We develop a simple stock selection model to explain why active equity managers tend to underperform a benchmark index. We motivate our model with the empirical observation that the best performing stocks in a broad market index often perform much better than the other stocks in the index. Randomly selecting a subset o…
New methods for handling time-varying label noise in time series classification.
problem Temporal label noise in time series classification tasks.
method Proposed methods to estimate temporal label noise function directly from data.
result Our methods lead to state-of-the-art performance under diverse types of temporal label noise.
ETFs with 2x and 3x leverage underperformed the S&P 500 index due to compounding and volatility.
problem ETFs with higher leverage failed to match the performance of the underlying index.
method Analyzed the performance of leveraged ETFs compared to the S&P 500 index, accounting for compounding and volatility.
result Two-thirds of the underperformance was due to compounding and volatility, with the rest due to covariance.
Selecting an optimizer is a central step in the contemporary deep learning pipeline. In this paper, we demonstrate the sensitivity of optimizer comparisons to the hyperparameter tuning protocol. Our findings suggest that the hyperparameter search space may be the single most important factor explaining the rankings obt…
This paper studies the empirical tracking performance of leveraged ETFs on gold, and their price relationships with gold spot and futures. For tracking the gold spot, we find that our optimized portfolios with short-term gold futures are highly effective in replicating prices. The market-traded gold ETF (GLD) also exhi…
Multi-task learning (MTL) refers to the paradigm of learning multiple related tasks together. In contrast, in single-task learning (STL) each individual task is learned independently. MTL often leads to better trained models because they can leverage the commonalities among related tasks. However, because MTL algorithm…
ChatGPT struggles in predicting stock movements, underperforming traditional methods.
problem Predicting stock market movements using ChatGPT.
method Zero-shot analysis of ChatGPT's multimodal stock prediction capabilities.
result ChatGPT underperforms traditional methods and state-of-the-art models in predicting stock movements.
BS-NAS broadens and shrinks search space for optimal neural architectures.
problem Suboptimal channel numbers and model averaging effects in One-Shot NAS methods.
method Broadening with spring block for channel search, shrinking with underperforming operations removal, evolutionary algorithm for optimal architecture search.
result BS-NAS achieves state-of-the-art performance on ImageNet.
A financial market is called "diverse" if no single stock is ever allowed to dominate the entire market in terms of relative capitalization. In the context of the standard Ito-process model initiated by Samuelson (1965) we formulate this property (and the allied, successively weaker notions of "weak diversity" and "asy…
New local-search methods close the gap in sparse tensor PCA.
problem Sparse tensor PCA underperforms compared to other methods.
method Proposes new local-search methods including greedy and random-threshold variants.
result Proves local-search methods close the gap to best known polynomial-time procedures.
Leveraged ETFs can outperform their targets in certain market conditions, contrary to the volatility drag hypothesis.
problem The long-term performance decay of leveraged ETFs due to volatility drag.
method Unified framework incorporating AR(1) and AR-GARCH models, continuous-time regime switching, and flexible rebalancing frequencies.
result Return dynamics, including return autocorrelation, volatility clustering, and regime persistence, determine LETF performance.
Study finds rough volatility models underperform in SPX option pricing.
problem Inconsistency of rough volatility models with SPX option prices.
method Empirical study using SPX options data, comparing rough and Markovian models.
result Rough volatility models with H∈(0,1/2) are inconsistent with SPX smiles, especially at short maturities. Federated learning aims to jointly learn statistical models over massively distributed remote devices. In this work, we propose FedDANE, an optimization method that we adapt from DANE, a method for classical distributed optimization, to handle the practical constraints of federated learning. We provide convergence guar…
COHORTNEY groups web users based on activity patterns.
problem Lack of academic discussion on cohort analysis for user behavior.
method Unsupervised non-parametric machine learning approach.
result COHORTNEY outperforms traditional methods in cohort analysis.
With the increasing size of today's data sets, finding the right parameter configuration in model selection via cross-validation can be an extremely time-consuming task. In this paper we propose an improved cross-validation procedure which uses nonparametric testing coupled with sequential analysis to determine the bes…
We obtain a lower asymptotic bound on the decay rate of the probability of a portfolio's underperformance against a benchmark over a large time horizon. It is assumed that the prices of the securities are governed by geometric Brownian motions with the coefficients depending on an economic factor, possibly nonlinearly.…
Fundamental portfolio beats market portfolio under certain conditions.
problem Empirical evidence of fundamental portfolio outperformance.
method Theoretical foundation based on stock price reversion to fundamental values.
result Fundamental portfolio outperforms market portfolio under strong reversion conditions.
