arXiv research

Short-horizon bias causes meta-optimization to favor small learning rates.

The paper explores MAB strategies for very short horizons, introducing new methods and showing improved performance.

New algorithm offers costless model selection in contextual bandits.

Financial event studies often misestimate causal effects due to misspecified factor models.

Filters on order flow improve short-term market directionality.

A new model for heterogeneous populations optimizes consumption and investment over short horizons.

The study reveals distinct patterns in retail investors' holding periods affecting stock returns.

Reward tweaking optimizes behavior for long-term goals by adjusting the reward function.

This paper improves LSTM networks for long-term forecasts.

Long horizon reinforcement learning is as hard as short horizon learning.

DeFi exploits lead to reduced CP spreads, contrary to contagion hypothesis.

This paper develops a method to select a reference contract for multi-contract quoting to minimize execution risk.

We provide complete source code for building a fundamental industry classification based on publically available and freely downloadable data. We compare various fundamental industry classifications by running a horserace of short-horizon trading signals (alphas) utilizing open source heterotic risk models (https://ssr…

Hybrid ML ensemble predicts market risk and generates alpha.

Deep forecasting models show output heads significantly improve performance on fat-tailed financial returns.

Paper uses SciPhyRL for optimizing large institutional portfolios.

We propose a 4-factor model for overnight returns and give explicit definitions of our 4 factors. Long horizon fundamental factors such as value and growth lack predictive power for overnight (or similar short horizon) returns and are not included. All 4 factors are constructed based on intraday price and volume data a…

We give a complete algorithm and source code for constructing general multifactor risk models (for equities) via any combination of style factors, principal components (betas) and/or industry factors. For short horizons we employ the Russian-doll risk model construction to obtain a nonsingular factor covariance matrix.…

Study shows priority access in ELA auctions is less valuable due to volatility risks.

Inverse statistics in economics is considered. We argue that the natural candidate for such statistics is the investment horizons distribution. This distribution of waiting times needed to achieve a predefined level of return is obtained from (often detrended) historic asset prices. Such a distribution typically goes t…

Short-term incentives lead to riskier trading strategies.

We give a simple explicit algorithm for building multi-factor risk models. It dramatically reduces the number of or altogether eliminates the risk factors for which the factor covariance matrix needs to be computed. This is achieved via a nested "Russian-doll" embedding: the factor covariance matrix itself is modeled v…

Realized moments of higher order computed from intraday returns are introduced in recent years. The literature indicates that realized skewness is an important factor in explaining future asset returns. However, the literature mainly focuses on the whole market and on the monthly or weekly scale. In this paper, we cond…

Foundation models improve on econometric benchmarks for forecasting volatility, but vary widely across models.

Bayesian machine learning methods improve nowcasting with mixed frequency data.

Generative AI improves stock selection by synthesizing features from diverse data sources.

The inverse statistics is the distribution of waiting times needed to achieve a predefined level of return obtained from (detrended) historic asset prices \cite{optihori,gainloss}. Such a distribution typically goes through a maximum at a time coined the {\em optimal investment horizon}, $τ^*_ρ$, which defines the most…

A new method for risk-averse decision-making in Markov processes with improved regret bounds.

Research shows bias in machine learning can be due to algorithmic flaws, not just data.

Project forecasts liquidity withdrawal using machine learning models.

New feature selection methods reduce bias amplification in models.

Financial LLMs need explicit bias consideration to avoid invalid results.

Solves VaR-constrained portfolio optimization in markets with stochastic volatility.

It has been noticed that some external CVIs exhibit a preferential bias towards a larger or smaller number of clusters which is monotonic (directly or inversely) in the number of clusters in candidate partitions. This type of bias is caused by the functional form of the CVI model. For example, the popular Rand index (R…

We analyze bias in post-bandit inference for stable index algorithms.

Mitigates gender bias amplification in model predictions.

Study uses deep learning to predict stock trends with superior performance.

Depth uncertainty networks don't improve with bias correction, contrary to expectations.

We quantify causal bias in continuous treatment settings.

Generically learns movement control policies from exploration data.

Bayesian model predicts interest rates with short-term accuracy and long-term stability.

The paper introduces Relative Bias to quantify LLM bias systematically.

Interpolated-MLPs control inductive bias for better performance in low-compute tasks.

SSMs have a built-in bias towards low-frequency components, which can be adjusted.

This paper assesses biases in contextualized word representations.

A bias classifier is introduced to resist adversarial attacks.

UBM transfers bias mitigation from upstream to downstream tasks efficiently.

Active learning introduces bias; this paper fixes it.