Markov Models and Gaussian Graphical Models.
result TAGM outperforms state-of-the-art methods for temporal network inference.
Sequential quantile estimation refers to incorporating observations into quantile estimates in an incremental fashion thus furnishing an online estimate of one or more quantiles at any given point in time. Sequential quantile estimation is also known as online quantile estimation. This area is relevant to the analysis …
Recidivism prediction instruments provide decision makers with an assessment of the likelihood that a criminal defendant will reoffend at a future point in time. While such instruments are gaining increasing popularity across the country, their use is attracting tremendous controversy. Much of the controversy concerns …
We consider a controlled diffusion process (Xt)t≥0 where the controller is allowed to choose the drift μt and the volatility σt from a set $\K(x) \subset \R\times (0,\infty)$ when Xt=x. By choosing the largest σ2μ at every point in time an extremal process is constructed which is under suita…
Bayesian model averaging has become a widely used approach to accounting for uncertainty about the structural form of the model generating the data. When data arrive sequentially and the generating model can change over time, Dynamic Model Averaging (DMA) extends model averaging to deal with this situation. Often in ma…
Model credit ratings using economic states with Markov chains.
problem Credit rating migration influenced by economic state changes.
method Developed a Markov chain model for credit ratings conditional on economic states.
result Derived asymptotic behavior of the rating process using Markov theory.
Combines multiple asset views with machine learning for better portfolio allocation.
problem Portfolio allocation with multiple uncertain asset views.
method Consistency-based data fusion techniques for combining Black-Litterman model with machine learning predictions.
result Improved portfolio allocation through fusion of multiple view estimates.
We propose a model in which dividend payments occur at regular, deterministic intervals in an otherwise continuous model. This contrasts traditional models where either the payment of continuous dividends is controlled or the dynamics are given by discrete time processes. Moreover, between two dividend payments, the st…
For nearly every major stock market there exist equity and implied volatility indices. These play important roles within finance: be it as a benchmark, a measure of general uncertainty or a way of investing or hedging. It is well known in the academic literature, that correlations and higher moments between different i…
Knowledge graphs (KGs) typically contain temporal facts indicating relationships among entities at different times. Due to their incompleteness, several approaches have been proposed to infer new facts for a KG based on the existing ones-a problem known as KG completion. KG embedding approaches have proved effective fo…
Credit risk management in Italy is characterized, in the period June 2008 to June 2012, by frequent (frequency=0.5 cycles per year) and intense (peak amplitude: mean=39.2 billion Euros, s.e.=2.83 billion Euros) quarterly contractions and expansions around the mean (915.4 billion Euros, s.e.=3.59 billion Euros) of the n…
This paper studies the application of machine learning in extracting the market implied features from historical risk neutral corporate bond yields. We consider the example of a hypothetical illiquid fixed income market. After choosing a surrogate liquid market, we apply the Denoising Autoencoder algorithm from the fie…
Recidivism prediction instruments (RPI's) provide decision makers with an assessment of the likelihood that a criminal defendant will reoffend at a future point in time. While such instruments are gaining increasing popularity across the country, their use is attracting tremendous controversy. Much of the controversy c…
This paper studies an application of machine learning in extracting features from the historical market implied corporate bond yields. We consider an example of a hypothetical illiquid fixed income market. After choosing a surrogate liquid market, we apply the Denoising Autoencoder (DAE) algorithm to learn the features…
If the probability of default parameters (PDs) fed as input into a credit portfolio model are estimated as through-the-cycle (TTC) PDs stressed market conditions have little impact on the results of the capital calculations conducted with the model. At first glance, this is totally different if the PDs are estimated as…
In this paper we experimentally analyze the convergence behavior of CoCoA and show, that the number of workers required to achieve the highest convergence rate at any point in time, changes over the course of the training. Based on this observation, we build Chicle, an elastic framework that dynamically adjusts the num…
We focus on two particular aspects of model risk: the inability of a chosen model to fit observed market prices at a given point in time (calibration error) and the model risk due to recalibration of model parameters (in contradiction to the model assumptions). In this context, we follow the approach of Glasserman and …
End-to-end deep model for coherent probabilistic forecasts in hierarchical time series.
problem Hierarchical probabilistic forecasting for coherent predictions.
method Dirichlet proportions model for learning root and child distributions.
result Significant improvements over state-of-the-art baselines (up to 26%).
