XGBoost Forecasting of NEPSE Index Log Returns with Walk Forward Validation ArXiv ID: 2601.08896 “View on arXiv” Authors: Sahaj Raj Malla, Shreeyash Kayastha, Rumi Suwal, Harish Chandra Bhandari, Rajendra Adhikari Abstract This study develops a robust machine learning framework for one-step-ahead forecasting of daily log-returns in the Nepal Stock Exchange (NEPSE) Index using the XGBoost regressor. A comprehensive feature set is engineered, including lagged log-returns (up to 30 days) and established technical indicators such as short- and medium-term rolling volatility measures and the 14-period Relative Strength Index. Hyperparameter optimization is performed using Optuna with time-series cross-validation on the initial training segment. Out-of-sample performance is rigorously assessed via walk-forward validation under both expanding and fixed-length rolling window schemes across multiple lag configurations, simulating real-world deployment and avoiding lookahead bias. Predictive accuracy is evaluated using root mean squared error, mean absolute error, coefficient of determination (R-squared), and directional accuracy on both log-returns and reconstructed closing prices. Empirical results show that the optimal configuration, an expanding window with 20 lags, outperforms tuned ARIMA and Ridge regression benchmarks, achieving the lowest log-return RMSE (0.013450) and MAE (0.009814) alongside a directional accuracy of 65.15%. While the R-squared remains modest, consistent with the noisy nature of financial returns, primary emphasis is placed on relative error reduction and directional prediction. Feature importance analysis and visual inspection further enhance interpretability. These findings demonstrate the effectiveness of gradient boosting ensembles in modeling nonlinear dynamics in volatile emerging market time series and establish a reproducible benchmark for NEPSE Index forecasting. ...

Enhancing Portfolio Optimization with Deep Learning Insights ArXiv ID: 2601.07942 “View on arXiv” Authors: Brandon Luo, Jim Skufca Abstract Our work focuses on deep learning (DL) portfolio optimization, tackling challenges in long-only, multi-asset strategies across market cycles. We propose training models with limited regime data using pre-training techniques and leveraging transformer architectures for state variable inclusion. Evaluating our approach against traditional methods shows promising results, demonstrating our models’ resilience in volatile markets. These findings emphasize the evolving landscape of DL-driven portfolio optimization, stressing the need for adaptive strategies to navigate dynamic market conditions and improve predictive accuracy. ...

Non-Convex Portfolio Optimization via Energy-Based Models: A Comparative Analysis Using the Thermodynamic HypergRaphical Model Library (THRML) for Index Tracking ArXiv ID: 2601.07792 “View on arXiv” Authors: Javier Mancilla, Theodoros D. Bouloumis, Frederic Goguikian Abstract Portfolio optimization under cardinality constraints transforms the classical Markowitz mean-variance problem from a convex quadratic problem into an NP-hard combinatorial optimization problem. This paper introduces a novel approach using THRML (Thermodynamic HypergRaphical Model Library), a JAX-based library for building and sampling probabilistic graphical models that reformulates index tracking as probabilistic inference on an Ising Hamiltonian. Unlike traditional methods that seek a single optimal solution, THRML samples from the Boltzmann distribution of high-quality portfolios using GPU-accelerated block Gibbs sampling, providing natural regularization against overfitting. We implement three key innovations: (1) dynamic coupling strength that scales inversely with market volatility (VIX), adapting diversification pressure to market regimes; (2) rebalanced bias weights prioritizing tracking quality over momentum for index replication; and (3) sector-aware post-processing ensuring institutional-grade diversification. Backtesting on a 100-stock S and P 500 universe from 2023 to 2025 demonstrates that THRML achieves 4.31 percent annualized tracking error versus 5.66 to 6.30 percent for baselines, while simultaneously generating 128.63 percent total return against the index total return of 79.61 percent. The Diebold-Mariano test confirms statistical significance with p less than 0.0001 across all comparisons. These results position energy-based models as a promising paradigm for portfolio construction, bridging statistical mechanics and quantitative finance. ...