Framework selects real estate redevelopment uses by integrating value, risk, complexity, and irreversibility.
problem Persistent underperformance of real estate assets due to structural misalignment.
method Integrates real-options logic and multi-criteria decision analysis.
result Reduces over-complexification and misalignment in strategic use selection.
FinFlowRL combines imitation and reinforcement learning for better financial control.
problem Traditional stochastic control methods fail in real-world finance due to changing market conditions.
method FinFlowRL uses imitation learning to pretrain an adaptive meta policy, then finetunes it with reinforcement learning.
result FinFlowRL consistently outperforms individual strategies across various market conditions.
Neuro-inspired recurrent neural network algorithms, such as echo state networks, are computationally lightweight and thereby map well onto untethered devices. The baseline echo state network algorithms are shown to be efficient in solving small-scale spatio-temporal problems. However, they underperform for complex task…
Machine learning portfolios perform well with simple imputation of missing data.
problem Handling missing values in machine learning portfolios constructed from cross-sectional return predictors.
method Simple imputation with cross-sectional means compared to rigorous expectation-maximization methods.
result Simple imputation performs well due to the structure of missing data.
Quantum model outperforms classical in training but underperforms in real-world metrics.
problem Mismatch between proxy reward signals and true investment objectives in financial domains.
method Hybrid quantum-classical reinforcement learning framework with automated feature engineering.
result Quantum models achieve higher training rewards but underperform in real-world metrics.
Study introduces new financial ratios for better predicting company performance.
problem Lack of progress in predicting company performance and assessing financial risks.
method Developed new financial and macroeconomic ratios, supervised learning models, and Bayesian models.
result New proposed variables improve model accuracy and FNN performs best across multiple tasks.
Study reveals AI skin cancer classifiers underperform for darker skin phototypes, advocating for fairness auditing.
problem AI bias in dermatology, particularly for darker skin phototypes.
method Predictive Representativity (PR) framework, evaluating classifiers on HAM10000 and BOSQUE Test sets.
result Substantial performance disparities by skin phototype, highlighting AI bias.
Improved Thompson Sampling outperforms existing Bayesian optimization methods.
problem Thompson Sampling's performance in Bayesian optimization is suboptimal compared to other methods.
method Developed Stagger Thompson Sampler (STS), which more precisely samples the optimal arm with less computation.
result STS outperforms TS, PSS, and other acquisition methods in various optimization tasks.
This study improves hyperparameter optimization for categorical and non-normal data.
problem Bayesian hyperparameter optimization struggles with categorical hyperparameters and non-normal data.
method Integrates conformalized quantile regression to address estimation weaknesses and provides robust calibration guarantees.
result Quantile surrogate architectures and acquisition functions yield superior performance compared to existing methods.
Calibrating a trading rule using a historical simulation (also called backtest) contributes to backtest overfitting, which in turn leads to underperformance. In this paper we propose a procedure for determining the optimal trading rule (OTR) without running alternative model configurations through a backtest engine. We…
A new method for efficient BNC parameter estimation outperforms HDP smoothing.
problem Efficiently estimating parameters for Bayesian network classifiers to match or exceed random forest performance.
method Uses log-linear regression to approximate hierarchical Dirichlet process (HDP) smoothing, making the approach simpler and faster.
result Our method outperforms HDP smoothing while being orders of magnitude faster and competitive with random forests.
Pairs trading strategy improved using Ornstein-Uhlenbeck process.
problem Improving pairs trading strategy effectiveness.
method Used Ornstein-Uhlenbeck process to model stock price spreads.
result OU model captures signals and trends effectively but underperforms compared to naive model.
ZeroS improves Transformers by adding negative weights, matching or beating softmax attention.
problem Limited performance of linear attention methods, especially in long context sequences.
method Proposes Zero-Sum Linear Attention (ZeroS) that removes the zero-order term and reweights zero-sum softmax residuals.
result ZeroS matches or exceeds standard softmax attention across various benchmarks, theoretically expanding representable functions.
Recent advances in deep reinforcement learning have made significant strides in performance on applications such as Go and Atari games. However, developing practical methods to balance exploration and exploitation in complex domains remains largely unsolved. Thompson Sampling and its extension to reinforcement learning…
Study uses zero-shot models to forecast mortality rates globally.
problem Forecasting mortality rates without task-specific fine-tuning.
method Two state-of-the-art foundation models (TimesFM and CHRONOS) and traditional/machine learning methods were evaluated.
result CHRONOS outperformed traditional methods for shorter-term forecasts, but TimesFM consistently underperformed.