It is important to identify the change point of a system's health status, which usually signifies an incipient fault under development. The One-Class Support Vector Machine (OC-SVM) is a popular machine learning model for anomaly detection and hence could be used for identifying change points; however, it is sometimes …
New model predicts banana disease risk from climate data.
problem Managing Black Sigatoka disease under climate change.
method Latent Neural ODEs to model infection dynamics.
result Superior generalization performance up to one month ahead.
Even in the face of deteriorating and highly volatile demand, firms often invest in, rather than discard, aging technologies. In order to study this phenomenon, we model the firm's profit stream as a Brownian motion with negative drift. At each point in time, the firm can continue operations, or it can stop and exit th…
New algorithms for online MAP inference and learning for NDPPs.
problem Online inference and learning for nonsymmetric determinantal point processes.
method Single-pass algorithms with sub-linear memory usage.
result Comparable performance to offline algorithms with multiple passes.
In this work, we introduce a deep-structured conditional random field (DS-CRF) model for the purpose of state-based object silhouette tracking. The proposed DS-CRF model consists of a series of state layers, where each state layer spatially characterizes the object silhouette at a particular point in time. The interact…
HireVAE adapts to market regimes for online stock prediction.
problem Building an online and adaptive factor model for stock prediction.
method HireVAE uses a hierarchical latent space to estimate latent factors from historical market information.
result HireVAE outperforms previous methods in active returns across benchmarks.
Methods for detecting structural changes, or change points, in time series data are widely used in many fields of science and engineering. This chapter sketches some basic methods for the analysis of structural changes in time series data. The exposition is confined to retrospective methods for univariate time series. …
In many physical, social or economical phenomena we observe changes of a studied quantity only in discrete, irregularly distributed points in time. The stochastic process used by physicists to describe this kind of variables is the Continuous Time Random Walk (CTRW). Despite the popularity of this type of stochastic pr…
M2VN forecasts financial volatility by fusing time series data with news embeddings.
problem Forecasting financial volatility with unstructured news data.
method Combines deep neural networks with open-source market features and news embeddings.
result M2VN outperforms existing models in financial volatility forecasting.
The paper extends asset pricing theory by considering conditional markets.
problem Analyzing financial markets with conditional information.
method Time consistency properties of dynamic nonlinear expectations applied to super- and subhedging prices.
result Derives a conditional version of the second fundamental theorem of asset pricing.
Learning in sparse reward settings remains a challenge in Reinforcement Learning, which is often addressed by using intrinsic rewards. One promising strategy is inspired by human curiosity, requiring the agent to learn to predict the future. In this paper a curiosity-driven agent is extended to use these predictions di…
This paper examines the valuation of a generalized American-style option known as a Game-style call option in an infinite time horizon setting. The specifications of this contract allow the writer to terminate the call option at any point in time for a fixed penalty amount paid directly to the holder. Valuation of a pe…
This work models overnight rates with jumps and discontinuities, extending classical short-rate models.
problem Capturing the jump behavior and discontinuities in overnight rates for accurate modeling.
method Developed a term structure modeling framework based on overnight rates, accommodating stochastic discontinuities.
result Simple specifications can capture the jump behavior of overnight rates, and explicit valuation formulas are provided.
New AIM algorithm optimizes exploration-exploitation in bandits.
problem Balancing exploration and exploitation in decision-making.
method Approximate Information Maximization (AIM) algorithm.
result AIM outperforms Infomax and Thompson sampling with enhanced speed and tractability.