Optimal Option Portfolios for Student t Returns ArXiv ID: 2601.07991 “View on arXiv” Authors: Kyle Sung, Traian A. Pirvu Abstract We provide an explicit solution for optimal option portfolios under variance and Value at Risk (VaR) minimization when the underlying returns follow a Student t-distribution. The novelty of our paper is the departure from the traditional normal returns setting. Our main contribution is the methodology for obtaining optimal portfolios. Numerical experiments reveal that, as expected, the optimal variance and VaR portfolio compositions differ by a significant amount, suggesting that more realistic tail risk settings can lead to potentially more realistic portfolio allocations. ...

Physics-Informed Singular-Value Learning for Cross-Covariances Forecasting in Financial Markets ArXiv ID: 2601.07687 “View on arXiv” Authors: Efstratios Manolakis, Christian Bongiorno, Rosario Nunzio Mantegna Abstract A new wave of work on covariance cleaning and nonlinear shrinkage has delivered asymptotically optimal analytical solutions for large covariance matrices. Building on this progress, these ideas have been generalized to empirical cross-covariance matrices, whose singular-value shrinkage characterizes comovements between one set of assets and another. Existing analytical cross-covariance cleaners are derived under strong stationarity and large-sample assumptions, and they typically rely on mesoscopic regularity conditions such as bounded spectra; macroscopic common modes (e.g., a global market factor) violate these conditions. When applied to real equity returns, where dependence structures drift over time and global modes are prominent, we find that these theoretically optimal formulas do not translate into robust out-of-sample performance. We address this gap by designing a random-matrix-inspired neural architecture that operates in the empirical singular-vector basis and learns a nonlinear mapping from empirical singular values to their corresponding cleaned values. By construction, the network can recover the analytical solution as a special case, yet it remains flexible enough to adapt to non-stationary dynamics and mode-driven distortions. Trained on a long history of equity returns, the proposed method achieves a more favorable bias-variance trade-off than purely analytical cleaners and delivers systematically lower out-of-sample cross-covariance prediction errors. Our results demonstrate that combining random-matrix theory with machine learning makes asymptotic theories practically effective in realistic time-varying markets. ...

Temporal-Aligned Meta-Learning for Risk Management: A Stacking Approach for Multi-Source Credit Scoring ArXiv ID: 2601.07588 “View on arXiv” Authors: O. Didkovskyi, A. Vidali, N. Jean, G. Le Pera Abstract This paper presents a meta-learning framework for credit risk assessment of Italian Small and Medium Enterprises (SMEs) that explicitly addresses the temporal misalignment of credit scoring models. The approach aligns financial statement reference dates with evaluation dates, mitigating bias arising from publication delays and asynchronous data sources. It is based on a two-step temporal decomposition that at first estimates annual probabilities of default (PDs) anchored to balance-sheet reference dates (December 31st) through a static model. Then it models the monthly evolution of PDs using higher-frequency behavioral data. Finally, we employ stacking-based architecture to aggregate multiple scoring systems, each capturing complementary aspects of default risk, into a unified predictive model. In this way, first level model outputs are treated as learned representations that encode non-linear relationships in financial and behavioral indicators, allowing integration of new expert-based features without retraining base models. This design provides a coherent and interpretable solution to challenges typical of low-default environments, including heterogeneous default definitions and reporting delays. Empirical validation shows that the framework effectively captures credit risk evolution over time, improving temporal consistency and predictive stability relative to standard ensemble methods. ...

The Limits of Complexity: Why Feature Engineering Beats Deep Learning in Investor Flow Prediction ArXiv ID: 2601.07131 “View on arXiv” Authors: Sungwoo Kang Abstract The application of machine learning to financial prediction has accelerated dramatically, yet the conditions under which complex models outperform simple alternatives remain poorly understood. This paper investigates whether advanced signal processing and deep learning techniques can extract predictive value from investor order flows beyond what simple feature engineering achieves. Using a comprehensive dataset of 2.79 million observations spanning 2,439 Korean equities from 2020–2024, we apply three methodologies: \textit{“Independent Component Analysis”} (ICA) to recover latent market drivers, \textit{“Wavelet Coherence”} analysis to characterize multi-scale correlation structure, and \textit{“Long Short-Term Memory”} (LSTM) networks with attention mechanisms for non-linear prediction. Our results reveal a striking finding: a parsimonious linear model using market capitalization-normalized flows (``Matched Filter’’ preprocessing) achieves a Sharpe ratio of 1.30 and cumulative return of 272.6%, while the full ICA-Wavelet-LSTM pipeline generates a Sharpe ratio of only 0.07 with a cumulative return of $-5.1%$. The raw LSTM model collapsed to predicting the unconditional mean, achieving a hit rate of 47.5% – worse than random. We conclude that in low signal-to-noise financial environments, domain-specific feature engineering yields substantially higher marginal returns than algorithmic complexity. These findings establish important boundary conditions for the application of deep learning to financial prediction. ...