This thesis identifies share buybacks and predicts their impact on stock performance.
problem Recognizing and predicting the impact of share buybacks on stock performance.
method NLP approaches for automated detection of share buybacks, machine learning models for prediction.
result Most companies underperform after a share buyback, but some significantly outperform.
AlphaZeroBeta uses deep reinforcement learning for market-neutral portfolios, outperforming traditional methods.
problem Traditional portfolio management methods often fail during market regime shifts or when assumptions break down.
method Combines a composite reward function and CNN-GRU policy trained end-to-end via Recurrent PPO.
result Achieves higher Sharpe ratios than baselines while maintaining near-zero benchmark correlations.
The use of L1 regularisation for sparse learning has generated immense research interest, with successful application in such diverse areas as signal acquisition, image coding, genomics and collaborative filtering. While existing work highlights the many advantages of L1 methods, in this paper we find that L1 regularis…
Expanding self-supervised learning to diverse domains reveals Rotation's semantic superiority.
problem Limited self-supervised learning experiments on diverse domains.
method Experimented on various domains (satellite, textural, biological) using popular self-supervised methods.
result Rotation task is semantically most meaningful, with other tasks relying on distribution rather than semantic understanding.
Study finds traditional technical indicators underperform in high-frequency trading, suggesting risk management over prediction.
problem Inadequately explored effectiveness of technical indicators in high-frequency trading, particularly at minute-level frequency.
method Evaluation of random forest models with traditional technical indicators on minute-level SPY data.
result In-sample performance is superior to out-of-sample, with risk-adjusted metrics not outperforming a simple buy-and-hold strategy.
BLAE solves batched linear bandits with optimal regret and practical performance.
problem Batched linear bandit problem with limited adaptivity.
method Integrates arm elimination with regularized G-optimal design, achieving minimax optimal regret.
result Achieves minimax optimal regret in both large-K and small-K regimes with O(loglogT) batches. We present results on simulations of a stock market with heterogeneous, cumulative information setup. We find a non-monotonic behaviour of traders' returns as a function of their information level. Particularly, the average informed agents underperform random traders; only the most informed agents are able to beat the …
Recently, neural approaches to coherence modeling have achieved state-of-the-art results in several evaluation tasks. However, we show that most of these models often fail on harder tasks with more realistic application scenarios. In particular, the existing models underperform on tasks that require the model to be sen…
Graph attention networks improve performance on heterogeneous graphs.
problem Complex performance of GNNs on heterogeneous graphs.
method Integrating positional encodings into graph attention networks.
result Graph attention networks excel in node classification and link prediction.
QUAM improves uncertainty quantification in deep learning models.
problem Estimating epistemic uncertainty in deep learning models.
method QUAM identifies regions with high divergence between predictions and a reference model.
result QUAM has lower approximation error of epistemic uncertainty compared to previous methods.
D3M debiases models by selectively removing problematic examples.
problem Model failures on underrepresented subgroups.
method Isolates and removes specific training examples that cause failures.
result Efficiently trains debiased classifiers with minimal example removal.
Corrected CBOW performs similarly to Skip-gram.
problem CBOW embeddings underperform Skip-gram embeddings in word2vec.
method Fixed a bug in CBOW gradient update to improve performance.
result Corrected CBOW embeddings are competitive with Skip-gram on various tasks.
Enhanced pairs trading with Black-Litterman model outperforms market indexes.
problem Underperformance of pairs trading in volatile or distressed markets.
method Integrated Black-Litterman model with pairs trading strategy.
result Superior performance compared to S\&P 500 index under various market conditions.
DiBO uses diffusion models to optimize high-dimensional black-box functions efficiently.
problem Optimizing high-dimensional and complex black-box functions efficiently.
method DiBO iterates two stages: training a diffusion model and casting candidate selection as posterior inference.
result DiBO outperforms state-of-the-art baselines across synthetic and real-world tasks.
Maximizes stock portfolio predictability using machine learning.
problem Improving stock portfolio performance through predictive modeling.
method Optimal constrained weights in the MPP constructed using Elastic Net, Random Forest, and Support Vector Regression models.
result MPP portfolios can outperform or underperform the index based on the time period.
Method enhances anomaly detection using contrastive learning and out-of-distribution data.
problem Improving anomaly detection in datasets with limited out-of-distribution data.
method Proposes a contrastive learning method that incorporates out-of-distribution data to enhance anomaly detection performance.
result The method significantly improves anomaly detection performance, even with limited out-of-distribution data.