arXiv subjects

Kay Giesecke

Publications and source records attributed to Kay Giesecke.

14 recordsLinked to original sources

arXiv2026

Agentic Empirical Asset Pricing: Methodological Foundations

Recent advances in LLM agents enable a new paradigm for asset pricing, which we call Agentic Empirical Asset Pricing (AEAP): systems that autonomously conduct the scientific discovery process itself. We define AEAP and identify its core building blocks. Existing evaluation practices backtest only the outputs (factors or trades), not the autonomous discovery system that produced them. We focus on factor discovery, contributing a reference architecture, a rigorous evaluation standard for discovered factors, and a method for out-of-sample backtesting the discovery system. As a concrete instance of that architecture, we evaluate SEADS against five re-implemented baselines on two US equity panels using this standard: no single metric ranks the systems consistently, motivating evaluation on multiple axes at once. A separate rolling re-execution then asks the complementary question of whether the discovery process itself, not one static output, is reliable. We also report negative findings and limitations that surface further evaluation pitfalls for future AEAP systems.

cs.AI↗

arXiv2026

The Stanford EDGAR Filings Dataset: Reconstructing U.S. Corporate and Financial Disclosures into Layout-Faithful and Token-Efficient Pretraining Data

As high-quality public web corpora become increasingly exhausted, clean long-context documents have become a scarce and expensive source of training data for large language models (LLMs). Existing long-context corpora are often proprietary and costly to acquire, synthetically generated, or concentrated in narrow domains such as programming. We introduce the Stanford EDGAR Filings Dataset (SEFD), an open reconstruction of SEC filings into layout-faithful MultiMarkdown for financial language modeling and evaluation. SEFD makes audited financial statements, risk disclosures, ownership reports, accounting notes, and market-moving event filings usable as long-context pretraining data and as a basis for financial reasoning, forecasting, compliance, and document understanding. The resulting corpus is token-efficient, model-ready, and has less than 0.1% overlap with Common Crawl-derived corpora. We release SEFD-v1, a 152B-token initial public snapshot, and provide corpus-level analyses of a larger 18.5M-filing archive estimated at 550B tokens. We further introduce two SEFD-derived benchmarks: EDGAR-Forecast, which evaluates filing-grounded numerical forecasting after model knowledge cutoffs, and EDGAR-OCR, which evaluates transcription of complex financial tables.

cs.AI↗

arXiv2026

Online Conformal Prediction for Non-Exchangeable Panel Data

Panel data, in which multiple units are repeatedly observed over time, arise throughout science and engineering. Quantifying predictive uncertainty in such settings is challenging because conformal prediction, while distribution-free and model-agnostic, classically relies on exchangeability assumptions that fail under temporal dependence and unit heterogeneity. We propose a simple online conformal framework for non-exchangeable panel data. The method exploits a key feature of online panel prediction: when a forecast is required for one unit, contemporaneous outcomes from related units may already be observed and can serve as a calibration panel. At each round, prediction sets are formed using currently observed calibration units together with two adaptive quantities: history-based similarity weights that emphasize calibration units resembling the target, and an adaptive miscoverage level that is updated whenever target feedback is revealed. This two-state design yields a stepwise coverage bound and a long-run coverage guarantee. Empirically, across synthetic and real panel data sets, the method improves coverage on the worst-covered target units through adaptive interval-width allocation rather than uniform inflation. The two states are complementary: similarity weights protect coverage when target feedback is sparse, while the adaptive level further improves coverage as feedback accumulates.

stat.ML↗

arXiv2025

AICO: Feature Significance Tests for Supervised Learning

Machine learning is central to modern science, industry, and policy, yet its predictive power often comes at the cost of transparency: we rarely know which input features truly drive a model's predictions. Without such understanding, researchers cannot draw reliable conclusions, practitioners cannot ensure fairness or accountability, and policymakers cannot trust or govern model-based decisions. Existing tools for assessing feature influence are limited; most lack statistical guarantees, and many require costly retraining or surrogate modeling, making them impractical for large modern models. We introduce AICO, a broadly applicable framework that turns model interpretability into an efficient statistical exercise. AICO tests whether each feature genuinely improves predictive performance by masking its information and measuring the resulting change. The method provides exact, finite-sample feature p-values and confidence intervals for feature importance through a simple, non-asymptotic hypothesis testing procedure. It requires no retraining, surrogate modeling, or distributional assumptions, making it feasible for large-scale algorithms. In both controlled experiments and real applications, from credit scoring to mortgage-behavior prediction, AICO reliably identifies the variables that drive model behavior, providing a scalable and statistically principled path toward transparent and trustworthy machine learning.

stat.ML↗

arXiv2025

A Set-Sequence Model for Time Series

Many prediction problems across science and engineering, especially in finance and economics, involve large cross-sections of individual time series, where each unit (e.g., a loan, stock, or customer) is driven by unit-level features and latent cross-sectional dynamics. While sequence models have advanced per-unit temporal prediction, capturing cross-sectional effects often still relies on hand-crafted summary features. We propose Set-Sequence, a model that learns cross-sectional structure directly, enhancing expressivity and eliminating manual feature engineering. At each time step, a permutation-invariant Set module summarizes the unit set; a Sequence module then models each unit's dynamics conditioned on both its features and the learned summary. The architecture accommodates unaligned series, supports varying numbers of units at inference, integrates with standard sequence backbones (e.g., Transformers), and scales linearly in cross-sectional size. Across a synthetic contagion task and two large-scale real-world applications, equity portfolio optimization and loan risk prediction, Set-Sequence significantly outperforms strong baselines, delivering higher Sharpe ratios, improved AUCs, and interpretable cross-sectional summaries.