Deep Reinforcement Learning for Optimum Order Execution: Mitigating Risk and Maximizing Returns ArXiv ID: 2601.04896 “View on arXiv” Authors: Khabbab Zakaria, Jayapaulraj Jerinsh, Andreas Maier, Patrick Krauss, Stefano Pasquali, Dhagash Mehta Abstract Optimal Order Execution is a well-established problem in finance that pertains to the flawless execution of a trade (buy or sell) for a given volume within a specified time frame. This problem revolves around optimizing returns while minimizing risk, yet recent research predominantly focuses on addressing one aspect of this challenge. In this paper, we introduce an innovative approach to Optimal Order Execution within the US market, leveraging Deep Reinforcement Learning (DRL) to effectively address this optimization problem holistically. Our study assesses the performance of our model in comparison to two widely employed execution strategies: Volume Weighted Average Price (VWAP) and Time Weighted Average Price (TWAP). Our experimental findings clearly demonstrate that our DRL-based approach outperforms both VWAP and TWAP in terms of return on investment and risk management. The model’s ability to adapt dynamically to market conditions, even during periods of market stress, underscores its promise as a robust solution. ...

Forecasting Equity Correlations with Hybrid Transformer Graph Neural Network ArXiv ID: 2601.04602 “View on arXiv” Authors: Jack Fanshawe, Rumi Masih, Alexander Cameron Abstract This paper studies forward-looking stock-stock correlation forecasting for S&P 500 constituents and evaluates whether learned correlation forecasts can improve graph-based clustering used in basket trading strategies. We cast 10-day ahead correlation prediction in Fisher-z space and train a Temporal-Heterogeneous Graph Neural Network (THGNN) to predict residual deviations from a rolling historical baseline. The architecture combines a Transformer-based temporal encoder, which captures non-stationary, complex, temporal dependencies, with an edge-aware graph attention network that propagates cross-asset information over the equity network. Inputs span daily returns, technicals, sector structure, previous correlations, and macro signals, enabling regime-aware forecasts and attention-based feature and neighbor importance to provide interpretability. Out-of-sample results from 2019-2024 show that the proposed model meaningfully reduces correlation forecasting error relative to rolling-window estimates. When integrated into a graph-based clustering framework, forward-looking correlations produce adaptable and economically meaningfully baskets, particularly during periods of market stress. These findings suggest that improvements in correlation forecasts translate into meaningful gains during portfolio construction tasks. ...

Forecasting the U.S. Treasury Yield Curve: A Distributionally Robust Machine Learning Approach ArXiv ID: 2601.04608 “View on arXiv” Authors: Jinjun Liu, Ming-Yen Cheng Abstract We study U.S. Treasury yield curve forecasting under distributional uncertainty and recast forecasting as an operations research and managerial decision problem. Rather than minimizing average forecast error, the forecaster selects a decision rule that minimizes worst case expected loss over an ambiguity set of forecast error distributions. To this end, we propose a distributionally robust ensemble forecasting framework that integrates parametric factor models with high dimensional nonparametric machine learning models through adaptive forecast combinations. The framework consists of three machine learning components. First, a rolling window Factor Augmented Dynamic Nelson Siegel model captures level, slope, and curvature dynamics using principal components extracted from economic indicators. Second, Random Forest models capture nonlinear interactions among macro financial drivers and lagged Treasury yields. Third, distributionally robust forecast combination schemes aggregate heterogeneous forecasts under moment uncertainty, penalizing downside tail risk via expected shortfall and stabilizing second moment estimation through ridge regularized covariance matrices. The severity of the worst case criterion is adjustable, allowing the forecaster to regulate the trade off between robustness and statistical efficiency. Using monthly data, we evaluate out of sample forecasts across maturities and horizons from one to twelve months ahead. Adaptive combinations deliver superior performance at short horizons, while Random Forest forecasts dominate at longer horizons. Extensions to global sovereign bond yields confirm the stability and generalizability of the proposed framework. ...