cs.LG↗

arXiv2021

Unbiased Simulation Estimators for Multivariate Jump-Diffusions

We develop and analyze a class of unbiased Monte Carlo estimators for multivariate jump-diffusion processes with state-dependent drift, volatility, jump intensity and jump size. A change of measure argument is used to extend existing unbiased estimators for the inter-arrival diffusion to include state-dependent jumps. Under standard regularity conditions on the coefficient and target functions, we prove the unbiasedness and finite variance properties of the resulting jump-diffusion estimators. Numerical experiments illustrate the efficiency of our estimators.

math.PR↗

arXiv2020

Significance Tests for Neural Networks

We develop a pivotal test to assess the statistical significance of the feature variables in a single-layer feedforward neural network regression model. We propose a gradient-based test statistic and study its asymptotics using nonparametric techniques. Under technical conditions, the limiting distribution is given by a mixture of chi-square distributions. The tests enable one to discern the impact of individual variables on the prediction of a neural network. The test statistic can be used to rank variables according to their influence. Simulation results illustrate the computational efficiency and the performance of the test. An empirical application to house price valuation highlights the behavior of the test using actual data.

math.ST↗

arXiv2020

Explainable Clustering and Application to Wealth Management Compliance

Many applications from the financial industry successfully leverage clustering algorithms to reveal meaningful patterns among a vast amount of unstructured financial data. However, these algorithms suffer from a lack of interpretability that is required both at a business and regulatory level. In order to overcome this issue, we propose a novel two-steps method to explain clusters. A classifier is first trained to predict the clusters labels, then the Single Feature Introduction Test (SFIT) method is run on the model to identify the statistically significant features that characterise each cluster. We describe a real wealth management compliance use-case that highlights the necessity of such an interpretable clustering method. We illustrate the performance of our method using simulated data and through an experiment on financial ratios of U.S. companies.

stat.AP↗

arXiv2019

Computationally Efficient Feature Significance and Importance for Machine Learning Models

We develop a simple and computationally efficient significance test for the features of a machine learning model. Our forward-selection approach applies to any model specification, learning task and variable type. The test is non-asymptotic, straightforward to implement, and does not require model refitting. It identifies the statistically significant features as well as feature interactions of any order in a hierarchical manner, and generates a model-free notion of feature importance. Experimental and empirical results illustrate its performance.

stat.ML↗

arXiv2018

Sensitivity based Neural Networks Explanations

Although neural networks can achieve very high predictive performance on various different tasks such as image recognition or natural language processing, they are often considered as opaque "black boxes". The difficulty of interpreting the predictions of a neural network often prevents its use in fields where explainability is important, such as the financial industry where regulators and auditors often insist on this aspect. In this paper, we present a way to assess the relative input features importance of a neural network based on the sensitivity of the model output with respect to its input. This method has the advantage of being fast to compute, it can provide both global and local levels of explanations and is applicable for many types of neural network architectures. We illustrate the performance of this method on both synthetic and real data and compare it with other interpretation techniques. This method is implemented into an open-source Python package that allows its users to easily generate and visualize explanations for their neural networks.

stat.ML↗

arXiv2018

Deep Learning for Mortgage Risk

We develop a deep learning model of multi-period mortgage risk and use it to analyze an unprecedented dataset of origination and monthly performance records for over 120 million mortgages originated across the US between 1995 and 2014. Our estimators of term structures of conditional probabilities of prepayment, foreclosure and various states of delinquency incorporate the dynamics of a large number of loan-specific as well as macroeconomic variables down to the zip-code level. The estimators uncover the highly nonlinear nature of the relationship between the variables and borrower behavior, especially prepayment. They also highlight the effects of local economic conditions on borrower behavior. State unemployment has the greatest explanatory power among all variables, offering strong evidence of the tight connection between housing finance markets and the macroeconomy. The sensitivity of a borrower to changes in unemployment strongly depends upon current unemployment. It also significantly varies across the entire borrower population, which highlights the interaction of unemployment and many other variables. These findings have important implications for mortgage-backed security investors, rating agencies, and housing finance policymakers.

q-fin.ST↗

arXiv2015

Large Portfolio Asymptotics for Loss From Default

We prove a law of large numbers for the loss from default and use it for approximating the distribution of the loss from default in large, potentially heterogenous portfolios. The density of the limiting measure is shown to solve a non-linear SPDE, and the moments of the limiting measure are shown to satisfy an infinite system of SDEs. The solution to this system leads to %the solution to the SPDE through an inverse moment problem, and to the distribution of the limiting portfolio loss, which we propose as an approximation to the loss distribution for a large portfolio. Numerical tests illustrate the accuracy of the approximation, and highlight its computational advantages over a direct Monte Carlo simulation of the original stochastic system.

q-fin.RM↗

arXiv2015

Fluctuation Analysis for the Loss From Default

We analyze the fluctuation of the loss from default around its large portfolio limit in a class of reduced-form models of correlated firm-by-firm default timing. We prove a weak convergence result for the fluctuation process and use it for developing a conditionally Gaussian approximation to the loss distribution. Numerical results illustrate the accuracy and computational efficiency of the approximation.

math.PR↗

arXiv2013

Default clustering in large portfolios: Typical events

We develop a dynamic point process model of correlated default timing in a portfolio of firms, and analyze typical default profiles in the limit as the size of the pool grows. In our model, a firm defaults at a stochastic intensity that is influenced by an idiosyncratic risk process, a systematic risk process common to all firms, and past defaults. We prove a law of large numbers for the default rate in the pool, which describes the "typical" behavior of defaults.

q-fin.RM↗